Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wandb/run-20241225_001558-sxxraa4n/run-sxxraa4n.wandb filter=lfs diff=lfs merge=lfs -text
+wandb/run-20241225_152744-sac86tlv/run-sac86tlv.wandb filter=lfs diff=lfs merge=lfs -text
+wandb/run-20241226_145403-c7ovtvny/run-c7ovtvny.wandb filter=lfs diff=lfs merge=lfs -text
+wandb/run-20241226_224836-fta6xses/run-fta6xses.wandb filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.13208570653647952,
+    "num_input_tokens_seen": 7732199424,
+    "train_loss": 0.059379862848258066,
+    "train_runtime": 15793.1588,
+    "train_samples_per_second": 0.467,
+    "train_steps_per_second": 0.233
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 524288,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 128000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c26dc16ca4103321217d048b95c093a962f9ac89050c3a8dd174346e207b3e7
+size 4886466168

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4809e517ef7c60c0f63a0c81f1adcf297ffcf154e63b2a6db6d726dda1c5308c
+size 4832007448

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e660ec0d0db2990b9b6ceae9215fbe5c95c1f8340fec45431712f87d49a9bb87
+size 4999813112

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a3bbc5a9053dbc89101e717c9e0a761bde1c3d70e098e721f5b3616924ed33
+size 4999813128

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1a00576deac5ab4ea67235bca5a8f00e16426c8d1b8664925073d5603d77af
+size 4832007496

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08282142ed7be238fc32e6843b2b02b98620c7addda0a6541f36f5632788d1c0
+size 4999813120

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c47188f45c65ffd7a396325f96621c61ef98c383daa96752fbe7c7975917c9ad
+size 2571158184

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 32121044992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2062 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.13208570653647952,
+    "num_input_tokens_seen": 7732199424,
+    "train_loss": 0.059379862848258066,
+    "train_runtime": 15793.1588,
+    "train_samples_per_second": 0.467,
+    "train_steps_per_second": 0.233
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6940cd967bdcf38d3c718ee07e93eda4a57d949efbc9b707df65a82dd8cc581e
+size 5560

wandb/debug.log

@@ -0,0 +1,32 @@
+2024-12-26 22:48:36,725 INFO    MainThread:839109 [wandb_setup.py:_flush():76] Current SDK version is 0.17.3
+2024-12-26 22:48:36,725 INFO    MainThread:839109 [wandb_setup.py:_flush():76] Configure stats pid to 839109
+2024-12-26 22:48:36,725 INFO    MainThread:839109 [wandb_setup.py:_flush():76] Loading settings from /home/ctpham_umass_edu/.config/wandb/settings
+2024-12-26 22:48:36,725 INFO    MainThread:839109 [wandb_setup.py:_flush():76] Loading settings from /work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/wandb/settings
+2024-12-26 22:48:36,725 INFO    MainThread:839109 [wandb_setup.py:_flush():76] Loading settings from environment variables: {'root_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'project': 'prolong', 'api_key': '***REDACTED***', 'mode': 'online'}
+2024-12-26 22:48:36,725 INFO    MainThread:839109 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-12-26 22:48:36,725 INFO    MainThread:839109 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'prolong-final/finetune.py', 'program_abspath': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py', 'program': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py'}
+2024-12-26 22:48:36,725 INFO    MainThread:839109 [wandb_setup.py:_flush():76] Applying login settings: {}
+2024-12-26 22:48:36,726 INFO    MainThread:839109 [wandb_init.py:_log_setup():520] Logging user logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241226_224836-fta6xses/logs/debug.log
+2024-12-26 22:48:36,726 INFO    MainThread:839109 [wandb_init.py:_log_setup():521] Logging internal logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241226_224836-fta6xses/logs/debug-internal.log
+2024-12-26 22:48:36,726 INFO    MainThread:839109 [wandb_init.py:init():560] calling init triggers
+2024-12-26 22:48:36,726 INFO    MainThread:839109 [wandb_init.py:init():567] wandb.init called with sweep_config: {}
+config: {}
+2024-12-26 22:48:36,726 INFO    MainThread:839109 [wandb_init.py:init():610] starting backend
+2024-12-26 22:48:36,726 INFO    MainThread:839109 [wandb_init.py:init():614] setting up manager
+2024-12-26 22:48:36,729 INFO    MainThread:839109 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-12-26 22:48:36,732 INFO    MainThread:839109 [wandb_init.py:init():622] backend started and connected
+2024-12-26 22:48:36,740 INFO    MainThread:839109 [wandb_init.py:init():711] updated telemetry
+2024-12-26 22:48:36,765 INFO    MainThread:839109 [wandb_init.py:init():744] communicating run to backend with 90.0 second timeout
+2024-12-26 22:48:37,011 INFO    MainThread:839109 [wandb_run.py:_on_init():2402] communicating current version
+2024-12-26 22:48:37,074 INFO    MainThread:839109 [wandb_run.py:_on_init():2411] got version response upgrade_message: "wandb version 0.19.1 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2024-12-26 22:48:37,074 INFO    MainThread:839109 [wandb_init.py:init():795] starting run threads in backend
+2024-12-26 22:48:44,772 INFO    MainThread:839109 [wandb_run.py:_console_start():2380] atexit reg
+2024-12-26 22:48:44,773 INFO    MainThread:839109 [wandb_run.py:_redirect():2235] redirect: wrap_raw
+2024-12-26 22:48:44,773 INFO    MainThread:839109 [wandb_run.py:_redirect():2300] Wrapping output streams.
+2024-12-26 22:48:44,773 INFO    MainThread:839109 [wandb_run.py:_redirect():2325] Redirects installed.
+2024-12-26 22:48:44,775 INFO    MainThread:839109 [wandb_init.py:init():838] run started, returning control to user process
+2024-12-26 22:48:44,777 INFO    MainThread:839109 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 128256, 'max_position_embeddings': 524288, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': True, 'rope_theta': 128000000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 128000, 'pad_token_id': 0, 'eos_token_id': 128009, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': '/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/', 'transformers_version': '4.44.2', 'model_type': 'llama', 'output_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'overwrite_output_dir': False, 'do_train': True, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-06, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.05, 'warmup_steps': 0, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec26_22-45-54_gpu021', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1.0, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 200, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 1, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'disable_tqdm': True, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': True, 'fsdp': ['auto_wrap', 'offload'], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': False, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False, 'min_lr_ratio': 0.1, 'cuda_empty_cache': True, 'streaming_dataset': True, 'seq_parallel_size': 8}
+2024-12-26 22:48:44,780 INFO    MainThread:839109 [wandb_config.py:__setitem__():151] config set model/num_parameters = 1003782656 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x78858f51ed40>>
+2024-12-26 22:48:44,780 INFO    MainThread:839109 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 1003782656 None
+2024-12-27 03:13:36,487 WARNING MsgRouterThr:839109 [router.py:message_loop():77] message_loop has been closed

wandb/run-20241225_001558-sxxraa4n/files/conda-environment.yaml

@@ -0,0 +1,232 @@
+name: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final
+channels:
+  - conda-forge
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - bzip2=1.0.8=h4bc722e_7
+  - ca-certificates=2024.12.14=hbcca054_0
+  - ld_impl_linux-64=2.43=h712a8e2_2
+  - libffi=3.4.2=h7f98852_5
+  - libgcc=14.2.0=h77fa898_1
+  - libgcc-ng=14.2.0=h69a702a_1
+  - libgomp=14.2.0=h77fa898_1
+  - liblzma=5.6.3=hb9d3cd8_1
+  - liblzma-devel=5.6.3=hb9d3cd8_1
+  - libnsl=2.0.1=hd590300_0
+  - libsqlite=3.47.2=hee588c1_0
+  - libuuid=2.38.1=h0b41bf4_0
+  - libzlib=1.3.1=hb9d3cd8_2
+  - ncurses=6.5=he02047a_1
+  - openssl=3.4.0=hb9d3cd8_0
+  - pip=24.3.1=pyh8b19718_2
+  - python=3.10.0=h543edf9_3_cpython
+  - readline=8.2=h8228510_1
+  - setuptools=75.6.0=pyhff2d567_1
+  - sqlite=3.47.2=h9eae976_0
+  - tk=8.6.13=noxft_h4845f30_101
+  - wheel=0.45.1=pyhd8ed1ab_1
+  - xz=5.6.3=hbcc6ac9_1
+  - xz-gpl-tools=5.6.3=hbcc6ac9_1
+  - xz-tools=5.6.3=hb9d3cd8_1
+  - pip:
+      - accelerate==0.32.1
+      - aiohappyeyeballs==2.4.3
+      - aiohttp==3.11.2
+      - aioprometheus==23.12.0
+      - aiosignal==1.3.1
+      - annotated-types==0.7.0
+      - anthropic==0.39.0
+      - anyio==4.6.2.post1
+      - argcomplete==3.5.1
+      - arrow==1.3.0
+      - async-timeout==5.0.1
+      - attrs==24.2.0
+      - azure-core==1.32.0
+      - azure-identity==1.19.0
+      - azure-storage-blob==12.24.0
+      - azure-storage-file-datalake==12.18.0
+      - backoff==2.2.1
+      - bcrypt==4.2.0
+      - blobfile==3.0.0
+      - boto3==1.35.63
+      - botocore==1.35.63
+      - brotli==1.1.0
+      - cachetools==5.5.0
+      - certifi==2024.8.30
+      - cffi==1.17.1
+      - charset-normalizer==3.4.0
+      - circuitbreaker==2.0.0
+      - click==8.1.7
+      - cloudpickle==3.1.0
+      - compressed-tensors==0.8.0
+      - contourpy==1.3.1
+      - cramjam==2.9.0
+      - cryptography==43.0.3
+      - cycler==0.12.1
+      - datasets==2.20.0
+      - debugpy==1.8.11
+      - dill==0.3.8
+      - diskcache==5.6.3
+      - distro==1.9.0
+      - docker-pycreds==0.4.0
+      - docstring-parser==0.16
+      - einops==0.8.0
+      - fastapi==0.115.5
+      - filelock==3.16.1
+      - flash-attn==2.6.1
+      - fonttools==4.55.0
+      - frozenlist==1.5.0
+      - fsspec==2024.5.0
+      - gguf==0.10.0
+      - gitdb==4.0.11
+      - gitpython==3.1.43
+      - google-api-core==2.23.0
+      - google-auth==2.36.0
+      - google-cloud-aiplatform==1.71.1
+      - google-cloud-bigquery==3.27.0
+      - google-cloud-core==2.4.1
+      - google-cloud-resource-manager==1.13.1
+      - google-cloud-storage==2.10.0
+      - google-crc32c==1.6.0
+      - google-resumable-media==2.7.2
+      - googleapis-common-protos==1.66.0
+      - gql==3.5.0
+      - graphql-core==3.2.5
+      - grpc-google-iam-v1==0.13.1
+      - grpcio==1.68.0
+      - grpcio-status==1.62.3
+      - h11==0.14.0
+      - httpcore==1.0.7
+      - httptools==0.6.4
+      - httpx==0.27.2
+      - huggingface-hub==0.26.2
+      - idna==3.10
+      - importlib-metadata==8.5.0
+      - interegular==0.3.3
+      - ipython==8.18.0
+      - isodate==0.7.2
+      - jedi==0.19.2
+      - jinja2==3.1.4
+      - jiter==0.7.1
+      - jmespath==1.0.1
+      - jsonschema==4.23.0
+      - jsonschema-specifications==2024.10.1
+      - kiwisolver==1.4.7
+      - lark==1.2.2
+      - llvmlite==0.43.0
+      - lm-format-enforcer==0.10.9
+      - lxml==5.3.0
+      - markdown-it-py==3.0.0
+      - markupsafe==3.0.2
+      - matplotlib==3.9.2
+      - mdurl==0.1.2
+      - mosaicml-cli==0.5.34
+      - mosaicml-streaming==0.8.1
+      - mpmath==1.3.0
+      - msal==1.31.1
+      - msal-extensions==1.2.0
+      - msgpack==1.1.0
+      - msgspec==0.18.6
+      - multidict==6.1.0
+      - multiprocess==0.70.16
+      - networkx==3.4.2
+      - ninja==1.11.1.1
+      - numba==0.60.0
+      - numpy==1.26.3
+      - nvidia-cublas-cu12==12.1.3.1
+      - nvidia-cuda-cupti-cu12==12.1.105
+      - nvidia-cuda-nvrtc-cu12==12.1.105
+      - nvidia-cuda-runtime-cu12==12.1.105
+      - nvidia-cudnn-cu12==9.1.0.70
+      - nvidia-cufft-cu12==11.0.2.54
+      - nvidia-curand-cu12==10.3.2.106
+      - nvidia-cusolver-cu12==11.4.5.107
+      - nvidia-cusparse-cu12==12.1.0.106
+      - nvidia-ml-py==12.560.30
+      - nvidia-nccl-cu12==2.20.5
+      - nvidia-nvjitlink-cu12==12.4.127
+      - nvidia-nvtx-cu12==12.1.105
+      - oci==2.138.1
+      - openai==1.54.5
+      - opencv-python-headless==4.10.0.84
+      - orjson==3.10.11
+      - outlines==0.0.46
+      - packaging==24.1
+      - pandas==2.2.1
+      - paramiko==3.5.0
+      - partial-json-parser==0.2.1.1.post4
+      - pillow==10.4.0
+      - portalocker==2.10.1
+      - prometheus-client==0.21.0
+      - prometheus-fastapi-instrumentator==7.0.0
+      - prompt-toolkit==3.0.36
+      - propcache==0.2.0
+      - proto-plus==1.25.0
+      - protobuf==4.25.3
+      - py-cpuinfo==9.0.0
+      - pyairports==2.1.1
+      - pyarrow==18.0.0
+      - pyarrow-hotfix==0.6
+      - pyasn1==0.6.1
+      - pyasn1-modules==0.4.1
+      - pycountry==24.6.1
+      - pycparser==2.22
+      - pycryptodomex==3.21.0
+      - pydantic==2.9.2
+      - pydantic-core==2.23.4
+      - pyjwt==2.10.0
+      - pynacl==1.5.0
+      - pyopenssl==24.2.1
+      - pyparsing==3.2.0
+      - python-dateutil==2.9.0
+      - python-dotenv==1.0.1
+      - python-snappy==0.7.3
+      - pytz==2024.2
+      - pyyaml==6.0.2
+      - quantile-python==1.1
+      - questionary==2.0.1
+      - ray==2.39.0
+      - referencing==0.35.1
+      - regex==2023.12.25
+      - requests==2.32.3
+      - rich==13.9.4
+      - rotary-emb==0.5.2
+      - rpds-py==0.21.0
+      - rsa==4.9
+      - ruamel-yaml==0.18.6
+      - ruamel-yaml-clib==0.2.12
+      - s3transfer==0.10.3
+      - safetensors==0.4.5
+      - sentencepiece==0.1.99
+      - sentry-sdk==2.18.0
+      - setproctitle==1.3.4
+      - shapely==2.0.6
+      - smmap==5.0.1
+      - sniffio==1.3.1
+      - starlette==0.41.3
+      - sympy==1.13.1
+      - tiktoken==0.7.0
+      - tokenizers==0.19.1
+      - torch==2.4.1
+      - torchvision==0.19.1
+      - tqdm==4.66.4
+      - transformers==4.44.2
+      - triton==3.0.0
+      - types-python-dateutil==2.9.0.20241003
+      - tzdata==2024.2
+      - urllib3==2.2.3
+      - uvicorn==0.32.0
+      - uvloop==0.21.0
+      - validators==0.34.0
+      - vertexai==1.71.1
+      - wandb==0.17.3
+      - watchfiles==0.24.0
+      - websockets==11.0.3
+      - xformers==0.0.28.post1
+      - xxhash==3.5.0
+      - yarl==1.17.2
+      - zipp==3.21.0
+      - zstandard==0.22.0
+      - zstd==1.5.5.1
+prefix: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final

