Model save

README.md

@@ -53,5 +53,4 @@ The following hyperparameters were used during training:
 - PEFT 0.13.0
 - Transformers 4.45.2
 - Pytorch 2.4.0
-- Datasets 2.21.0
 - Tokenizers 0.20.0

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "q_proj",
+    "down_proj",
+    "up_proj",
     "k_proj",
-    "v_proj",
     "o_proj",
-    "gate_proj",
-    "down_proj",
-    "up_proj"
+    "v_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c6245eb4daaee1c4c5b51cba6948ff67053ebab3759dc1a01a4ca4fc4dc776
+oid sha256:d83e1ffcf41c38cb37e240f0595b7c1c8ee222452f34d73735b544aaf6b00467
 size 1082290000

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c539a7280f49663488f16c65af4329d4dca3cecaf249910a3780485f16f7ce6
-size 17378692
+oid sha256:6cdb5a41c4ff365aaf322d31b46b6ce2c9f8493fa398bd5ad4fbe6179ebfa53e
+size 17378691

tokenizer_config.json

@@ -9403,6 +9403,6 @@
   ],
   "model_max_length": 2048,
   "pad_token": "!",
-  "padding_side": "right",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

trainer_state.json

@@ -10,40 +10,40 @@
   "log_history": [
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 1.80476975440979,
+      "grad_norm": 1.9892364740371704,
       "learning_rate": 7.587548638132295e-05,
-      "loss": 0.6951,
+      "loss": 0.6525,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 1.3268828392028809,
+      "grad_norm": 1.4275233745574951,
       "learning_rate": 5.155642023346303e-05,
-      "loss": 0.3819,
+      "loss": 0.3853,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 1.490614414215088,
+      "grad_norm": 1.557817816734314,
       "learning_rate": 2.7237354085603113e-05,
-      "loss": 0.3553,
+      "loss": 0.3583,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 1.4715696573257446,
+      "grad_norm": 1.433948278427124,
       "learning_rate": 2.9182879377431908e-06,
-      "loss": 0.3348,
+      "loss": 0.3395,
       "step": 1000
     },
     {
       "epoch": 2.0,
       "step": 1030,
-      "total_flos": 2.5008097487007744e+17,
-      "train_loss": 0.43835841891835037,
-      "train_runtime": 12656.9656,
-      "train_samples_per_second": 20.832,
-      "train_steps_per_second": 0.081
+      "total_flos": 2.5022303713855488e+17,
+      "train_loss": 0.43088643712904845,
+      "train_runtime": 24573.8901,
+      "train_samples_per_second": 10.73,
+      "train_steps_per_second": 0.042
     }
   ],
   "logging_steps": 250,
@@ -63,7 +63,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5008097487007744e+17,
+  "total_flos": 2.5022303713855488e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e0dae5103974b746d2fdd4495fd0e5453b289bdb72e5f359295701cf7eb031
+oid sha256:3bd5ca25124fcf7769a2acce94062b2f60ae59ef5828b4b262fd471889bf7c6f
 size 5176