Model save

README.md

@@ -34,8 +34,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 64
-- eval_batch_size: 64
+- train_batch_size: 128
+- eval_batch_size: 128
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine_with_restarts

config.json

@@ -57,6 +57,7 @@
   ],
   "patch_size": 4,
   "path_norm": true,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "stage_names": [
     "stem",

logs/events.out.tfevents.1740248341.943ca99e1f33.812.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d7d9dcc74857039590802ccd1cc97ab45361b5a1501c87e33ba3dc58a609a6
-size 88
+oid sha256:11652482b8e3545cbbefc4f248adec4cc1105712f771b6ad18cdb574543a17b2
+size 6058

logs/events.out.tfevents.1740248566.943ca99e1f33.812.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca696c031bd73372d3eefcbada800d8fa71291ae7cf91cc849cfd6fa7662017c
+size 88

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26503754261fd4ee769194b7ed0db2f4e16009156e8f0275e203d29d61d0711e
+oid sha256:a9883de3c1b05220773ab950916f65bf4fb80ee01e5cb8f0914e0df02e419822
 size 347523416

trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0,
+  "eval_steps": 500,
+  "global_step": 0,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1432a45a87f78d16321d550a5eb80d944c53afb091422facf1b12e82e25c427
+oid sha256:2aa27d7b85cc841b9c04b978097c8a2456afee17bd48de31f3d9352e70815b48
 size 5496