wandb/run-20241225_001558-sxxraa4n/files/config.yaml

@@ -0,0 +1,705 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.10.0
+    cli_version: 0.17.3
+    framework: huggingface
+    huggingface_version: 4.44.2
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    start_time: 1735085758
+    t:
+      1:
+      - 1
+      - 11
+      - 41
+      - 49
+      - 51
+      - 55
+      - 71
+      - 105
+      2:
+      - 1
+      - 11
+      - 41
+      - 49
+      - 51
+      - 55
+      - 71
+      - 105
+      3:
+      - 7
+      - 13
+      - 19
+      - 23
+      - 66
+      4: 3.10.0
+      5: 0.17.3
+      6: 4.44.2
+      8:
+      - 5
+      9:
+        1: transformers_trainer
+      13: linux-x86_64
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    - 1: train/loss
+      5: 1
+      6:
+      - 1
+    - 1: train/grad_norm
+      5: 1
+      6:
+      - 1
+    - 1: train/learning_rate
+      5: 1
+      6:
+      - 1
+    - 1: train/epoch
+      5: 1
+      6:
+      - 1
+    - 1: train/num_input_tokens_seen
+      5: 1
+      6:
+      - 1
+vocab_size:
+  desc: null
+  value: 128256
+max_position_embeddings:
+  desc: null
+  value: 524288
+hidden_size:
+  desc: null
+  value: 4096
+intermediate_size:
+  desc: null
+  value: 14336
+num_hidden_layers:
+  desc: null
+  value: 32
+num_attention_heads:
+  desc: null
+  value: 32
+num_key_value_heads:
+  desc: null
+  value: 8
+hidden_act:
+  desc: null
+  value: silu
+initializer_range:
+  desc: null
+  value: 0.02
+rms_norm_eps:
+  desc: null
+  value: 1.0e-05
+pretraining_tp:
+  desc: null
+  value: 1
+use_cache:
+  desc: null
+  value: true
+rope_theta:
+  desc: null
+  value: 128000000.0
+rope_scaling:
+  desc: null
+  value: null
+attention_bias:
+  desc: null
+  value: false
+attention_dropout:
+  desc: null
+  value: 0.0
+mlp_bias:
+  desc: null
+  value: false
+return_dict:
+  desc: null
+  value: true
+output_hidden_states:
+  desc: null
+  value: false
+output_attentions:
+  desc: null
+  value: false
+torchscript:
+  desc: null
+  value: false
+torch_dtype:
+  desc: null
+  value: float32
+use_bfloat16:
+  desc: null
+  value: false
+tf_legacy_loss:
+  desc: null
+  value: false
+pruned_heads:
+  desc: null
+  value: {}
+tie_word_embeddings:
+  desc: null
+  value: false
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+is_encoder_decoder:
+  desc: null
+  value: false
+is_decoder:
+  desc: null
+  value: false
+cross_attention_hidden_size:
+  desc: null
+  value: null
+add_cross_attention:
+  desc: null
+  value: false
+tie_encoder_decoder:
+  desc: null
+  value: false
+max_length:
+  desc: null
+  value: 20
+min_length:
+  desc: null
+  value: 0
+do_sample:
+  desc: null
+  value: false
+early_stopping:
+  desc: null
+  value: false
+num_beams:
+  desc: null
+  value: 1
+num_beam_groups:
+  desc: null
+  value: 1
+diversity_penalty:
+  desc: null
+  value: 0.0
+temperature:
+  desc: null
+  value: 1.0
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+typical_p:
+  desc: null
+  value: 1.0
+repetition_penalty:
+  desc: null
+  value: 1.0
+length_penalty:
+  desc: null
+  value: 1.0
+no_repeat_ngram_size:
+  desc: null
+  value: 0
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+bad_words_ids:
+  desc: null
+  value: null
+num_return_sequences:
+  desc: null
+  value: 1
+output_scores:
+  desc: null
+  value: false
+return_dict_in_generate:
+  desc: null
+  value: false
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+remove_invalid_values:
+  desc: null
+  value: false
+exponential_decay_length_penalty:
+  desc: null
+  value: null
+suppress_tokens:
+  desc: null
+  value: null
+begin_suppress_tokens:
+  desc: null
+  value: null
+architectures:
+  desc: null
+  value:
+  - LlamaForCausalLM
+finetuning_task:
+  desc: null
+  value: null
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+tokenizer_class:
+  desc: null
+  value: null
+prefix:
+  desc: null
+  value: null
+bos_token_id:
+  desc: null
+  value: 128000
+pad_token_id:
+  desc: null
+  value: 0
+eos_token_id:
+  desc: null
+  value: 128009
+sep_token_id:
+  desc: null
+  value: null
+decoder_start_token_id:
+  desc: null
+  value: null
+task_specific_params:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+_name_or_path:
+  desc: null
+  value: /scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/
+transformers_version:
+  desc: null
+  value: 4.44.2
+model_type:
+  desc: null
+  value: llama
+output_dir:
+  desc: null
+  value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
+overwrite_output_dir:
+  desc: null
+  value: false
+do_train:
+  desc: null
+  value: true
+do_eval:
+  desc: null
+  value: false
+do_predict:
+  desc: null
+  value: false
+eval_strategy:
+  desc: null
+  value: 'no'
+prediction_loss_only:
+  desc: null
+  value: false
+per_device_train_batch_size:
+  desc: null
+  value: 1
+per_device_eval_batch_size:
+  desc: null
+  value: 8
+per_gpu_train_batch_size:
+  desc: null
+  value: null
+per_gpu_eval_batch_size:
+  desc: null
+  value: null
+gradient_accumulation_steps:
+  desc: null
+  value: 2
+eval_accumulation_steps:
+  desc: null
+  value: null
+eval_delay:
+  desc: null
+  value: 0
+torch_empty_cache_steps:
+  desc: null
+  value: null
+learning_rate:
+  desc: null
+  value: 1.0e-06
+weight_decay:
+  desc: null
+  value: 0.1
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.95
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+max_grad_norm:
+  desc: null
+  value: 1.0
+num_train_epochs:
+  desc: null
+  value: 1.0
+max_steps:
+  desc: null
+  value: -1
+lr_scheduler_type:
+  desc: null
+  value: cosine
+lr_scheduler_kwargs:
+  desc: null
+  value: {}
+warmup_ratio:
+  desc: null
+  value: 0.05
+warmup_steps:
+  desc: null
+  value: 0
+log_level:
+  desc: null
+  value: info
+log_level_replica:
+  desc: null
+  value: warning
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec25_00-13-47_gpu021
+logging_strategy:
+  desc: null
+  value: steps
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 1.0
+logging_nan_inf_filter:
+  desc: null
+  value: true
+save_strategy:
+  desc: null
+  value: steps
+save_steps:
+  desc: null
+  value: 200
+save_total_limit:
+  desc: null
+  value: null
+save_safetensors:
+  desc: null
+  value: true
+save_on_each_node:
+  desc: null
+  value: false
+save_only_model:
+  desc: null
+  value: false
+restore_callback_states_from_checkpoint:
+  desc: null
+  value: false
+no_cuda:
+  desc: null
+  value: false
+use_cpu:
+  desc: null
+  value: false
+use_mps_device:
+  desc: null
+  value: false
+seed:
+  desc: null
+  value: 42
+data_seed:
+  desc: null
+  value: null
+jit_mode_eval:
+  desc: null
+  value: false
+use_ipex:
+  desc: null
+  value: false
+bf16:
+  desc: null
+  value: true
+fp16:
+  desc: null
+  value: false
+fp16_opt_level:
+  desc: null
+  value: O1
+half_precision_backend:
+  desc: null
+  value: auto
+bf16_full_eval:
+  desc: null
+  value: false
+fp16_full_eval:
+  desc: null
+  value: false
+tf32:
+  desc: null
+  value: null
+local_rank:
+  desc: null
+  value: 0
+ddp_backend:
+  desc: null
+  value: null
+tpu_num_cores:
+  desc: null
+  value: null
+tpu_metrics_debug:
+  desc: null
+  value: false
+debug:
+  desc: null
+  value: []
+dataloader_drop_last:
+  desc: null
+  value: false
+eval_steps:
+  desc: null
+  value: null
+dataloader_num_workers:
+  desc: null
+  value: 1
+dataloader_prefetch_factor:
+  desc: null
+  value: null
+past_index:
+  desc: null
+  value: -1
+run_name:
+  desc: null
+  value: balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
+disable_tqdm:
+  desc: null
+  value: true
+remove_unused_columns:
+  desc: null
+  value: false
+label_names:
+  desc: null
+  value: null
+load_best_model_at_end:
+  desc: null
+  value: false
+metric_for_best_model:
+  desc: null
+  value: null
+greater_is_better:
+  desc: null
+  value: null
+ignore_data_skip:
+  desc: null
+  value: false
+fsdp:
+  desc: null
+  value:
+  - auto_wrap
+  - offload
+fsdp_min_num_params:
+  desc: null
+  value: 0
+fsdp_config:
+  desc: null
+  value:
+    min_num_params: 0
+    xla: false
+    xla_fsdp_v2: false
+    xla_fsdp_grad_ckpt: false
+fsdp_transformer_layer_cls_to_wrap:
+  desc: null
+  value: null
+accelerator_config:
+  desc: null
+  value:
+    split_batches: false
+    dispatch_batches: null
+    even_batches: true
+    use_seedable_sampler: true
+    non_blocking: false
+    gradient_accumulation_kwargs: null
+deepspeed:
+  desc: null
+  value: null
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+optim:
+  desc: null
+  value: adamw_torch
+optim_args:
+  desc: null
+  value: null
+adafactor:
+  desc: null
+  value: false
+group_by_length:
+  desc: null
+  value: false
+length_column_name:
+  desc: null
+  value: length
+report_to:
+  desc: null
+  value:
+  - wandb
+ddp_find_unused_parameters:
+  desc: null
+  value: false
+ddp_bucket_cap_mb:
+  desc: null
+  value: null
+ddp_broadcast_buffers:
+  desc: null
+  value: null
+dataloader_pin_memory:
+  desc: null
+  value: true
+dataloader_persistent_workers:
+  desc: null
+  value: false
+skip_memory_metrics:
+  desc: null
+  value: true
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+push_to_hub:
+  desc: null
+  value: false
+resume_from_checkpoint:
+  desc: null
+  value: null
+hub_model_id:
+  desc: null
+  value: null
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+hub_private_repo:
+  desc: null
+  value: false
+hub_always_push:
+  desc: null
+  value: false
+gradient_checkpointing:
+  desc: null
+  value: true
+gradient_checkpointing_kwargs:
+  desc: null
+  value: null
+include_inputs_for_metrics:
+  desc: null
+  value: false
+eval_do_concat_batches:
+  desc: null
+  value: true
+fp16_backend:
+  desc: null
+  value: auto
+evaluation_strategy:
+  desc: null
+  value: null
+push_to_hub_model_id:
+  desc: null
+  value: null
+push_to_hub_organization:
+  desc: null
+  value: null
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+mp_parameters:
+  desc: null
+  value: ''
+auto_find_batch_size:
+  desc: null
+  value: false
+full_determinism:
+  desc: null
+  value: false
+torchdynamo:
+  desc: null
+  value: null
+ray_scope:
+  desc: null
+  value: last
+ddp_timeout:
+  desc: null
+  value: 1800
+torch_compile:
+  desc: null
+  value: false
+torch_compile_backend:
+  desc: null
+  value: null
+torch_compile_mode:
+  desc: null
+  value: null
+dispatch_batches:
+  desc: null
+  value: null
+split_batches:
+  desc: null
+  value: null
+include_tokens_per_second:
+  desc: null
+  value: false
+include_num_input_tokens_seen:
+  desc: null
+  value: false
+neftune_noise_alpha:
+  desc: null
+  value: null
+optim_target_modules:
+  desc: null
+  value: null
+batch_eval_metrics:
+  desc: null
+  value: false
+eval_on_start:
+  desc: null
+  value: false
+eval_use_gather_object:
+  desc: null
+  value: false
+min_lr_ratio:
+  desc: null
+  value: 0.1
+cuda_empty_cache:
+  desc: null
+  value: true
+streaming_dataset:
+  desc: null
+  value: true
+seq_parallel_size:
+  desc: null
+  value: 8
+model/num_parameters:
+  desc: null
+  value: 1003782656

wandb/run-20241225_001558-sxxraa4n/files/output.log

@@ -0,0 +1,9 @@
+/scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final/lib/python3.10/site-packages/torch/utils/checkpoint.py:1399: FutureWarning: `torch.cpu.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cpu', args...)` instead.
+  with device_autocast_ctx, torch.cpu.amp.autocast(**cpu_autocast_kwargs), recompute_context:  # type: ignore[attr-defined]
+[INFO|trainer.py:175] 2024-12-25 00:16:55,348 >> {'loss': 1.4339, 'grad_norm': 39.49641418457031, 'learning_rate': 5.405405405405406e-09, 'epoch': 0.00027122321670735016, 'num_input_tokens_seen': 2097152, 'completed': '0.03% (1 / 3_687)', 'remaining time': '48:49:02', 'throughput': '2749.09', 'gpu_mem_free': '5581MB'}
+[INFO|trainer.py:175] 2024-12-25 00:17:30,230 >> {'loss': 1.4592, 'grad_norm': 34.68007278442383, 'learning_rate': 1.0810810810810811e-08, 'epoch': 0.0005424464334147003, 'num_input_tokens_seen': 4194304, 'completed': '0.05% (2 / 3_687)', 'remaining time': '42:15:16', 'throughput': '7515.28', 'gpu_mem_free': '5581MB'}
+[INFO|trainer.py:175] 2024-12-25 00:18:05,807 >> {'loss': 1.5967, 'grad_norm': 39.95429992675781, 'learning_rate': 1.6216216216216218e-08, 'epoch': 0.0008136696501220504, 'num_input_tokens_seen': 6291456, 'completed': '0.08% (3 / 3_687)', 'remaining time': '40:17:52', 'throughput': '7368.26', 'gpu_mem_free': '5581MB'}
+[INFO|trainer.py:175] 2024-12-25 00:18:36,833 >> {'loss': 1.2915, 'grad_norm': 31.149150848388672, 'learning_rate': 2.1621621621621623e-08, 'epoch': 0.0010848928668294006, 'num_input_tokens_seen': 8388608, 'completed': '0.11% (4 / 3_687)', 'remaining time': '38:09:01', 'throughput': '8449.32', 'gpu_mem_free': '5581MB'}
+[INFO|trainer.py:175] 2024-12-25 00:19:08,749 >> {'loss': 1.8907, 'grad_norm': 42.642982482910156, 'learning_rate': 2.7027027027027028e-08, 'epoch': 0.0013561160835367507, 'num_input_tokens_seen': 10485760, 'completed': '0.14% (5 / 3_687)', 'remaining time': '37:02:26', 'throughput': '8213.40', 'gpu_mem_free': '5581MB'}
+[INFO|trainer.py:175] 2024-12-25 00:19:38,678 >> {'loss': 1.5168, 'grad_norm': 41.49152755737305, 'learning_rate': 3.2432432432432436e-08, 'epoch': 0.0016273393002441008, 'num_input_tokens_seen': 12582912, 'completed': '0.16% (6 / 3_687)', 'remaining time': '35:57:33', 'throughput': '8759.08', 'gpu_mem_free': '5581MB'}
+[INFO|trainer.py:175] 2024-12-25 00:20:10,870 >> {'loss': 1.4075, 'grad_norm': 35.22410202026367, 'learning_rate': 3.783783783783784e-08, 'epoch': 0.001898562516951451, 'num_input_tokens_seen': 14680064, 'completed': '0.19% (7 / 3_687)', 'remaining time': '35:30:53', 'throughput': '8142.93', 'gpu_mem_free': '5581MB'}

