Add model files and configs

README.md

@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.36.0.dev0
+- Transformers 4.35.2
 - Pytorch 2.2.0.dev20231114
-- Datasets 2.14.6
-- Tokenizers 0.14.1
+- Datasets 2.15.0
+- Tokenizers 0.15.0

all_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.6294479370117188,
-    "train_runtime": 14.4911,
-    "train_samples_per_second": 8.074,
-    "train_steps_per_second": 1.035
+    "train_loss": 0.5570555263095431,
+    "train_runtime": 17.3481,
+    "train_samples_per_second": 7.436,
+    "train_steps_per_second": 1.038
 }

config.json

@@ -45,7 +45,7 @@
   ],
   "problem_type": "single_label_classification",
   "semantic_loss_ignore_index": 255,
-  "transformers_version": "4.36.0.dev0",
+  "transformers_version": "4.35.2",
   "use_absolute_position_embeddings": true,
   "use_auxiliary_head": true,
   "use_mask_token": true,

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.6294479370117188,
-    "train_runtime": 14.4911,
-    "train_samples_per_second": 8.074,
-    "train_steps_per_second": 1.035
+    "train_loss": 0.5570555263095431,
+    "train_runtime": 17.3481,
+    "train_samples_per_second": 7.436,
+    "train_steps_per_second": 1.038
 }

trainer_state.json

@@ -3,26 +3,26 @@
   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 15,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 3.0,
-      "step": 15,
-      "total_flos": 9067617800736768.0,
-      "train_loss": 0.6294479370117188,
-      "train_runtime": 14.4911,
-      "train_samples_per_second": 8.074,
-      "train_steps_per_second": 1.035
+      "step": 18,
+      "total_flos": 9997629882863616.0,
+      "train_loss": 0.5570555263095431,
+      "train_runtime": 17.3481,
+      "train_samples_per_second": 7.436,
+      "train_steps_per_second": 1.038
     }
   ],
   "logging_steps": 500,
-  "max_steps": 15,
+  "max_steps": 18,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 9067617800736768.0,
+  "total_flos": 9997629882863616.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0c1e74c85f426352c503551abb429faf8f58dc744bc1ea002e8c2ffac5493c
-size 4600
+oid sha256:2059d238b115f5ffcbcd8a5d04fc8803894e1dd28e3e8ed4f0d1fe4a199f846e
+size 4536