Training in progress, step 500

config.json

@@ -1,37 +1,29 @@
 {
-  "_name_or_path": "bigcode/santacoder",
-  "activation_function": "gelu_fast",
+  "_name_or_path": "microsoft/codebert-base",
   "architectures": [
-    "GPT2LMHeadCustomModel"
+    "RobertaForCausalLM"
   ],
-  "attention_head_type": "multiquery",
-  "attn_pdrop": 0.1,
-  "auto_map": {
-    "AutoConfig": "bigcode/santacoder--configuration_gpt2_mq.GPT2CustomConfig",
-    "AutoModelForCausalLM": "bigcode/santacoder--modeling_gpt2_mq.GPT2LMHeadCustomModel"
-  },
-  "bos_token_id": 49152,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 49152,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_embd": 2048,
-  "n_head": 16,
-  "n_inner": 8192,
-  "n_layer": 24,
-  "n_positions": 2048,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
+  "intermediate_size": 3072,
+  "is_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.34.1",
+  "transformers_version": "4.35.0",
+  "type_vocab_size": 1,
   "use_cache": false,
-  "vocab_size": 49280
+  "vocab_size": 50265
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f298ad144b799a7cf07bda2b748586f0cf3b6279d2d0a49aa19c6449105465
+size 498813948

runs/Nov07_10-09-45_a72424146e8a/events.out.tfevents.1699351818.a72424146e8a.771.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab23b7d935b7ad5bd51e5fcf1d14ab00725fae8a28693c1045aa79e99d19736
+size 12429

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1a09cd7ad4aae6e268789b65e76aab281f2dcc3bf4ce1986d0d5d7a220d3196
-size 4536
+oid sha256:c8408c29e517fa10487968df65caa388f6b6ce9d13fdf750ac3e06f287920b92
+size 4600