wandb/run-20241225_001558-sxxraa4n/files/requirements.txt

@@ -0,0 +1,242 @@
+Brotli==1.1.0
+GitPython==3.1.43
+Jinja2==3.1.4
+MarkupSafe==3.0.2
+PyJWT==2.10.0
+PyNaCl==1.5.0
+PyYAML==6.0.2
+Pygments==2.18.0
+accelerate==0.32.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.11.2
+aioprometheus==23.12.0
+aiosignal==1.3.1
+annotated-types==0.7.0
+anthropic==0.39.0
+anyio==4.6.2.post1
+argcomplete==3.5.1
+arrow==1.3.0
+asttokens==2.4.1
+async-timeout==5.0.1
+attrs==24.2.0
+autocommand==2.2.2
+azure-core==1.32.0
+azure-identity==1.19.0
+azure-storage-blob==12.24.0
+azure-storage-file-datalake==12.18.0
+backoff==2.2.1
+backports.tarfile==1.2.0
+bcrypt==4.2.0
+blobfile==3.0.0
+boto3==1.35.63
+botocore==1.35.63
+cachetools==5.5.0
+certifi==2024.8.30
+cffi==1.17.1
+charset-normalizer==3.4.0
+circuitbreaker==2.0.0
+click==8.1.7
+cloudpickle==3.1.0
+comm==0.2.2
+compressed-tensors==0.8.0
+contourpy==1.3.1
+cramjam==2.9.0
+cryptography==43.0.3
+cycler==0.12.1
+datasets==2.20.0
+debugpy==1.8.11
+decorator==5.1.1
+dill==0.3.8
+diskcache==5.6.3
+distro==1.9.0
+docker-pycreds==0.4.0
+docstring_parser==0.16
+einops==0.8.0
+exceptiongroup==1.2.2
+executing==2.1.0
+fastapi==0.115.5
+filelock==3.16.1
+flash-attn==2.6.1
+fonttools==4.55.0
+frozenlist==1.5.0
+fsspec==2024.5.0
+gguf==0.10.0
+gitdb==4.0.11
+google-api-core==2.23.0
+google-auth==2.36.0
+google-cloud-aiplatform==1.71.1
+google-cloud-bigquery==3.27.0
+google-cloud-core==2.4.1
+google-cloud-resource-manager==1.13.1
+google-cloud-storage==2.10.0
+google-crc32c==1.6.0
+google-resumable-media==2.7.2
+googleapis-common-protos==1.66.0
+gql==3.5.0
+graphql-core==3.2.5
+grpc-google-iam-v1==0.13.1
+grpcio-status==1.62.3
+grpcio==1.68.0
+h11==0.14.0
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.27.2
+huggingface-hub==0.26.2
+idna==3.10
+importlib_metadata==8.0.0
+importlib_metadata==8.5.0
+inflect==7.3.1
+interegular==0.3.3
+ipykernel==6.29.5
+ipython==8.18.0
+isodate==0.7.2
+jaraco.collections==5.1.0
+jaraco.context==5.3.0
+jaraco.functools==4.0.1
+jaraco.text==3.12.1
+jedi==0.19.2
+jiter==0.7.1
+jmespath==1.0.1
+jsonschema-specifications==2024.10.1
+jsonschema==4.23.0
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+kiwisolver==1.4.7
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.9
+lxml==5.3.0
+markdown-it-py==3.0.0
+matplotlib-inline==0.1.7
+matplotlib==3.9.2
+mdurl==0.1.2
+more-itertools==10.3.0
+mosaicml-cli==0.5.34
+mosaicml-streaming==0.8.1
+mpmath==1.3.0
+msal-extensions==1.2.0
+msal==1.31.1
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.16
+nest-asyncio==1.6.0
+networkx==3.4.2
+ninja==1.11.1.1
+numba==0.60.0
+numpy==1.26.3
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==12.560.30
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.1.105
+oci==2.138.1
+openai==1.54.5
+opencv-python-headless==4.10.0.84
+orjson==3.10.11
+outlines==0.0.46
+packaging==24.1
+packaging==24.2
+pandas==2.2.1
+paramiko==3.5.0
+parso==0.8.4
+partial-json-parser==0.2.1.1.post4
+pexpect==4.9.0
+pillow==10.4.0
+pip==24.3.1
+platformdirs==4.2.2
+platformdirs==4.3.6
+portalocker==2.10.1
+prometheus-fastapi-instrumentator==7.0.0
+prometheus_client==0.21.0
+prompt-toolkit==3.0.36
+propcache==0.2.0
+proto-plus==1.25.0
+protobuf==4.25.3
+psutil==6.1.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+py-cpuinfo==9.0.0
+pyOpenSSL==24.2.1
+pyairports==2.1.1
+pyarrow-hotfix==0.6
+pyarrow==18.0.0
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycountry==24.6.1
+pycparser==2.22
+pycryptodomex==3.21.0
+pydantic==2.9.2
+pydantic_core==2.23.4
+pyparsing==3.2.0
+python-dateutil==2.9.0
+python-dotenv==1.0.1
+python-snappy==0.7.3
+pytz==2024.2
+pyzmq==26.2.0
+quantile-python==1.1
+questionary==2.0.1
+ray==2.39.0
+referencing==0.35.1
+regex==2023.12.25
+requests==2.32.3
+rich==13.9.4
+rotary-emb==0.5.2
+rpds-py==0.21.0
+rsa==4.9
+ruamel.yaml.clib==0.2.12
+ruamel.yaml==0.18.6
+s3transfer==0.10.3
+safetensors==0.4.5
+sentencepiece==0.1.99
+sentry-sdk==2.18.0
+setproctitle==1.3.4
+setuptools==75.6.0
+shapely==2.0.6
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+stack-data==0.6.3
+starlette==0.41.3
+sympy==1.13.1
+tiktoken==0.7.0
+tokenizers==0.19.1
+tomli==2.0.1
+torch==2.4.1
+torchvision==0.19.1
+tornado==6.4.1
+tqdm==4.66.4
+traitlets==5.14.3
+transformers==4.44.2
+triton==3.0.0
+typeguard==4.3.0
+types-python-dateutil==2.9.0.20241003
+typing_extensions==4.12.2
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.32.0
+uvloop==0.21.0
+validators==0.34.0
+vertexai==1.71.1
+wandb==0.17.3
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==11.0.3
+wheel==0.43.0
+wheel==0.45.1
+xformers==0.0.28.post1
+xxhash==3.5.0
+yarl==1.17.2
+zipp==3.19.2
+zipp==3.21.0
+zstandard==0.22.0
+zstd==1.5.5.1

wandb/run-20241225_001558-sxxraa4n/files/wandb-metadata.json

@@ -0,0 +1,705 @@
+{
+    "os": "Linux-6.8.0-48-generic-x86_64-with-glibc2.39",
+    "python": "3.10.0",
+    "heartbeatAt": "2024-12-25T00:15:59.115811",
+    "startedAt": "2024-12-25T00:15:58.550714",
+    "docker": null,
+    "cuda": null,
+    "args": [
+        "--model_family",
+        "llama",
+        "--apply_instruct_masks",
+        "--token_scaled_loss",
+        "--seq_parallel_size",
+        "8",
+        "--report_to",
+        "wandb",
+        "--do_train",
+        "--model_name_or_path",
+        "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
+        "--config_name",
+        "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
+        "--tokenizer_name",
+        "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
+        "--run_name",
+        "balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
+        "--output_dir",
+        "/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
+        "--config_overrides_json",
+        "",
+        "--gradient_accumulation_steps",
+        "2",
+        "--per_device_train_batch_size",
+        "1",
+        "--bf16",
+        "--learning_rate",
+        "1e-6",
+        "--min_lr_ratio",
+        "0.1",
+        "--lr_scheduler_type",
+        "cosine",
+        "--max_grad_norm",
+        "1.0",
+        "--adam_beta1",
+        "0.9",
+        "--adam_beta2",
+        "0.95",
+        "--weight_decay",
+        "0.1",
+        "--warmup_ratio",
+        "0.05",
+        "--optim",
+        "adamw_torch",
+        "--logging_steps",
+        "1",
+        "--log_level",
+        "info",
+        "--save_steps",
+        "200",
+        "--dataloader_num_workers",
+        "1",
+        "--disable_tqdm",
+        "true",
+        "--use_fast_tokenizer",
+        "false",
+        "--remove_unused_columns",
+        "false",
+        "--ddp_find_unused_parameters",
+        "false",
+        "--fsdp",
+        "auto_wrap offload",
+        "--gradient_checkpointing",
+        "--tokenized_mds_train",
+        "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/data/ft/bookclaim_balanced_pack_complete",
+        "--cuda_empty_cache",
+        "--num_train_epochs",
+        "1"
+    ],
+    "state": "running",
+    "program": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py",
+    "codePathLocal": "finetune.py",
+    "codePath": "prolong-final/finetune.py",
+    "git": {
+        "remote": "https://github.com/chtmp223/BookGen-dev.git",
+        "commit": "6da087f2362deca9028ab5004e1b057d7fcf3f63"
+    },
+    "email": "[email protected]",
+    "root": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev",
+    "host": "gpu021",
+    "username": "ctpham_umass_edu",
+    "executable": "/scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final/bin/python3.10",
+    "cpu_count": 112,
+    "cpu_count_logical": 112,
+    "cpu_freq": {
+        "current": 916.1786517857144,
+        "min": 800.0,
+        "max": 3800.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 779.024,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 915.357,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 3000.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2182.285,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2400.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2018.045,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1743.52,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 785.265,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1300.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1998.947,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 782.919,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 784.049,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 789.099,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1700.017,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2400.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 782.252,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 782.368,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 783.608,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1700.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2400.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        }
+    ],
+    "disk": {
+        "/": {
+            "total": 438.487850189209,
+            "used": 16.227672576904297
+        }
+    },
+    "gpu": "NVIDIA A100-SXM4-80GB",
+    "gpu_count": 8,
+    "gpu_devices": [
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        }
+    ],
+    "memory": {
+        "total": 2015.3287200927734
+    }
+}

wandb/run-20241225_001558-sxxraa4n/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss": 0.5641, "train/grad_norm": 21.8282413482666, "train/learning_rate": 9.249723507271425e-07, "train/epoch": 0.22728505560075943, "train/num_input_tokens_seen": 1757413376, "train/global_step": 838, "_timestamp": 1735112616.697628, "_runtime": 26858.12992310524, "_step": 837}

wandb/run-20241225_001558-sxxraa4n/logs/debug.log

@@ -0,0 +1,31 @@
+2024-12-25 00:15:58,558 INFO    MainThread:677532 [wandb_setup.py:_flush():76] Current SDK version is 0.17.3
+2024-12-25 00:15:58,558 INFO    MainThread:677532 [wandb_setup.py:_flush():76] Configure stats pid to 677532
+2024-12-25 00:15:58,558 INFO    MainThread:677532 [wandb_setup.py:_flush():76] Loading settings from /home/ctpham_umass_edu/.config/wandb/settings
+2024-12-25 00:15:58,558 INFO    MainThread:677532 [wandb_setup.py:_flush():76] Loading settings from /work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/wandb/settings
+2024-12-25 00:15:58,558 INFO    MainThread:677532 [wandb_setup.py:_flush():76] Loading settings from environment variables: {'root_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'project': 'prolong', 'api_key': '***REDACTED***', 'mode': 'online'}
+2024-12-25 00:15:58,558 INFO    MainThread:677532 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-12-25 00:15:58,559 INFO    MainThread:677532 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'prolong-final/finetune.py', 'program_abspath': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py', 'program': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py'}
+2024-12-25 00:15:58,559 INFO    MainThread:677532 [wandb_setup.py:_flush():76] Applying login settings: {}
+2024-12-25 00:15:58,559 INFO    MainThread:677532 [wandb_init.py:_log_setup():520] Logging user logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241225_001558-sxxraa4n/logs/debug.log
+2024-12-25 00:15:58,559 INFO    MainThread:677532 [wandb_init.py:_log_setup():521] Logging internal logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241225_001558-sxxraa4n/logs/debug-internal.log
+2024-12-25 00:15:58,559 INFO    MainThread:677532 [wandb_init.py:init():560] calling init triggers
+2024-12-25 00:15:58,559 INFO    MainThread:677532 [wandb_init.py:init():567] wandb.init called with sweep_config: {}
+config: {}
+2024-12-25 00:15:58,559 INFO    MainThread:677532 [wandb_init.py:init():610] starting backend
+2024-12-25 00:15:58,559 INFO    MainThread:677532 [wandb_init.py:init():614] setting up manager
+2024-12-25 00:15:58,562 INFO    MainThread:677532 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-12-25 00:15:58,565 INFO    MainThread:677532 [wandb_init.py:init():622] backend started and connected
+2024-12-25 00:15:58,571 INFO    MainThread:677532 [wandb_init.py:init():711] updated telemetry
+2024-12-25 00:15:58,639 INFO    MainThread:677532 [wandb_init.py:init():744] communicating run to backend with 90.0 second timeout
+2024-12-25 00:15:58,891 INFO    MainThread:677532 [wandb_run.py:_on_init():2402] communicating current version
+2024-12-25 00:15:58,954 INFO    MainThread:677532 [wandb_run.py:_on_init():2411] got version response upgrade_message: "wandb version 0.19.1 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2024-12-25 00:15:58,954 INFO    MainThread:677532 [wandb_init.py:init():795] starting run threads in backend
+2024-12-25 00:16:07,232 INFO    MainThread:677532 [wandb_run.py:_console_start():2380] atexit reg
+2024-12-25 00:16:07,233 INFO    MainThread:677532 [wandb_run.py:_redirect():2235] redirect: wrap_raw
+2024-12-25 00:16:07,233 INFO    MainThread:677532 [wandb_run.py:_redirect():2300] Wrapping output streams.
+2024-12-25 00:16:07,233 INFO    MainThread:677532 [wandb_run.py:_redirect():2325] Redirects installed.
+2024-12-25 00:16:07,236 INFO    MainThread:677532 [wandb_init.py:init():838] run started, returning control to user process
+2024-12-25 00:16:07,238 INFO    MainThread:677532 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 128256, 'max_position_embeddings': 524288, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': True, 'rope_theta': 128000000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 128000, 'pad_token_id': 0, 'eos_token_id': 128009, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': '/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/', 'transformers_version': '4.44.2', 'model_type': 'llama', 'output_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'overwrite_output_dir': False, 'do_train': True, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-06, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.05, 'warmup_steps': 0, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec25_00-13-47_gpu021', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1.0, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 200, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 1, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'disable_tqdm': True, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': ['auto_wrap', 'offload'], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': False, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False, 'min_lr_ratio': 0.1, 'cuda_empty_cache': True, 'streaming_dataset': True, 'seq_parallel_size': 8}
+2024-12-25 00:16:07,240 INFO    MainThread:677532 [wandb_config.py:__setitem__():151] config set model/num_parameters = 1003782656 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7882a024de40>>
+2024-12-25 00:16:07,240 INFO    MainThread:677532 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 1003782656 None

wandb/run-20241225_001558-sxxraa4n/run-sxxraa4n.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b91b6f51d0a2d417083666b9c5a963db2a195e76381710e6b850746eb7235072
+size 5051393

