Upload folder using huggingface_hub

config.json

@@ -4,7 +4,6 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "dtype": "float32",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -36,7 +35,8 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.56.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 28996

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da0d870fe32caaa73b0257d00dcb2e4613ee21a4e48e3a323459477a92afe0b
+oid sha256:a116629a4282b83bbbc6ae5c0c78022c367c952f9b5770c0b4520893160417b0
 size 430923588

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91fd6abd42136eaf14564256ab3a855f1ae4ce27084fd86aebf60c01f9fb02d8
+oid sha256:83814b56092b8cdda9bc091166b623666d463f1dbcd550dc0e134f3869075c12
 size 861970123

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d5263c935b8c615057c961ca54207b077eed325bcf0c80f1a1c5a33a6b0f7f
+oid sha256:ea246aba954a9bf876500e5102a90bebac5164933d3a04b50d122d18b3a18191
 size 14645

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 63,
-  "best_metric": 0.27545732259750366,
+  "best_metric": 0.2536899447441101,
   "best_model_checkpoint": "projects/PetBERT_disease/model/checkpoint-63",
   "epoch": 4.0,
   "eval_steps": 500,
@@ -11,46 +11,46 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_f1": 0.47875495609031343,
-      "eval_loss": 0.27545732259750366,
-      "eval_precision": 0.4511570199977183,
-      "eval_recall": 0.5409002761541312,
-      "eval_runtime": 10.1248,
-      "eval_samples_per_second": 135.114,
-      "eval_steps_per_second": 4.247,
+      "eval_f1": 0.5469600521701229,
+      "eval_loss": 0.2536899447441101,
+      "eval_precision": 0.6240827679507994,
+      "eval_recall": 0.5707008372952973,
+      "eval_runtime": 18.8855,
+      "eval_samples_per_second": 72.437,
+      "eval_steps_per_second": 2.277,
       "step": 63
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.656379559644343,
-      "eval_loss": 0.3127790689468384,
-      "eval_precision": 0.6457809071887031,
-      "eval_recall": 0.7069872637961768,
-      "eval_runtime": 10.2131,
-      "eval_samples_per_second": 133.945,
-      "eval_steps_per_second": 4.21,
+      "eval_f1": 0.6530841773386488,
+      "eval_loss": 0.2897721529006958,
+      "eval_precision": 0.6121946789552213,
+      "eval_recall": 0.7268689387271124,
+      "eval_runtime": 18.8901,
+      "eval_samples_per_second": 72.419,
+      "eval_steps_per_second": 2.276,
       "step": 126
     },
     {
       "epoch": 3.0,
-      "eval_f1": 0.6649764694308206,
-      "eval_loss": 0.3234550952911377,
-      "eval_precision": 0.6586549765457441,
-      "eval_recall": 0.7026409236615889,
-      "eval_runtime": 10.2585,
-      "eval_samples_per_second": 133.353,
-      "eval_steps_per_second": 4.192,
+      "eval_f1": 0.6474491673607571,
+      "eval_loss": 0.28480294346809387,
+      "eval_precision": 0.613922648135192,
+      "eval_recall": 0.7047525364262208,
+      "eval_runtime": 18.8954,
+      "eval_samples_per_second": 72.398,
+      "eval_steps_per_second": 2.276,
       "step": 189
     },
     {
       "epoch": 4.0,
-      "eval_f1": 0.6602750315588134,
-      "eval_loss": 0.4237957298755646,
-      "eval_precision": 0.6305051786684939,
-      "eval_recall": 0.7352174951136592,
-      "eval_runtime": 10.3722,
-      "eval_samples_per_second": 131.891,
-      "eval_steps_per_second": 4.146,
+      "eval_f1": 0.6666160547465906,
+      "eval_loss": 0.3676050901412964,
+      "eval_precision": 0.643380757727672,
+      "eval_recall": 0.7153767840809319,
+      "eval_runtime": 18.886,
+      "eval_samples_per_second": 72.435,
+      "eval_steps_per_second": 2.277,
       "step": 252
     }
   ],
@@ -80,7 +80,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2077925737316352.0,
+  "total_flos": 2075835268767744.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9222e4d87976229d54fa57cf91356fc54b06f031d0f6513393ba467c4a032c3
-size 5777
+oid sha256:749c49a6f77fe67d4230dd105f729ac9490a2f4a041ed0a6f305717d9657892a
+size 5713