wandb/run-20241225_152744-sac86tlv/files/conda-environment.yaml

@@ -0,0 +1,232 @@
+name: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final
+channels:
+  - conda-forge
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - bzip2=1.0.8=h4bc722e_7
+  - ca-certificates=2024.12.14=hbcca054_0
+  - ld_impl_linux-64=2.43=h712a8e2_2
+  - libffi=3.4.2=h7f98852_5
+  - libgcc=14.2.0=h77fa898_1
+  - libgcc-ng=14.2.0=h69a702a_1
+  - libgomp=14.2.0=h77fa898_1
+  - liblzma=5.6.3=hb9d3cd8_1
+  - liblzma-devel=5.6.3=hb9d3cd8_1
+  - libnsl=2.0.1=hd590300_0
+  - libsqlite=3.47.2=hee588c1_0
+  - libuuid=2.38.1=h0b41bf4_0
+  - libzlib=1.3.1=hb9d3cd8_2
+  - ncurses=6.5=he02047a_1
+  - openssl=3.4.0=hb9d3cd8_0
+  - pip=24.3.1=pyh8b19718_2
+  - python=3.10.0=h543edf9_3_cpython
+  - readline=8.2=h8228510_1
+  - setuptools=75.6.0=pyhff2d567_1
+  - sqlite=3.47.2=h9eae976_0
+  - tk=8.6.13=noxft_h4845f30_101
+  - wheel=0.45.1=pyhd8ed1ab_1
+  - xz=5.6.3=hbcc6ac9_1
+  - xz-gpl-tools=5.6.3=hbcc6ac9_1
+  - xz-tools=5.6.3=hb9d3cd8_1
+  - pip:
+      - accelerate==0.32.1
+      - aiohappyeyeballs==2.4.3
+      - aiohttp==3.11.2
+      - aioprometheus==23.12.0
+      - aiosignal==1.3.1
+      - annotated-types==0.7.0
+      - anthropic==0.39.0
+      - anyio==4.6.2.post1
+      - argcomplete==3.5.1
+      - arrow==1.3.0
+      - async-timeout==5.0.1
+      - attrs==24.2.0
+      - azure-core==1.32.0
+      - azure-identity==1.19.0
+      - azure-storage-blob==12.24.0
+      - azure-storage-file-datalake==12.18.0
+      - backoff==2.2.1
+      - bcrypt==4.2.0
+      - blobfile==3.0.0
+      - boto3==1.35.63
+      - botocore==1.35.63
+      - brotli==1.1.0
+      - cachetools==5.5.0
+      - certifi==2024.8.30
+      - cffi==1.17.1
+      - charset-normalizer==3.4.0
+      - circuitbreaker==2.0.0
+      - click==8.1.7
+      - cloudpickle==3.1.0
+      - compressed-tensors==0.8.0
+      - contourpy==1.3.1
+      - cramjam==2.9.0
+      - cryptography==43.0.3
+      - cycler==0.12.1
+      - datasets==2.20.0
+      - debugpy==1.8.11
+      - dill==0.3.8
+      - diskcache==5.6.3
+      - distro==1.9.0
+      - docker-pycreds==0.4.0
+      - docstring-parser==0.16
+      - einops==0.8.0
+      - fastapi==0.115.5
+      - filelock==3.16.1
+      - flash-attn==2.6.1
+      - fonttools==4.55.0
+      - frozenlist==1.5.0
+      - fsspec==2024.5.0
+      - gguf==0.10.0
+      - gitdb==4.0.11
+      - gitpython==3.1.43
+      - google-api-core==2.23.0
+      - google-auth==2.36.0
+      - google-cloud-aiplatform==1.71.1
+      - google-cloud-bigquery==3.27.0
+      - google-cloud-core==2.4.1
+      - google-cloud-resource-manager==1.13.1
+      - google-cloud-storage==2.10.0
+      - google-crc32c==1.6.0
+      - google-resumable-media==2.7.2
+      - googleapis-common-protos==1.66.0
+      - gql==3.5.0
+      - graphql-core==3.2.5
+      - grpc-google-iam-v1==0.13.1
+      - grpcio==1.68.0
+      - grpcio-status==1.62.3
+      - h11==0.14.0
+      - httpcore==1.0.7
+      - httptools==0.6.4
+      - httpx==0.27.2
+      - huggingface-hub==0.26.2
+      - idna==3.10
+      - importlib-metadata==8.5.0
+      - interegular==0.3.3
+      - ipython==8.18.0
+      - isodate==0.7.2
+      - jedi==0.19.2
+      - jinja2==3.1.4
+      - jiter==0.7.1
+      - jmespath==1.0.1
+      - jsonschema==4.23.0
+      - jsonschema-specifications==2024.10.1
+      - kiwisolver==1.4.7
+      - lark==1.2.2
+      - llvmlite==0.43.0
+      - lm-format-enforcer==0.10.9
+      - lxml==5.3.0
+      - markdown-it-py==3.0.0
+      - markupsafe==3.0.2
+      - matplotlib==3.9.2
+      - mdurl==0.1.2
+      - mosaicml-cli==0.5.34
+      - mosaicml-streaming==0.8.1
+      - mpmath==1.3.0
+      - msal==1.31.1
+      - msal-extensions==1.2.0
+      - msgpack==1.1.0
+      - msgspec==0.18.6
+      - multidict==6.1.0
+      - multiprocess==0.70.16
+      - networkx==3.4.2
+      - ninja==1.11.1.1
+      - numba==0.60.0
+      - numpy==1.26.3
+      - nvidia-cublas-cu12==12.1.3.1
+      - nvidia-cuda-cupti-cu12==12.1.105
+      - nvidia-cuda-nvrtc-cu12==12.1.105
+      - nvidia-cuda-runtime-cu12==12.1.105
+      - nvidia-cudnn-cu12==9.1.0.70
+      - nvidia-cufft-cu12==11.0.2.54
+      - nvidia-curand-cu12==10.3.2.106
+      - nvidia-cusolver-cu12==11.4.5.107
+      - nvidia-cusparse-cu12==12.1.0.106
+      - nvidia-ml-py==12.560.30
+      - nvidia-nccl-cu12==2.20.5
+      - nvidia-nvjitlink-cu12==12.4.127
+      - nvidia-nvtx-cu12==12.1.105
+      - oci==2.138.1
+      - openai==1.54.5
+      - opencv-python-headless==4.10.0.84
+      - orjson==3.10.11
+      - outlines==0.0.46
+      - packaging==24.1
+      - pandas==2.2.1
+      - paramiko==3.5.0
+      - partial-json-parser==0.2.1.1.post4
+      - pillow==10.4.0
+      - portalocker==2.10.1
+      - prometheus-client==0.21.0
+      - prometheus-fastapi-instrumentator==7.0.0
+      - prompt-toolkit==3.0.36
+      - propcache==0.2.0
+      - proto-plus==1.25.0
+      - protobuf==4.25.3
+      - py-cpuinfo==9.0.0
+      - pyairports==2.1.1
+      - pyarrow==18.0.0
+      - pyarrow-hotfix==0.6
+      - pyasn1==0.6.1
+      - pyasn1-modules==0.4.1
+      - pycountry==24.6.1
+      - pycparser==2.22
+      - pycryptodomex==3.21.0
+      - pydantic==2.9.2
+      - pydantic-core==2.23.4
+      - pyjwt==2.10.0
+      - pynacl==1.5.0
+      - pyopenssl==24.2.1
+      - pyparsing==3.2.0
+      - python-dateutil==2.9.0
+      - python-dotenv==1.0.1
+      - python-snappy==0.7.3
+      - pytz==2024.2
+      - pyyaml==6.0.2
+      - quantile-python==1.1
+      - questionary==2.0.1
+      - ray==2.39.0
+      - referencing==0.35.1
+      - regex==2023.12.25
+      - requests==2.32.3
+      - rich==13.9.4
+      - rotary-emb==0.5.2
+      - rpds-py==0.21.0
+      - rsa==4.9
+      - ruamel-yaml==0.18.6
+      - ruamel-yaml-clib==0.2.12
+      - s3transfer==0.10.3
+      - safetensors==0.4.5
+      - sentencepiece==0.1.99
+      - sentry-sdk==2.18.0
+      - setproctitle==1.3.4
+      - shapely==2.0.6
+      - smmap==5.0.1
+      - sniffio==1.3.1
+      - starlette==0.41.3
+      - sympy==1.13.1
+      - tiktoken==0.7.0
+      - tokenizers==0.19.1
+      - torch==2.4.1
+      - torchvision==0.19.1
+      - tqdm==4.66.4
+      - transformers==4.44.2
+      - triton==3.0.0
+      - types-python-dateutil==2.9.0.20241003
+      - tzdata==2024.2
+      - urllib3==2.2.3
+      - uvicorn==0.32.0
+      - uvloop==0.21.0
+      - validators==0.34.0
+      - vertexai==1.71.1
+      - wandb==0.17.3
+      - watchfiles==0.24.0
+      - websockets==11.0.3
+      - xformers==0.0.28.post1
+      - xxhash==3.5.0
+      - yarl==1.17.2
+      - zipp==3.21.0
+      - zstandard==0.22.0
+      - zstd==1.5.5.1
+prefix: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final

wandb/run-20241225_152744-sac86tlv/files/config.yaml

@@ -0,0 +1,705 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.10.0
+    cli_version: 0.17.3
+    framework: huggingface
+    huggingface_version: 4.44.2
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    start_time: 1735140464
+    t:
+      1:
+      - 1
+      - 11
+      - 41
+      - 49
+      - 51
+      - 55
+      - 71
+      - 105
+      2:
+      - 1
+      - 11
+      - 41
+      - 49
+      - 51
+      - 55
+      - 71
+      - 105
+      3:
+      - 7
+      - 13
+      - 19
+      - 23
+      - 66
+      4: 3.10.0
+      5: 0.17.3
+      6: 4.44.2
+      8:
+      - 5
+      9:
+        1: transformers_trainer
+      13: linux-x86_64
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    - 1: train/loss
+      5: 1
+      6:
+      - 1
+    - 1: train/grad_norm
+      5: 1
+      6:
+      - 1
+    - 1: train/learning_rate
+      5: 1
+      6:
+      - 1
+    - 1: train/epoch
+      5: 1
+      6:
+      - 1
+    - 1: train/num_input_tokens_seen
+      5: 1
+      6:
+      - 1
+vocab_size:
+  desc: null
+  value: 128256
+max_position_embeddings:
+  desc: null
+  value: 524288
+hidden_size:
+  desc: null
+  value: 4096
+intermediate_size:
+  desc: null
+  value: 14336
+num_hidden_layers:
+  desc: null
+  value: 32
+num_attention_heads:
+  desc: null
+  value: 32
+num_key_value_heads:
+  desc: null
+  value: 8
+hidden_act:
+  desc: null
+  value: silu
+initializer_range:
+  desc: null
+  value: 0.02
+rms_norm_eps:
+  desc: null
+  value: 1.0e-05
+pretraining_tp:
+  desc: null
+  value: 1
+use_cache:
+  desc: null
+  value: true
+rope_theta:
+  desc: null
+  value: 128000000.0
+rope_scaling:
+  desc: null
+  value: null
+attention_bias:
+  desc: null
+  value: false
+attention_dropout:
+  desc: null
+  value: 0.0
+mlp_bias:
+  desc: null
+  value: false
+return_dict:
+  desc: null
+  value: true
+output_hidden_states:
+  desc: null
+  value: false
+output_attentions:
+  desc: null
+  value: false
+torchscript:
+  desc: null
+  value: false
+torch_dtype:
+  desc: null
+  value: float32
+use_bfloat16:
+  desc: null
+  value: false
+tf_legacy_loss:
+  desc: null
+  value: false
+pruned_heads:
+  desc: null
+  value: {}
+tie_word_embeddings:
+  desc: null
+  value: false
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+is_encoder_decoder:
+  desc: null
+  value: false
+is_decoder:
+  desc: null
+  value: false
+cross_attention_hidden_size:
+  desc: null
+  value: null
+add_cross_attention:
+  desc: null
+  value: false
+tie_encoder_decoder:
+  desc: null
+  value: false
+max_length:
+  desc: null
+  value: 20
+min_length:
+  desc: null
+  value: 0
+do_sample:
+  desc: null
+  value: false
+early_stopping:
+  desc: null
+  value: false
+num_beams:
+  desc: null
+  value: 1
+num_beam_groups:
+  desc: null
+  value: 1
+diversity_penalty:
+  desc: null
+  value: 0.0
+temperature:
+  desc: null
+  value: 1.0
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+typical_p:
+  desc: null
+  value: 1.0
+repetition_penalty:
+  desc: null
+  value: 1.0
+length_penalty:
+  desc: null
+  value: 1.0
+no_repeat_ngram_size:
+  desc: null
+  value: 0
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+bad_words_ids:
+  desc: null
+  value: null
+num_return_sequences:
+  desc: null
+  value: 1
+output_scores:
+  desc: null
+  value: false
+return_dict_in_generate:
+  desc: null
+  value: false
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+remove_invalid_values:
+  desc: null
+  value: false
+exponential_decay_length_penalty:
+  desc: null
+  value: null
+suppress_tokens:
+  desc: null
+  value: null
+begin_suppress_tokens:
+  desc: null
+  value: null
+architectures:
+  desc: null
+  value:
+  - LlamaForCausalLM
+finetuning_task:
+  desc: null
+  value: null
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+tokenizer_class:
+  desc: null
+  value: null
+prefix:
+  desc: null
+  value: null
+bos_token_id:
+  desc: null
+  value: 128000
+pad_token_id:
+  desc: null
+  value: 0
+eos_token_id:
+  desc: null
+  value: 128009
+sep_token_id:
+  desc: null
+  value: null
+decoder_start_token_id:
+  desc: null
+  value: null
+task_specific_params:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+_name_or_path:
+  desc: null
+  value: /scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/
+transformers_version:
+  desc: null
+  value: 4.44.2
+model_type:
+  desc: null
+  value: llama
+output_dir:
+  desc: null
+  value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
+overwrite_output_dir:
+  desc: null
+  value: false
+do_train:
+  desc: null
+  value: true
+do_eval:
+  desc: null
+  value: false
+do_predict:
+  desc: null
+  value: false
+eval_strategy:
+  desc: null
+  value: 'no'
+prediction_loss_only:
+  desc: null
+  value: false
+per_device_train_batch_size:
+  desc: null
+  value: 1
+per_device_eval_batch_size:
+  desc: null
+  value: 8
+per_gpu_train_batch_size:
+  desc: null
+  value: null
+per_gpu_eval_batch_size:
+  desc: null
+  value: null
+gradient_accumulation_steps:
+  desc: null
+  value: 2
+eval_accumulation_steps:
+  desc: null
+  value: null
+eval_delay:
+  desc: null
+  value: 0
+torch_empty_cache_steps:
+  desc: null
+  value: null
+learning_rate:
+  desc: null
+  value: 1.0e-06
+weight_decay:
+  desc: null
+  value: 0.1
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.95
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+max_grad_norm:
+  desc: null
+  value: 1.0
+num_train_epochs:
+  desc: null
+  value: 1.0
+max_steps:
+  desc: null
+  value: -1
+lr_scheduler_type:
+  desc: null
+  value: cosine
+lr_scheduler_kwargs:
+  desc: null
+  value: {}
+warmup_ratio:
+  desc: null
+  value: 0.05
+warmup_steps:
+  desc: null
+  value: 0
+log_level:
+  desc: null
+  value: info
+log_level_replica:
+  desc: null
+  value: warning
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec25_15-21-22_gpu020
+logging_strategy:
+  desc: null
+  value: steps
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 1.0
+logging_nan_inf_filter:
+  desc: null
+  value: true
+save_strategy:
+  desc: null
+  value: steps
+save_steps:
+  desc: null
+  value: 200
+save_total_limit:
+  desc: null
+  value: null
+save_safetensors:
+  desc: null
+  value: true
+save_on_each_node:
+  desc: null
+  value: false
+save_only_model:
+  desc: null
+  value: false
+restore_callback_states_from_checkpoint:
+  desc: null
+  value: false
+no_cuda:
+  desc: null
+  value: false
+use_cpu:
+  desc: null
+  value: false
+use_mps_device:
+  desc: null
+  value: false
+seed:
+  desc: null
+  value: 42
+data_seed:
+  desc: null
+  value: null
+jit_mode_eval:
+  desc: null
+  value: false
+use_ipex:
+  desc: null
+  value: false
+bf16:
+  desc: null
+  value: true
+fp16:
+  desc: null
+  value: false
+fp16_opt_level:
+  desc: null
+  value: O1
+half_precision_backend:
+  desc: null
+  value: auto
+bf16_full_eval:
+  desc: null
+  value: false
+fp16_full_eval:
+  desc: null
+  value: false
+tf32:
+  desc: null
+  value: null
+local_rank:
+  desc: null
+  value: 0
+ddp_backend:
+  desc: null
+  value: null
+tpu_num_cores:
+  desc: null
+  value: null
+tpu_metrics_debug:
+  desc: null
+  value: false
+debug:
+  desc: null
+  value: []
+dataloader_drop_last:
+  desc: null
+  value: false
+eval_steps:
+  desc: null
+  value: null
+dataloader_num_workers:
+  desc: null
+  value: 1
+dataloader_prefetch_factor:
+  desc: null
+  value: null
+past_index:
+  desc: null
+  value: -1
+run_name:
+  desc: null
+  value: balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
+disable_tqdm:
+  desc: null
+  value: true
+remove_unused_columns:
+  desc: null
+  value: false
+label_names:
+  desc: null
+  value: null
+load_best_model_at_end:
+  desc: null
+  value: false
+metric_for_best_model:
+  desc: null
+  value: null
+greater_is_better:
+  desc: null
+  value: null
+ignore_data_skip:
+  desc: null
+  value: true
+fsdp:
+  desc: null
+  value:
+  - auto_wrap
+  - offload
+fsdp_min_num_params:
+  desc: null
+  value: 0
+fsdp_config:
+  desc: null
+  value:
+    min_num_params: 0
+    xla: false
+    xla_fsdp_v2: false
+    xla_fsdp_grad_ckpt: false
+fsdp_transformer_layer_cls_to_wrap:
+  desc: null
+  value: null
+accelerator_config:
+  desc: null
+  value:
+    split_batches: false
+    dispatch_batches: null
+    even_batches: true
+    use_seedable_sampler: true
+    non_blocking: false
+    gradient_accumulation_kwargs: null
+deepspeed:
+  desc: null
+  value: null
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+optim:
+  desc: null
+  value: adamw_torch
+optim_args:
+  desc: null
+  value: null
+adafactor:
+  desc: null
+  value: false
+group_by_length:
+  desc: null
+  value: false
+length_column_name:
+  desc: null
+  value: length
+report_to:
+  desc: null
+  value:
+  - wandb
+ddp_find_unused_parameters:
+  desc: null
+  value: false
+ddp_bucket_cap_mb:
+  desc: null
+  value: null
+ddp_broadcast_buffers:
+  desc: null
+  value: null
+dataloader_pin_memory:
+  desc: null
+  value: true
+dataloader_persistent_workers:
+  desc: null
+  value: false
+skip_memory_metrics:
+  desc: null
+  value: true
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+push_to_hub:
+  desc: null
+  value: false
+resume_from_checkpoint:
+  desc: null
+  value: null
+hub_model_id:
+  desc: null
+  value: null
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+hub_private_repo:
+  desc: null
+  value: false
+hub_always_push:
+  desc: null
+  value: false
+gradient_checkpointing:
+  desc: null
+  value: true
+gradient_checkpointing_kwargs:
+  desc: null
+  value: null
+include_inputs_for_metrics:
+  desc: null
+  value: false
+eval_do_concat_batches:
+  desc: null
+  value: true
+fp16_backend:
+  desc: null
+  value: auto
+evaluation_strategy:
+  desc: null
+  value: null
+push_to_hub_model_id:
+  desc: null
+  value: null
+push_to_hub_organization:
+  desc: null
+  value: null
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+mp_parameters:
+  desc: null
+  value: ''
+auto_find_batch_size:
+  desc: null
+  value: false
+full_determinism:
+  desc: null
+  value: false
+torchdynamo:
+  desc: null
+  value: null
+ray_scope:
+  desc: null
+  value: last
+ddp_timeout:
+  desc: null
+  value: 1800
+torch_compile:
+  desc: null
+  value: false
+torch_compile_backend:
+  desc: null
+  value: null
+torch_compile_mode:
+  desc: null
+  value: null
+dispatch_batches:
+  desc: null
+  value: null
+split_batches:
+  desc: null
+  value: null
+include_tokens_per_second:
+  desc: null
+  value: false
+include_num_input_tokens_seen:
+  desc: null
+  value: false
+neftune_noise_alpha:
+  desc: null
+  value: null
+optim_target_modules:
+  desc: null
+  value: null
+batch_eval_metrics:
+  desc: null
+  value: false
+eval_on_start:
+  desc: null
+  value: false
+eval_use_gather_object:
+  desc: null
+  value: false
+min_lr_ratio:
+  desc: null
+  value: 0.1
+cuda_empty_cache:
+  desc: null
+  value: true
+streaming_dataset:
+  desc: null
+  value: true
+seq_parallel_size:
+  desc: null
+  value: 8
+model/num_parameters:
+  desc: null
+  value: 1003782656

wandb/run-20241225_152744-sac86tlv/files/requirements.txt

@@ -0,0 +1,242 @@
+Brotli==1.1.0
+GitPython==3.1.43
+Jinja2==3.1.4
+MarkupSafe==3.0.2
+PyJWT==2.10.0
+PyNaCl==1.5.0
+PyYAML==6.0.2
+Pygments==2.18.0
+accelerate==0.32.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.11.2
+aioprometheus==23.12.0
+aiosignal==1.3.1
+annotated-types==0.7.0
+anthropic==0.39.0
+anyio==4.6.2.post1
+argcomplete==3.5.1
+arrow==1.3.0
+asttokens==2.4.1
+async-timeout==5.0.1
+attrs==24.2.0
+autocommand==2.2.2
+azure-core==1.32.0
+azure-identity==1.19.0
+azure-storage-blob==12.24.0
+azure-storage-file-datalake==12.18.0
+backoff==2.2.1
+backports.tarfile==1.2.0
+bcrypt==4.2.0
+blobfile==3.0.0
+boto3==1.35.63
+botocore==1.35.63
+cachetools==5.5.0
+certifi==2024.8.30
+cffi==1.17.1
+charset-normalizer==3.4.0
+circuitbreaker==2.0.0
+click==8.1.7
+cloudpickle==3.1.0
+comm==0.2.2
+compressed-tensors==0.8.0
+contourpy==1.3.1
+cramjam==2.9.0
+cryptography==43.0.3
+cycler==0.12.1
+datasets==2.20.0
+debugpy==1.8.11
+decorator==5.1.1
+dill==0.3.8
+diskcache==5.6.3
+distro==1.9.0
+docker-pycreds==0.4.0
+docstring_parser==0.16
+einops==0.8.0
+exceptiongroup==1.2.2
+executing==2.1.0
+fastapi==0.115.5
+filelock==3.16.1
+flash-attn==2.6.1
+fonttools==4.55.0
+frozenlist==1.5.0
+fsspec==2024.5.0
+gguf==0.10.0
+gitdb==4.0.11
+google-api-core==2.23.0
+google-auth==2.36.0
+google-cloud-aiplatform==1.71.1
+google-cloud-bigquery==3.27.0
+google-cloud-core==2.4.1
+google-cloud-resource-manager==1.13.1
+google-cloud-storage==2.10.0
+google-crc32c==1.6.0
+google-resumable-media==2.7.2
+googleapis-common-protos==1.66.0
+gql==3.5.0
+graphql-core==3.2.5
+grpc-google-iam-v1==0.13.1
+grpcio-status==1.62.3
+grpcio==1.68.0
+h11==0.14.0
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.27.2
+huggingface-hub==0.26.2
+idna==3.10
+importlib_metadata==8.0.0
+importlib_metadata==8.5.0
+inflect==7.3.1
+interegular==0.3.3
+ipykernel==6.29.5
+ipython==8.18.0
+isodate==0.7.2
+jaraco.collections==5.1.0
+jaraco.context==5.3.0
+jaraco.functools==4.0.1
+jaraco.text==3.12.1
+jedi==0.19.2
+jiter==0.7.1
+jmespath==1.0.1
+jsonschema-specifications==2024.10.1
+jsonschema==4.23.0
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+kiwisolver==1.4.7
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.9
+lxml==5.3.0
+markdown-it-py==3.0.0
+matplotlib-inline==0.1.7
+matplotlib==3.9.2
+mdurl==0.1.2
+more-itertools==10.3.0
+mosaicml-cli==0.5.34
+mosaicml-streaming==0.8.1
+mpmath==1.3.0
+msal-extensions==1.2.0
+msal==1.31.1
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.16
+nest-asyncio==1.6.0
+networkx==3.4.2
+ninja==1.11.1.1
+numba==0.60.0
+numpy==1.26.3
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==12.560.30
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.1.105
+oci==2.138.1
+openai==1.54.5
+opencv-python-headless==4.10.0.84
+orjson==3.10.11
+outlines==0.0.46
+packaging==24.1
+packaging==24.2
+pandas==2.2.1
+paramiko==3.5.0
+parso==0.8.4
+partial-json-parser==0.2.1.1.post4
+pexpect==4.9.0
+pillow==10.4.0
+pip==24.3.1
+platformdirs==4.2.2
+platformdirs==4.3.6
+portalocker==2.10.1
+prometheus-fastapi-instrumentator==7.0.0
+prometheus_client==0.21.0
+prompt-toolkit==3.0.36
+propcache==0.2.0
+proto-plus==1.25.0
+protobuf==4.25.3
+psutil==6.1.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+py-cpuinfo==9.0.0
+pyOpenSSL==24.2.1
+pyairports==2.1.1
+pyarrow-hotfix==0.6
+pyarrow==18.0.0
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycountry==24.6.1
+pycparser==2.22
+pycryptodomex==3.21.0
+pydantic==2.9.2
+pydantic_core==2.23.4
+pyparsing==3.2.0
+python-dateutil==2.9.0
+python-dotenv==1.0.1
+python-snappy==0.7.3
+pytz==2024.2
+pyzmq==26.2.0
+quantile-python==1.1
+questionary==2.0.1
+ray==2.39.0
+referencing==0.35.1
+regex==2023.12.25
+requests==2.32.3
+rich==13.9.4
+rotary-emb==0.5.2
+rpds-py==0.21.0
+rsa==4.9
+ruamel.yaml.clib==0.2.12
+ruamel.yaml==0.18.6
+s3transfer==0.10.3
+safetensors==0.4.5
+sentencepiece==0.1.99
+sentry-sdk==2.18.0
+setproctitle==1.3.4
+setuptools==75.6.0
+shapely==2.0.6
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+stack-data==0.6.3
+starlette==0.41.3
+sympy==1.13.1
+tiktoken==0.7.0
+tokenizers==0.19.1
+tomli==2.0.1
+torch==2.4.1
+torchvision==0.19.1
+tornado==6.4.1
+tqdm==4.66.4
+traitlets==5.14.3
+transformers==4.44.2
+triton==3.0.0
+typeguard==4.3.0
+types-python-dateutil==2.9.0.20241003
+typing_extensions==4.12.2
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.32.0
+uvloop==0.21.0
+validators==0.34.0
+vertexai==1.71.1
+wandb==0.17.3
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==11.0.3
+wheel==0.43.0
+wheel==0.45.1
+xformers==0.0.28.post1
+xxhash==3.5.0
+yarl==1.17.2
+zipp==3.19.2
+zipp==3.21.0
+zstandard==0.22.0
+zstd==1.5.5.1

wandb/run-20241225_152744-sac86tlv/files/wandb-metadata.json

@@ -0,0 +1,705 @@
+{
+    "os": "Linux-6.8.0-48-generic-x86_64-with-glibc2.39",
+    "python": "3.10.0",
+    "heartbeatAt": "2024-12-25T15:27:44.870156",
+    "startedAt": "2024-12-25T15:27:44.387439",
+    "docker": null,
+    "cuda": null,
+    "args": [
+        "--model_family",
+        "llama",
+        "--apply_instruct_masks",
+        "--token_scaled_loss",
+        "--seq_parallel_size",
+        "8",
+        "--report_to",
+        "wandb",
+        "--do_train",
+        "--model_name_or_path",
+        "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
+        "--config_name",
+        "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
+        "--tokenizer_name",
+        "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
+        "--run_name",
+        "balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
+        "--output_dir",
+        "/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
+        "--config_overrides_json",
+        "",
+        "--gradient_accumulation_steps",
+        "2",
+        "--per_device_train_batch_size",
+        "1",
+        "--bf16",
+        "--learning_rate",
+        "1e-6",
+        "--min_lr_ratio",
+        "0.1",
+        "--lr_scheduler_type",
+        "cosine",
+        "--max_grad_norm",
+        "1.0",
+        "--adam_beta1",
+        "0.9",
+        "--adam_beta2",
+        "0.95",
+        "--weight_decay",
+        "0.1",
+        "--warmup_ratio",
+        "0.05",
+        "--optim",
+        "adamw_torch",
+        "--logging_steps",
+        "1",
+        "--log_level",
+        "info",
+        "--save_steps",
+        "200",
+        "--dataloader_num_workers",
+        "1",
+        "--disable_tqdm",
+        "true",
+        "--use_fast_tokenizer",
+        "false",
+        "--remove_unused_columns",
+        "false",
+        "--ddp_find_unused_parameters",
+        "false",
+        "--fsdp",
+        "auto_wrap offload",
+        "--gradient_checkpointing",
+        "--tokenized_mds_train",
+        "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/data/ft/bookclaim_balanced_pack_complete",
+        "--cuda_empty_cache",
+        "--num_train_epochs",
+        "1"
+    ],
+    "state": "running",
+    "program": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py",
+    "codePathLocal": "finetune.py",
+    "codePath": "prolong-final/finetune.py",
+    "git": {
+        "remote": "https://github.com/chtmp223/BookGen-dev.git",
+        "commit": "438e68ae65a707227d28baa427c5f6fdb0932c7b"
+    },
+    "email": "[email protected]",
+    "root": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev",
+    "host": "gpu020",
+    "username": "ctpham_umass_edu",
+    "executable": "/scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final/bin/python3.10",
+    "cpu_count": 112,
+    "cpu_count_logical": 112,
+    "cpu_freq": {
+        "current": 997.5532857142858,
+        "min": 800.0,
+        "max": 3800.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 765.075,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 783.551,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 791.32,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 791.402,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 788.612,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 783.817,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1700.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 783.39,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 783.853,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1600.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1995.789,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2400.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2400.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2400.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2400.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 3800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 784.222,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2400.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2054.42,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1998.667,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 3800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2009.408,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1991.42,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 783.068,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 783.462,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        }
+    ],
+    "disk": {
+        "/": {
+            "total": 438.487850189209,
+            "used": 18.09857940673828
+        }
+    },
+    "gpu": "NVIDIA A100-SXM4-80GB",
+    "gpu_count": 8,
+    "gpu_devices": [
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        }
+    ],
+    "memory": {
+        "total": 2015.3287239074707
+    }
+}

wandb/run-20241225_152744-sac86tlv/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss": 0.3707, "train/grad_norm": 19.094097137451172, "train/learning_rate": 3.1585738590718157e-07, "train/epoch": 0.4735557363710334, "train/num_input_tokens_seen": 5339348992, "train/global_step": 2546, "_timestamp": 1735196422.1364121, "_runtime": 55957.73042821884, "_step": 1745}

wandb/run-20241225_152744-sac86tlv/logs/debug.log

@@ -0,0 +1,31 @@
+2024-12-25 15:27:44,398 INFO    MainThread:315136 [wandb_setup.py:_flush():76] Current SDK version is 0.17.3
+2024-12-25 15:27:44,398 INFO    MainThread:315136 [wandb_setup.py:_flush():76] Configure stats pid to 315136
+2024-12-25 15:27:44,398 INFO    MainThread:315136 [wandb_setup.py:_flush():76] Loading settings from /home/ctpham_umass_edu/.config/wandb/settings
+2024-12-25 15:27:44,398 INFO    MainThread:315136 [wandb_setup.py:_flush():76] Loading settings from /work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/wandb/settings
+2024-12-25 15:27:44,398 INFO    MainThread:315136 [wandb_setup.py:_flush():76] Loading settings from environment variables: {'root_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'project': 'prolong', 'api_key': '***REDACTED***', 'mode': 'online'}
+2024-12-25 15:27:44,398 INFO    MainThread:315136 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-12-25 15:27:44,398 INFO    MainThread:315136 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'prolong-final/finetune.py', 'program_abspath': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py', 'program': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py'}
+2024-12-25 15:27:44,398 INFO    MainThread:315136 [wandb_setup.py:_flush():76] Applying login settings: {}
+2024-12-25 15:27:44,399 INFO    MainThread:315136 [wandb_init.py:_log_setup():520] Logging user logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241225_152744-sac86tlv/logs/debug.log
+2024-12-25 15:27:44,399 INFO    MainThread:315136 [wandb_init.py:_log_setup():521] Logging internal logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241225_152744-sac86tlv/logs/debug-internal.log
+2024-12-25 15:27:44,399 INFO    MainThread:315136 [wandb_init.py:init():560] calling init triggers
+2024-12-25 15:27:44,399 INFO    MainThread:315136 [wandb_init.py:init():567] wandb.init called with sweep_config: {}
+config: {}
+2024-12-25 15:27:44,399 INFO    MainThread:315136 [wandb_init.py:init():610] starting backend
+2024-12-25 15:27:44,399 INFO    MainThread:315136 [wandb_init.py:init():614] setting up manager
+2024-12-25 15:27:44,402 INFO    MainThread:315136 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-12-25 15:27:44,405 INFO    MainThread:315136 [wandb_init.py:init():622] backend started and connected
+2024-12-25 15:27:44,414 INFO    MainThread:315136 [wandb_init.py:init():711] updated telemetry
+2024-12-25 15:27:44,442 INFO    MainThread:315136 [wandb_init.py:init():744] communicating run to backend with 90.0 second timeout
+2024-12-25 15:27:44,703 INFO    MainThread:315136 [wandb_run.py:_on_init():2402] communicating current version
+2024-12-25 15:27:44,769 INFO    MainThread:315136 [wandb_run.py:_on_init():2411] got version response upgrade_message: "wandb version 0.19.1 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2024-12-25 15:27:44,769 INFO    MainThread:315136 [wandb_init.py:init():795] starting run threads in backend
+2024-12-25 15:27:52,193 INFO    MainThread:315136 [wandb_run.py:_console_start():2380] atexit reg
+2024-12-25 15:27:52,193 INFO    MainThread:315136 [wandb_run.py:_redirect():2235] redirect: wrap_raw
+2024-12-25 15:27:52,194 INFO    MainThread:315136 [wandb_run.py:_redirect():2300] Wrapping output streams.
+2024-12-25 15:27:52,194 INFO    MainThread:315136 [wandb_run.py:_redirect():2325] Redirects installed.
+2024-12-25 15:27:52,195 INFO    MainThread:315136 [wandb_init.py:init():838] run started, returning control to user process
+2024-12-25 15:27:52,197 INFO    MainThread:315136 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 128256, 'max_position_embeddings': 524288, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': True, 'rope_theta': 128000000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 128000, 'pad_token_id': 0, 'eos_token_id': 128009, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': '/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/', 'transformers_version': '4.44.2', 'model_type': 'llama', 'output_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'overwrite_output_dir': False, 'do_train': True, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-06, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.05, 'warmup_steps': 0, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec25_15-21-22_gpu020', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1.0, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 200, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 1, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'disable_tqdm': True, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': True, 'fsdp': ['auto_wrap', 'offload'], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': False, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False, 'min_lr_ratio': 0.1, 'cuda_empty_cache': True, 'streaming_dataset': True, 'seq_parallel_size': 8}
+2024-12-25 15:27:52,199 INFO    MainThread:315136 [wandb_config.py:__setitem__():151] config set model/num_parameters = 1003782656 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x74e6e91a2da0>>
+2024-12-25 15:27:52,200 INFO    MainThread:315136 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 1003782656 None

wandb/run-20241225_152744-sac86tlv/run-sac86tlv.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf10a3dda753a2585274da80ad47f6378f71e6ae1d836e595dcf4f0c9d35cb2a
+size 11275886

wandb/run-20241226_145403-c7ovtvny/files/conda-environment.yaml

@@ -0,0 +1,232 @@
+name: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final
+channels:
+  - conda-forge
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - bzip2=1.0.8=h4bc722e_7
+  - ca-certificates=2024.12.14=hbcca054_0
+  - ld_impl_linux-64=2.43=h712a8e2_2
+  - libffi=3.4.2=h7f98852_5
+  - libgcc=14.2.0=h77fa898_1
+  - libgcc-ng=14.2.0=h69a702a_1
+  - libgomp=14.2.0=h77fa898_1
+  - liblzma=5.6.3=hb9d3cd8_1
+  - liblzma-devel=5.6.3=hb9d3cd8_1
+  - libnsl=2.0.1=hd590300_0
+  - libsqlite=3.47.2=hee588c1_0
+  - libuuid=2.38.1=h0b41bf4_0
+  - libzlib=1.3.1=hb9d3cd8_2
+  - ncurses=6.5=he02047a_1
+  - openssl=3.4.0=hb9d3cd8_0
+  - pip=24.3.1=pyh8b19718_2
+  - python=3.10.0=h543edf9_3_cpython
+  - readline=8.2=h8228510_1
+  - setuptools=75.6.0=pyhff2d567_1
+  - sqlite=3.47.2=h9eae976_0
+  - tk=8.6.13=noxft_h4845f30_101
+  - wheel=0.45.1=pyhd8ed1ab_1
+  - xz=5.6.3=hbcc6ac9_1
+  - xz-gpl-tools=5.6.3=hbcc6ac9_1
+  - xz-tools=5.6.3=hb9d3cd8_1
+  - pip:
+      - accelerate==0.32.1
+      - aiohappyeyeballs==2.4.3
+      - aiohttp==3.11.2
+      - aioprometheus==23.12.0
+      - aiosignal==1.3.1
+      - annotated-types==0.7.0
+      - anthropic==0.39.0
+      - anyio==4.6.2.post1
+      - argcomplete==3.5.1
+      - arrow==1.3.0
+      - async-timeout==5.0.1
+      - attrs==24.2.0
+      - azure-core==1.32.0
+      - azure-identity==1.19.0
+      - azure-storage-blob==12.24.0
+      - azure-storage-file-datalake==12.18.0
+      - backoff==2.2.1
+      - bcrypt==4.2.0
+      - blobfile==3.0.0
+      - boto3==1.35.63
+      - botocore==1.35.63
+      - brotli==1.1.0
+      - cachetools==5.5.0
+      - certifi==2024.8.30
+      - cffi==1.17.1
+      - charset-normalizer==3.4.0
+      - circuitbreaker==2.0.0
+      - click==8.1.7
+      - cloudpickle==3.1.0
+      - compressed-tensors==0.8.0
+      - contourpy==1.3.1
+      - cramjam==2.9.0
+      - cryptography==43.0.3
+      - cycler==0.12.1
+      - datasets==2.20.0
+      - debugpy==1.8.11
+      - dill==0.3.8
+      - diskcache==5.6.3
+      - distro==1.9.0
+      - docker-pycreds==0.4.0
+      - docstring-parser==0.16
+      - einops==0.8.0
+      - fastapi==0.115.5
+      - filelock==3.16.1
+      - flash-attn==2.6.1
+      - fonttools==4.55.0
+      - frozenlist==1.5.0
+      - fsspec==2024.5.0
+      - gguf==0.10.0
+      - gitdb==4.0.11
+      - gitpython==3.1.43
+      - google-api-core==2.23.0
+      - google-auth==2.36.0
+      - google-cloud-aiplatform==1.71.1
+      - google-cloud-bigquery==3.27.0
+      - google-cloud-core==2.4.1
+      - google-cloud-resource-manager==1.13.1
+      - google-cloud-storage==2.10.0
+      - google-crc32c==1.6.0
+      - google-resumable-media==2.7.2
+      - googleapis-common-protos==1.66.0
+      - gql==3.5.0
+      - graphql-core==3.2.5
+      - grpc-google-iam-v1==0.13.1
+      - grpcio==1.68.0
+      - grpcio-status==1.62.3
+      - h11==0.14.0
+      - httpcore==1.0.7
+      - httptools==0.6.4
+      - httpx==0.27.2
+      - huggingface-hub==0.26.2
+      - idna==3.10
+      - importlib-metadata==8.5.0
+      - interegular==0.3.3
+      - ipython==8.18.0
+      - isodate==0.7.2
+      - jedi==0.19.2
+      - jinja2==3.1.4
+      - jiter==0.7.1
+      - jmespath==1.0.1
+      - jsonschema==4.23.0
+      - jsonschema-specifications==2024.10.1
+      - kiwisolver==1.4.7
+      - lark==1.2.2
+      - llvmlite==0.43.0
+      - lm-format-enforcer==0.10.9
+      - lxml==5.3.0
+      - markdown-it-py==3.0.0
+      - markupsafe==3.0.2
+      - matplotlib==3.9.2
+      - mdurl==0.1.2
+      - mosaicml-cli==0.5.34
+      - mosaicml-streaming==0.8.1
+      - mpmath==1.3.0
+      - msal==1.31.1
+      - msal-extensions==1.2.0
+      - msgpack==1.1.0
+      - msgspec==0.18.6
+      - multidict==6.1.0
+      - multiprocess==0.70.16
+      - networkx==3.4.2
+      - ninja==1.11.1.1
+      - numba==0.60.0
+      - numpy==1.26.3
+      - nvidia-cublas-cu12==12.1.3.1
+      - nvidia-cuda-cupti-cu12==12.1.105
+      - nvidia-cuda-nvrtc-cu12==12.1.105
+      - nvidia-cuda-runtime-cu12==12.1.105
+      - nvidia-cudnn-cu12==9.1.0.70
+      - nvidia-cufft-cu12==11.0.2.54
+      - nvidia-curand-cu12==10.3.2.106
+      - nvidia-cusolver-cu12==11.4.5.107
+      - nvidia-cusparse-cu12==12.1.0.106
+      - nvidia-ml-py==12.560.30
+      - nvidia-nccl-cu12==2.20.5
+      - nvidia-nvjitlink-cu12==12.4.127
+      - nvidia-nvtx-cu12==12.1.105
+      - oci==2.138.1
+      - openai==1.54.5
+      - opencv-python-headless==4.10.0.84
+      - orjson==3.10.11
+      - outlines==0.0.46
+      - packaging==24.1
+      - pandas==2.2.1
+      - paramiko==3.5.0
+      - partial-json-parser==0.2.1.1.post4
+      - pillow==10.4.0
+      - portalocker==2.10.1
+      - prometheus-client==0.21.0
+      - prometheus-fastapi-instrumentator==7.0.0
+      - prompt-toolkit==3.0.36
+      - propcache==0.2.0
+      - proto-plus==1.25.0
+      - protobuf==4.25.3
+      - py-cpuinfo==9.0.0
+      - pyairports==2.1.1
+      - pyarrow==18.0.0
+      - pyarrow-hotfix==0.6
+      - pyasn1==0.6.1
+      - pyasn1-modules==0.4.1
+      - pycountry==24.6.1
+      - pycparser==2.22
+      - pycryptodomex==3.21.0
+      - pydantic==2.9.2
+      - pydantic-core==2.23.4
+      - pyjwt==2.10.0
+      - pynacl==1.5.0
+      - pyopenssl==24.2.1
+      - pyparsing==3.2.0
+      - python-dateutil==2.9.0
+      - python-dotenv==1.0.1
+      - python-snappy==0.7.3
+      - pytz==2024.2
+      - pyyaml==6.0.2
+      - quantile-python==1.1
+      - questionary==2.0.1
+      - ray==2.39.0
+      - referencing==0.35.1
+      - regex==2023.12.25
+      - requests==2.32.3
+      - rich==13.9.4
+      - rotary-emb==0.5.2
+      - rpds-py==0.21.0
+      - rsa==4.9
+      - ruamel-yaml==0.18.6
+      - ruamel-yaml-clib==0.2.12
+      - s3transfer==0.10.3
+      - safetensors==0.4.5
+      - sentencepiece==0.1.99
+      - sentry-sdk==2.18.0
+      - setproctitle==1.3.4
+      - shapely==2.0.6
+      - smmap==5.0.1
+      - sniffio==1.3.1
+      - starlette==0.41.3
+      - sympy==1.13.1
+      - tiktoken==0.7.0
+      - tokenizers==0.19.1
+      - torch==2.4.1
+      - torchvision==0.19.1
+      - tqdm==4.66.4
+      - transformers==4.44.2
+      - triton==3.0.0
+      - types-python-dateutil==2.9.0.20241003
+      - tzdata==2024.2
+      - urllib3==2.2.3
+      - uvicorn==0.32.0
+      - uvloop==0.21.0
+      - validators==0.34.0
+      - vertexai==1.71.1
+      - wandb==0.17.3
+      - watchfiles==0.24.0
+      - websockets==11.0.3
+      - xformers==0.0.28.post1
+      - xxhash==3.5.0
+      - yarl==1.17.2
+      - zipp==3.21.0
+      - zstandard==0.22.0
+      - zstd==1.5.5.1
+prefix: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final

wandb/run-20241226_145403-c7ovtvny/files/config.yaml

@@ -0,0 +1,705 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.10.0
+    cli_version: 0.17.3
+    framework: huggingface
+    huggingface_version: 4.44.2
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    start_time: 1735224843
+    t:
+      1:
+      - 1
+      - 11
+      - 41
+      - 49
+      - 51
+      - 55
+      - 71
+      - 105
+      2:
+      - 1
+      - 11
+      - 41
+      - 49
+      - 51
+      - 55
+      - 71
+      - 105
+      3:
+      - 7
+      - 13
+      - 19
+      - 23
+      - 66
+      4: 3.10.0
+      5: 0.17.3
+      6: 4.44.2
+      8:
+      - 5
+      9:
+        1: transformers_trainer
+      13: linux-x86_64
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    - 1: train/loss
+      5: 1
+      6:
+      - 1
+    - 1: train/grad_norm
+      5: 1
+      6:
+      - 1
+    - 1: train/learning_rate
+      5: 1
+      6:
+      - 1
+    - 1: train/epoch
+      5: 1
+      6:
+      - 1
+    - 1: train/num_input_tokens_seen
+      5: 1
+      6:
+      - 1
+vocab_size:
+  desc: null
+  value: 128256
+max_position_embeddings:
+  desc: null
+  value: 524288
+hidden_size:
+  desc: null
+  value: 4096
+intermediate_size:
+  desc: null
+  value: 14336
+num_hidden_layers:
+  desc: null
+  value: 32
+num_attention_heads:
+  desc: null
+  value: 32
+num_key_value_heads:
+  desc: null
+  value: 8
+hidden_act:
+  desc: null
+  value: silu
+initializer_range:
+  desc: null
+  value: 0.02
+rms_norm_eps:
+  desc: null
+  value: 1.0e-05
+pretraining_tp:
+  desc: null
+  value: 1
+use_cache:
+  desc: null
+  value: true
+rope_theta:
+  desc: null
+  value: 128000000.0
+rope_scaling:
+  desc: null
+  value: null
+attention_bias:
+  desc: null
+  value: false
+attention_dropout:
+  desc: null
+  value: 0.0
+mlp_bias:
+  desc: null
+  value: false
+return_dict:
+  desc: null
+  value: true
+output_hidden_states:
+  desc: null
+  value: false
+output_attentions:
+  desc: null
+  value: false
+torchscript:
+  desc: null
+  value: false
+torch_dtype:
+  desc: null
+  value: float32
+use_bfloat16:
+  desc: null
+  value: false
+tf_legacy_loss:
+  desc: null
+  value: false
+pruned_heads:
+  desc: null
+  value: {}
+tie_word_embeddings:
+  desc: null
+  value: false
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+is_encoder_decoder:
+  desc: null
+  value: false
+is_decoder:
+  desc: null
+  value: false
+cross_attention_hidden_size:
+  desc: null
+  value: null
+add_cross_attention:
+  desc: null
+  value: false
+tie_encoder_decoder:
+  desc: null
+  value: false
+max_length:
+  desc: null
+  value: 20
+min_length:
+  desc: null
+  value: 0
+do_sample:
+  desc: null
+  value: false
+early_stopping:
+  desc: null
+  value: false
+num_beams:
+  desc: null
+  value: 1
+num_beam_groups:
+  desc: null
+  value: 1
+diversity_penalty:
+  desc: null
+  value: 0.0
+temperature:
+  desc: null
+  value: 1.0
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+typical_p:
+  desc: null
+  value: 1.0
+repetition_penalty:
+  desc: null
+  value: 1.0
+length_penalty:
+  desc: null
+  value: 1.0
+no_repeat_ngram_size:
+  desc: null
+  value: 0
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+bad_words_ids:
+  desc: null
+  value: null
+num_return_sequences:
+  desc: null
+  value: 1
+output_scores:
+  desc: null
+  value: false
+return_dict_in_generate:
+  desc: null
+  value: false
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+remove_invalid_values:
+  desc: null
+  value: false
+exponential_decay_length_penalty:
+  desc: null
+  value: null
+suppress_tokens:
+  desc: null
+  value: null
+begin_suppress_tokens:
+  desc: null
+  value: null
+architectures:
+  desc: null
+  value:
+  - LlamaForCausalLM
+finetuning_task:
+  desc: null
+  value: null
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+tokenizer_class:
+  desc: null
+  value: null
+prefix:
+  desc: null
+  value: null
+bos_token_id:
+  desc: null
+  value: 128000
+pad_token_id:
+  desc: null
+  value: 0
+eos_token_id:
+  desc: null
+  value: 128009
+sep_token_id:
+  desc: null
+  value: null
+decoder_start_token_id:
+  desc: null
+  value: null
+task_specific_params:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+_name_or_path:
+  desc: null
+  value: /scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/
+transformers_version:
+  desc: null
+  value: 4.44.2
+model_type:
+  desc: null
+  value: llama
+output_dir:
+  desc: null
+  value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
+overwrite_output_dir:
+  desc: null
+  value: false
+do_train:
+  desc: null
+  value: true
+do_eval:
+  desc: null
+  value: false
+do_predict:
+  desc: null
+  value: false
+eval_strategy:
+  desc: null
+  value: 'no'
+prediction_loss_only:
+  desc: null
+  value: false
+per_device_train_batch_size:
+  desc: null
+  value: 1
+per_device_eval_batch_size:
+  desc: null
+  value: 8
+per_gpu_train_batch_size:
+  desc: null
+  value: null
+per_gpu_eval_batch_size:
+  desc: null
+  value: null
+gradient_accumulation_steps:
+  desc: null
+  value: 2
+eval_accumulation_steps:
+  desc: null
+  value: null
+eval_delay:
+  desc: null
+  value: 0
+torch_empty_cache_steps:
+  desc: null
+  value: null
+learning_rate:
+  desc: null
+  value: 1.0e-06
+weight_decay:
+  desc: null
+  value: 0.1
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.95
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+max_grad_norm:
+  desc: null
+  value: 1.0
+num_train_epochs:
+  desc: null
+  value: 1.0
+max_steps:
+  desc: null
+  value: -1
+lr_scheduler_type:
+  desc: null
+  value: cosine
+lr_scheduler_kwargs:
+  desc: null
+  value: {}
+warmup_ratio:
+  desc: null
+  value: 0.05
+warmup_steps:
+  desc: null
+  value: 0
+log_level:
+  desc: null
+  value: info
+log_level_replica:
+  desc: null
+  value: warning
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec26_14-47-22_gpu021
+logging_strategy:
+  desc: null
+  value: steps
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 1.0
+logging_nan_inf_filter:
+  desc: null
+  value: true
+save_strategy:
+  desc: null
+  value: steps
+save_steps:
+  desc: null
+  value: 200
+save_total_limit:
+  desc: null
+  value: null
+save_safetensors:
+  desc: null
+  value: true
+save_on_each_node:
+  desc: null
+  value: false
+save_only_model:
+  desc: null
+  value: false
+restore_callback_states_from_checkpoint:
+  desc: null
+  value: false
+no_cuda:
+  desc: null
+  value: false
+use_cpu:
+  desc: null
+  value: false
+use_mps_device:
+  desc: null
+  value: false
+seed:
+  desc: null
+  value: 42
+data_seed:
+  desc: null
+  value: null
+jit_mode_eval:
+  desc: null
+  value: false
+use_ipex:
+  desc: null
+  value: false
+bf16:
+  desc: null
+  value: true
+fp16:
+  desc: null
+  value: false
+fp16_opt_level:
+  desc: null
+  value: O1
+half_precision_backend:
+  desc: null
+  value: auto
+bf16_full_eval:
+  desc: null
+  value: false
+fp16_full_eval:
+  desc: null
+  value: false
+tf32:
+  desc: null
+  value: null
+local_rank:
+  desc: null
+  value: 0
+ddp_backend:
+  desc: null
+  value: null
+tpu_num_cores:
+  desc: null
+  value: null
+tpu_metrics_debug:
+  desc: null
+  value: false
+debug:
+  desc: null
+  value: []
+dataloader_drop_last:
+  desc: null
+  value: false
+eval_steps:
+  desc: null
+  value: null
+dataloader_num_workers:
+  desc: null
+  value: 1
+dataloader_prefetch_factor:
+  desc: null
+  value: null
+past_index:
+  desc: null
+  value: -1
+run_name:
+  desc: null
+  value: balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
+disable_tqdm:
+  desc: null
+  value: true
+remove_unused_columns:
+  desc: null
+  value: false
+label_names:
+  desc: null
+  value: null
+load_best_model_at_end:
+  desc: null
+  value: false
+metric_for_best_model:
+  desc: null
+  value: null
+greater_is_better:
+  desc: null
+  value: null
+ignore_data_skip:
+  desc: null
+  value: true
+fsdp:
+  desc: null
+  value:
+  - auto_wrap
+  - offload
+fsdp_min_num_params:
+  desc: null
+  value: 0
+fsdp_config:
+  desc: null
+  value:
+    min_num_params: 0
+    xla: false
+    xla_fsdp_v2: false
+    xla_fsdp_grad_ckpt: false
+fsdp_transformer_layer_cls_to_wrap:
+  desc: null
+  value: null
+accelerator_config:
+  desc: null
+  value:
+    split_batches: false
+    dispatch_batches: null
+    even_batches: true
+    use_seedable_sampler: true
+    non_blocking: false
+    gradient_accumulation_kwargs: null
+deepspeed:
+  desc: null
+  value: null
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+optim:
+  desc: null
+  value: adamw_torch
+optim_args:
+  desc: null
+  value: null
+adafactor:
+  desc: null
+  value: false
+group_by_length:
+  desc: null
+  value: false
+length_column_name:
+  desc: null
+  value: length
+report_to:
+  desc: null
+  value:
+  - wandb
+ddp_find_unused_parameters:
+  desc: null
+  value: false
+ddp_bucket_cap_mb:
+  desc: null
+  value: null
+ddp_broadcast_buffers:
+  desc: null
+  value: null
+dataloader_pin_memory:
+  desc: null
+  value: true
+dataloader_persistent_workers:
+  desc: null
+  value: false
+skip_memory_metrics:
+  desc: null
+  value: true
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+push_to_hub:
+  desc: null
+  value: false
+resume_from_checkpoint:
+  desc: null
+  value: null
+hub_model_id:
+  desc: null
+  value: null
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+hub_private_repo:
+  desc: null
+  value: false
+hub_always_push:
+  desc: null
+  value: false
+gradient_checkpointing:
+  desc: null
+  value: true
+gradient_checkpointing_kwargs:
+  desc: null
+  value: null
+include_inputs_for_metrics:
+  desc: null
+  value: false
+eval_do_concat_batches:
+  desc: null
+  value: true
+fp16_backend:
+  desc: null
+  value: auto
+evaluation_strategy:
+  desc: null
+  value: null
+push_to_hub_model_id:
+  desc: null
+  value: null
+push_to_hub_organization:
+  desc: null
+  value: null
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+mp_parameters:
+  desc: null
+  value: ''
+auto_find_batch_size:
+  desc: null
+  value: false
+full_determinism:
+  desc: null
+  value: false
+torchdynamo:
+  desc: null
+  value: null
+ray_scope:
+  desc: null
+  value: last
+ddp_timeout:
+  desc: null
+  value: 1800
+torch_compile:
+  desc: null
+  value: false
+torch_compile_backend:
+  desc: null
+  value: null
+torch_compile_mode:
+  desc: null
+  value: null
+dispatch_batches:
+  desc: null
+  value: null
+split_batches:
+  desc: null
+  value: null
+include_tokens_per_second:
+  desc: null
+  value: false
+include_num_input_tokens_seen:
+  desc: null
+  value: false
+neftune_noise_alpha:
+  desc: null
+  value: null
+optim_target_modules:
+  desc: null
+  value: null
+batch_eval_metrics:
+  desc: null
+  value: false
+eval_on_start:
+  desc: null
+  value: false
+eval_use_gather_object:
+  desc: null
+  value: false
+min_lr_ratio:
+  desc: null
+  value: 0.1
+cuda_empty_cache:
+  desc: null
+  value: true
+streaming_dataset:
+  desc: null
+  value: true
+seq_parallel_size:
+  desc: null
+  value: 8
+model/num_parameters:
+  desc: null
+  value: 1003782656

wandb/run-20241226_145403-c7ovtvny/files/requirements.txt

@@ -0,0 +1,242 @@
+Brotli==1.1.0
+GitPython==3.1.43
+Jinja2==3.1.4
+MarkupSafe==3.0.2
+PyJWT==2.10.0
+PyNaCl==1.5.0
+PyYAML==6.0.2
+Pygments==2.18.0
+accelerate==0.32.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.11.2
+aioprometheus==23.12.0
+aiosignal==1.3.1
+annotated-types==0.7.0
+anthropic==0.39.0
+anyio==4.6.2.post1
+argcomplete==3.5.1
+arrow==1.3.0
+asttokens==2.4.1
+async-timeout==5.0.1
+attrs==24.2.0
+autocommand==2.2.2
+azure-core==1.32.0
+azure-identity==1.19.0
+azure-storage-blob==12.24.0
+azure-storage-file-datalake==12.18.0
+backoff==2.2.1
+backports.tarfile==1.2.0
+bcrypt==4.2.0
+blobfile==3.0.0
+boto3==1.35.63
+botocore==1.35.63
+cachetools==5.5.0
+certifi==2024.8.30
+cffi==1.17.1
+charset-normalizer==3.4.0
+circuitbreaker==2.0.0
+click==8.1.7
+cloudpickle==3.1.0
+comm==0.2.2
+compressed-tensors==0.8.0
+contourpy==1.3.1
+cramjam==2.9.0
+cryptography==43.0.3
+cycler==0.12.1
+datasets==2.20.0
+debugpy==1.8.11
+decorator==5.1.1
+dill==0.3.8
+diskcache==5.6.3
+distro==1.9.0
+docker-pycreds==0.4.0
+docstring_parser==0.16
+einops==0.8.0
+exceptiongroup==1.2.2
+executing==2.1.0
+fastapi==0.115.5
+filelock==3.16.1
+flash-attn==2.6.1
+fonttools==4.55.0
+frozenlist==1.5.0
+fsspec==2024.5.0
+gguf==0.10.0
+gitdb==4.0.11
+google-api-core==2.23.0
+google-auth==2.36.0
+google-cloud-aiplatform==1.71.1
+google-cloud-bigquery==3.27.0
+google-cloud-core==2.4.1
+google-cloud-resource-manager==1.13.1
+google-cloud-storage==2.10.0
+google-crc32c==1.6.0
+google-resumable-media==2.7.2
+googleapis-common-protos==1.66.0
+gql==3.5.0
+graphql-core==3.2.5
+grpc-google-iam-v1==0.13.1
+grpcio-status==1.62.3
+grpcio==1.68.0
+h11==0.14.0
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.27.2
+huggingface-hub==0.26.2
+idna==3.10
+importlib_metadata==8.0.0
+importlib_metadata==8.5.0
+inflect==7.3.1
+interegular==0.3.3
+ipykernel==6.29.5
+ipython==8.18.0
+isodate==0.7.2
+jaraco.collections==5.1.0
+jaraco.context==5.3.0
+jaraco.functools==4.0.1
+jaraco.text==3.12.1
+jedi==0.19.2
+jiter==0.7.1
+jmespath==1.0.1
+jsonschema-specifications==2024.10.1
+jsonschema==4.23.0
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+kiwisolver==1.4.7
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.9
+lxml==5.3.0
+markdown-it-py==3.0.0
+matplotlib-inline==0.1.7
+matplotlib==3.9.2
+mdurl==0.1.2
+more-itertools==10.3.0
+mosaicml-cli==0.5.34
+mosaicml-streaming==0.8.1
+mpmath==1.3.0
+msal-extensions==1.2.0
+msal==1.31.1
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.16
+nest-asyncio==1.6.0
+networkx==3.4.2
+ninja==1.11.1.1
+numba==0.60.0
+numpy==1.26.3
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==12.560.30
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.1.105
+oci==2.138.1
+openai==1.54.5
+opencv-python-headless==4.10.0.84
+orjson==3.10.11
+outlines==0.0.46
+packaging==24.1
+packaging==24.2
+pandas==2.2.1
+paramiko==3.5.0
+parso==0.8.4
+partial-json-parser==0.2.1.1.post4
+pexpect==4.9.0
+pillow==10.4.0
+pip==24.3.1
+platformdirs==4.2.2
+platformdirs==4.3.6
+portalocker==2.10.1
+prometheus-fastapi-instrumentator==7.0.0
+prometheus_client==0.21.0
+prompt-toolkit==3.0.36
+propcache==0.2.0
+proto-plus==1.25.0
+protobuf==4.25.3
+psutil==6.1.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+py-cpuinfo==9.0.0
+pyOpenSSL==24.2.1
+pyairports==2.1.1
+pyarrow-hotfix==0.6
+pyarrow==18.0.0
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycountry==24.6.1
+pycparser==2.22
+pycryptodomex==3.21.0
+pydantic==2.9.2
+pydantic_core==2.23.4
+pyparsing==3.2.0
+python-dateutil==2.9.0
+python-dotenv==1.0.1
+python-snappy==0.7.3
+pytz==2024.2
+pyzmq==26.2.0
+quantile-python==1.1
+questionary==2.0.1
+ray==2.39.0
+referencing==0.35.1
+regex==2023.12.25
+requests==2.32.3
+rich==13.9.4
+rotary-emb==0.5.2
+rpds-py==0.21.0
+rsa==4.9
+ruamel.yaml.clib==0.2.12
+ruamel.yaml==0.18.6
+s3transfer==0.10.3
+safetensors==0.4.5
+sentencepiece==0.1.99
+sentry-sdk==2.18.0
+setproctitle==1.3.4
+setuptools==75.6.0
+shapely==2.0.6
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+stack-data==0.6.3
+starlette==0.41.3
+sympy==1.13.1
+tiktoken==0.7.0
+tokenizers==0.19.1
+tomli==2.0.1
+torch==2.4.1
+torchvision==0.19.1
+tornado==6.4.1
+tqdm==4.66.4
+traitlets==5.14.3
+transformers==4.44.2
+triton==3.0.0
+typeguard==4.3.0
+types-python-dateutil==2.9.0.20241003
+typing_extensions==4.12.2
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.32.0
+uvloop==0.21.0
+validators==0.34.0
+vertexai==1.71.1
+wandb==0.17.3
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==11.0.3
+wheel==0.43.0
+wheel==0.45.1
+xformers==0.0.28.post1
+xxhash==3.5.0
+yarl==1.17.2
+zipp==3.19.2
+zipp==3.21.0
+zstandard==0.22.0
+zstd==1.5.5.1

wandb/run-20241226_145403-c7ovtvny/files/wandb-metadata.json

@@ -0,0 +1,705 @@
+{
+    "os": "Linux-6.8.0-48-generic-x86_64-with-glibc2.39",
+    "python": "3.10.0",
+    "heartbeatAt": "2024-12-26T14:54:03.533915",
+    "startedAt": "2024-12-26T14:54:03.029672",
+    "docker": null,
+    "cuda": null,
+    "args": [
+        "--model_family",
+        "llama",
+        "--apply_instruct_masks",
+        "--token_scaled_loss",
+        "--seq_parallel_size",
+        "8",
+        "--report_to",
+        "wandb",
+        "--do_train",
+        "--model_name_or_path",
+        "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
+        "--config_name",
+        "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
+        "--tokenizer_name",
+        "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
+        "--run_name",
+        "balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
+        "--output_dir",
+        "/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
+        "--config_overrides_json",
+        "",
+        "--gradient_accumulation_steps",
+        "2",
+        "--per_device_train_batch_size",
+        "1",
+        "--bf16",
+        "--learning_rate",
+        "1e-6",
+        "--min_lr_ratio",
+        "0.1",
+        "--lr_scheduler_type",
+        "cosine",
+        "--max_grad_norm",
+        "1.0",
+        "--adam_beta1",
+        "0.9",
+        "--adam_beta2",
+        "0.95",
+        "--weight_decay",
+        "0.1",
+        "--warmup_ratio",
+        "0.05",
+        "--optim",
+        "adamw_torch",
+        "--logging_steps",
+        "1",
+        "--log_level",
+        "info",
+        "--save_steps",
+        "200",
+        "--dataloader_num_workers",
+        "1",
+        "--disable_tqdm",
+        "true",
+        "--use_fast_tokenizer",
+        "false",
+        "--remove_unused_columns",
+        "false",
+        "--ddp_find_unused_parameters",
+        "false",
+        "--fsdp",
+        "auto_wrap offload",
+        "--gradient_checkpointing",
+        "--tokenized_mds_train",
+        "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/data/ft/bookclaim_balanced_pack_complete",
+        "--cuda_empty_cache",
+        "--num_train_epochs",
+        "1"
+    ],
+    "state": "running",
+    "program": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py",
+    "codePathLocal": "finetune.py",
+    "codePath": "prolong-final/finetune.py",
+    "git": {
+        "remote": "https://github.com/chtmp223/BookGen-dev.git",
+        "commit": "438e68ae65a707227d28baa427c5f6fdb0932c7b"
+    },
+    "email": "[email protected]",
+    "root": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev",
+    "host": "gpu021",
+    "username": "ctpham_umass_edu",
+    "executable": "/scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final/bin/python3.10",
+    "cpu_count": 112,
+    "cpu_count_logical": 112,
+    "cpu_freq": {
+        "current": 903.8299553571429,
+        "min": 800.0,
+        "max": 3800.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 790.24,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1600.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1700.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 784.117,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 787.786,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1000.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 892.512,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1400.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 790.711,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 790.69,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1300.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 2400.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1100.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1782.468,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1100.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1700.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 1000.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 784.039,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 782.714,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 783.793,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 794.544,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 784.441,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3800.0
+        }
+    ],
+    "disk": {
+        "/": {
+            "total": 438.487850189209,
+            "used": 16.265323638916016
+        }
+    },
+    "gpu": "NVIDIA A100-SXM4-80GB",
+    "gpu_count": 8,
+    "gpu_devices": [
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        }
+    ],
+    "memory": {
+        "total": 2015.3287200927734
+    }
+}

wandb/run-20241226_145403-c7ovtvny/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss": 0.4968, "train/grad_norm": 16.78160285949707, "train/learning_rate": 1.4057417934619453e-07, "train/epoch": 0.21969080553295361, "train/num_input_tokens_seen": 6731857920, "train/global_step": 3210, "_timestamp": 1735250926.6301687, "_runtime": 26083.580728769302, "_step": 809}

wandb/run-20241226_145403-c7ovtvny/logs/debug.log

@@ -0,0 +1,31 @@
+2024-12-26 14:54:03,041 INFO    MainThread:821408 [wandb_setup.py:_flush():76] Current SDK version is 0.17.3
+2024-12-26 14:54:03,041 INFO    MainThread:821408 [wandb_setup.py:_flush():76] Configure stats pid to 821408
+2024-12-26 14:54:03,041 INFO    MainThread:821408 [wandb_setup.py:_flush():76] Loading settings from /home/ctpham_umass_edu/.config/wandb/settings
+2024-12-26 14:54:03,041 INFO    MainThread:821408 [wandb_setup.py:_flush():76] Loading settings from /work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/wandb/settings
+2024-12-26 14:54:03,041 INFO    MainThread:821408 [wandb_setup.py:_flush():76] Loading settings from environment variables: {'root_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'project': 'prolong', 'api_key': '***REDACTED***', 'mode': 'online'}
+2024-12-26 14:54:03,042 INFO    MainThread:821408 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-12-26 14:54:03,042 INFO    MainThread:821408 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'prolong-final/finetune.py', 'program_abspath': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py', 'program': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py'}
+2024-12-26 14:54:03,042 INFO    MainThread:821408 [wandb_setup.py:_flush():76] Applying login settings: {}
+2024-12-26 14:54:03,042 INFO    MainThread:821408 [wandb_init.py:_log_setup():520] Logging user logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241226_145403-c7ovtvny/logs/debug.log
+2024-12-26 14:54:03,042 INFO    MainThread:821408 [wandb_init.py:_log_setup():521] Logging internal logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241226_145403-c7ovtvny/logs/debug-internal.log
+2024-12-26 14:54:03,042 INFO    MainThread:821408 [wandb_init.py:init():560] calling init triggers
+2024-12-26 14:54:03,042 INFO    MainThread:821408 [wandb_init.py:init():567] wandb.init called with sweep_config: {}
+config: {}
+2024-12-26 14:54:03,042 INFO    MainThread:821408 [wandb_init.py:init():610] starting backend
+2024-12-26 14:54:03,042 INFO    MainThread:821408 [wandb_init.py:init():614] setting up manager
+2024-12-26 14:54:03,045 INFO    MainThread:821408 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-12-26 14:54:03,048 INFO    MainThread:821408 [wandb_init.py:init():622] backend started and connected
+2024-12-26 14:54:03,057 INFO    MainThread:821408 [wandb_init.py:init():711] updated telemetry
+2024-12-26 14:54:03,100 INFO    MainThread:821408 [wandb_init.py:init():744] communicating run to backend with 90.0 second timeout
+2024-12-26 14:54:03,347 INFO    MainThread:821408 [wandb_run.py:_on_init():2402] communicating current version
+2024-12-26 14:54:03,407 INFO    MainThread:821408 [wandb_run.py:_on_init():2411] got version response upgrade_message: "wandb version 0.19.1 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2024-12-26 14:54:03,407 INFO    MainThread:821408 [wandb_init.py:init():795] starting run threads in backend
+2024-12-26 14:54:11,326 INFO    MainThread:821408 [wandb_run.py:_console_start():2380] atexit reg
+2024-12-26 14:54:11,326 INFO    MainThread:821408 [wandb_run.py:_redirect():2235] redirect: wrap_raw
+2024-12-26 14:54:11,326 INFO    MainThread:821408 [wandb_run.py:_redirect():2300] Wrapping output streams.
+2024-12-26 14:54:11,326 INFO    MainThread:821408 [wandb_run.py:_redirect():2325] Redirects installed.
+2024-12-26 14:54:11,328 INFO    MainThread:821408 [wandb_init.py:init():838] run started, returning control to user process
+2024-12-26 14:54:11,330 INFO    MainThread:821408 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 128256, 'max_position_embeddings': 524288, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': True, 'rope_theta': 128000000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 128000, 'pad_token_id': 0, 'eos_token_id': 128009, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': '/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/', 'transformers_version': '4.44.2', 'model_type': 'llama', 'output_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'overwrite_output_dir': False, 'do_train': True, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-06, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.05, 'warmup_steps': 0, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec26_14-47-22_gpu021', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1.0, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 200, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 1, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'disable_tqdm': True, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': True, 'fsdp': ['auto_wrap', 'offload'], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': False, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False, 'min_lr_ratio': 0.1, 'cuda_empty_cache': True, 'streaming_dataset': True, 'seq_parallel_size': 8}
+2024-12-26 14:54:11,333 INFO    MainThread:821408 [wandb_config.py:__setitem__():151] config set model/num_parameters = 1003782656 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7d56b9546da0>>
+2024-12-26 14:54:11,333 INFO    MainThread:821408 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 1003782656 None

wandb/run-20241226_145403-c7ovtvny/run-c7ovtvny.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4515d1b5896835583655b9ecdfda579f01b8079e4399415d206f76bff8f05046
+size 5248016

wandb/run-20241226_224836-fta6xses/files/conda-environment.yaml

@@ -0,0 +1,232 @@
+name: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final
+channels:
+  - conda-forge
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - bzip2=1.0.8=h4bc722e_7
+  - ca-certificates=2024.12.14=hbcca054_0
+  - ld_impl_linux-64=2.43=h712a8e2_2
+  - libffi=3.4.2=h7f98852_5
+  - libgcc=14.2.0=h77fa898_1
+  - libgcc-ng=14.2.0=h69a702a_1
+  - libgomp=14.2.0=h77fa898_1
+  - liblzma=5.6.3=hb9d3cd8_1
+  - liblzma-devel=5.6.3=hb9d3cd8_1
+  - libnsl=2.0.1=hd590300_0
+  - libsqlite=3.47.2=hee588c1_0
+  - libuuid=2.38.1=h0b41bf4_0
+  - libzlib=1.3.1=hb9d3cd8_2
+  - ncurses=6.5=he02047a_1
+  - openssl=3.4.0=hb9d3cd8_0
+  - pip=24.3.1=pyh8b19718_2
+  - python=3.10.0=h543edf9_3_cpython
+  - readline=8.2=h8228510_1
+  - setuptools=75.6.0=pyhff2d567_1
+  - sqlite=3.47.2=h9eae976_0
+  - tk=8.6.13=noxft_h4845f30_101
+  - wheel=0.45.1=pyhd8ed1ab_1
+  - xz=5.6.3=hbcc6ac9_1
+  - xz-gpl-tools=5.6.3=hbcc6ac9_1
+  - xz-tools=5.6.3=hb9d3cd8_1
+  - pip:
+      - accelerate==0.32.1
+      - aiohappyeyeballs==2.4.3
+      - aiohttp==3.11.2
+      - aioprometheus==23.12.0
+      - aiosignal==1.3.1
+      - annotated-types==0.7.0
+      - anthropic==0.39.0
+      - anyio==4.6.2.post1
+      - argcomplete==3.5.1
+      - arrow==1.3.0
+      - async-timeout==5.0.1
+      - attrs==24.2.0
+      - azure-core==1.32.0
+      - azure-identity==1.19.0
+      - azure-storage-blob==12.24.0
+      - azure-storage-file-datalake==12.18.0
+      - backoff==2.2.1
+      - bcrypt==4.2.0
+      - blobfile==3.0.0
+      - boto3==1.35.63
+      - botocore==1.35.63
+      - brotli==1.1.0
+      - cachetools==5.5.0
+      - certifi==2024.8.30
+      - cffi==1.17.1
+      - charset-normalizer==3.4.0
+      - circuitbreaker==2.0.0
+      - click==8.1.7
+      - cloudpickle==3.1.0
+      - compressed-tensors==0.8.0
+      - contourpy==1.3.1
+      - cramjam==2.9.0
+      - cryptography==43.0.3
+      - cycler==0.12.1
+      - datasets==2.20.0
+      - debugpy==1.8.11
+      - dill==0.3.8
+      - diskcache==5.6.3
+      - distro==1.9.0
+      - docker-pycreds==0.4.0
+      - docstring-parser==0.16
+      - einops==0.8.0
+      - fastapi==0.115.5
+      - filelock==3.16.1
+      - flash-attn==2.6.1
+      - fonttools==4.55.0
+      - frozenlist==1.5.0
+      - fsspec==2024.5.0
+      - gguf==0.10.0
+      - gitdb==4.0.11
+      - gitpython==3.1.43
+      - google-api-core==2.23.0
+      - google-auth==2.36.0
+      - google-cloud-aiplatform==1.71.1
+      - google-cloud-bigquery==3.27.0
+      - google-cloud-core==2.4.1
+      - google-cloud-resource-manager==1.13.1
+      - google-cloud-storage==2.10.0
+      - google-crc32c==1.6.0
+      - google-resumable-media==2.7.2
+      - googleapis-common-protos==1.66.0
+      - gql==3.5.0
+      - graphql-core==3.2.5
+      - grpc-google-iam-v1==0.13.1
+      - grpcio==1.68.0
+      - grpcio-status==1.62.3
+      - h11==0.14.0
+      - httpcore==1.0.7
+      - httptools==0.6.4
+      - httpx==0.27.2
+      - huggingface-hub==0.26.2
+      - idna==3.10
+      - importlib-metadata==8.5.0
+      - interegular==0.3.3
+      - ipython==8.18.0
+      - isodate==0.7.2
+      - jedi==0.19.2
+      - jinja2==3.1.4
+      - jiter==0.7.1
+      - jmespath==1.0.1
+      - jsonschema==4.23.0
+      - jsonschema-specifications==2024.10.1
+      - kiwisolver==1.4.7
+      - lark==1.2.2
+      - llvmlite==0.43.0
+      - lm-format-enforcer==0.10.9
+      - lxml==5.3.0
+      - markdown-it-py==3.0.0
+      - markupsafe==3.0.2
+      - matplotlib==3.9.2
+      - mdurl==0.1.2
+      - mosaicml-cli==0.5.34
+      - mosaicml-streaming==0.8.1
+      - mpmath==1.3.0
+      - msal==1.31.1
+      - msal-extensions==1.2.0
+      - msgpack==1.1.0
+      - msgspec==0.18.6
+      - multidict==6.1.0
+      - multiprocess==0.70.16
+      - networkx==3.4.2
+      - ninja==1.11.1.1
+      - numba==0.60.0
+      - numpy==1.26.3
+      - nvidia-cublas-cu12==12.1.3.1
+      - nvidia-cuda-cupti-cu12==12.1.105
+      - nvidia-cuda-nvrtc-cu12==12.1.105
+      - nvidia-cuda-runtime-cu12==12.1.105
+      - nvidia-cudnn-cu12==9.1.0.70
+      - nvidia-cufft-cu12==11.0.2.54
+      - nvidia-curand-cu12==10.3.2.106
+      - nvidia-cusolver-cu12==11.4.5.107
+      - nvidia-cusparse-cu12==12.1.0.106
+      - nvidia-ml-py==12.560.30
+      - nvidia-nccl-cu12==2.20.5
+      - nvidia-nvjitlink-cu12==12.4.127
+      - nvidia-nvtx-cu12==12.1.105
+      - oci==2.138.1
+      - openai==1.54.5
+      - opencv-python-headless==4.10.0.84
+      - orjson==3.10.11
+      - outlines==0.0.46
+      - packaging==24.1
+      - pandas==2.2.1
+      - paramiko==3.5.0
+      - partial-json-parser==0.2.1.1.post4
+      - pillow==10.4.0
+      - portalocker==2.10.1
+      - prometheus-client==0.21.0
+      - prometheus-fastapi-instrumentator==7.0.0
+      - prompt-toolkit==3.0.36
+      - propcache==0.2.0
+      - proto-plus==1.25.0
+      - protobuf==4.25.3
+      - py-cpuinfo==9.0.0
+      - pyairports==2.1.1
+      - pyarrow==18.0.0
+      - pyarrow-hotfix==0.6
+      - pyasn1==0.6.1
+      - pyasn1-modules==0.4.1
+      - pycountry==24.6.1
+      - pycparser==2.22
+      - pycryptodomex==3.21.0
+      - pydantic==2.9.2
+      - pydantic-core==2.23.4
+      - pyjwt==2.10.0
+      - pynacl==1.5.0
+      - pyopenssl==24.2.1
+      - pyparsing==3.2.0
+      - python-dateutil==2.9.0
+      - python-dotenv==1.0.1
+      - python-snappy==0.7.3
+      - pytz==2024.2
+      - pyyaml==6.0.2
+      - quantile-python==1.1
+      - questionary==2.0.1
+      - ray==2.39.0
+      - referencing==0.35.1
+      - regex==2023.12.25
+      - requests==2.32.3
+      - rich==13.9.4
+      - rotary-emb==0.5.2
+      - rpds-py==0.21.0
+      - rsa==4.9
+      - ruamel-yaml==0.18.6
+      - ruamel-yaml-clib==0.2.12
+      - s3transfer==0.10.3
+      - safetensors==0.4.5
+      - sentencepiece==0.1.99
+      - sentry-sdk==2.18.0
+      - setproctitle==1.3.4
+      - shapely==2.0.6
+      - smmap==5.0.1
+      - sniffio==1.3.1
+      - starlette==0.41.3
+      - sympy==1.13.1
+      - tiktoken==0.7.0
+      - tokenizers==0.19.1
+      - torch==2.4.1
+      - torchvision==0.19.1
+      - tqdm==4.66.4
+      - transformers==4.44.2
+      - triton==3.0.0
+      - types-python-dateutil==2.9.0.20241003
+      - tzdata==2024.2
+      - urllib3==2.2.3
+      - uvicorn==0.32.0
+      - uvloop==0.21.0
+      - validators==0.34.0
+      - vertexai==1.71.1
+      - wandb==0.17.3
+      - watchfiles==0.24.0
+      - websockets==11.0.3
+      - xformers==0.0.28.post1
+      - xxhash==3.5.0
+      - yarl==1.17.2
+      - zipp==3.21.0
+      - zstandard==0.22.0
+      - zstd==1.5.5.1
+prefix: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final