End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+integrated_gradients_grid.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -4,8 +4,6 @@ license: apache-2.0
 base_model: google/vit-base-patch16-224
 tags:
 - generated_from_trainer
-datasets:
-- imagefolder
 metrics:
 - precision
 - recall
@@ -13,29 +11,7 @@ metrics:
 - accuracy
 model-index:
 - name: vit-base-patch16-224-finetuned-barkley
-  results:
-  - task:
-      name: Image Classification
-      type: image-classification
-    dataset:
-      name: imagefolder
-      type: imagefolder
-      config: default
-      split: train
-      args: default
-    metrics:
-    - name: Precision
-      type: precision
-      value: 0.9936145510835913
-    - name: Recall
-      type: recall
-      value: 0.993421052631579
-    - name: F1
-      type: f1
-      value: 0.993419541966282
-    - name: Accuracy
-      type: accuracy
-      value: 0.9939393939393939
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,15 +19,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-patch16-224-finetuned-barkley
 
-This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0340
-- Precision: 0.9936
-- Recall: 0.9934
-- F1: 0.9934
-- Accuracy: 0.9939
-- Top1 Accuracy: 0.9934
-- Error Rate: 0.0061
+- Loss: 0.0036
+- Precision: 1.0
+- Recall: 1.0
+- F1: 1.0
+- Accuracy: 1.0
+- Top1 Accuracy: 1.0
+- Error Rate: 0.0
 
 ## Model description
 
@@ -70,10 +46,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 32
-- eval_batch_size: 32
+- learning_rate: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -84,25 +62,28 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy | Top1 Accuracy | Error Rate |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------------:|:----------:|
-| 1.7463        | 1.0   | 38   | 1.7013          | 0.2143    | 0.2171 | 0.1930 | 0.2186   | 0.2171        | 0.7814     |
-| 1.5581        | 2.0   | 76   | 1.4481          | 0.3512    | 0.3487 | 0.3287 | 0.3682   | 0.3487        | 0.6318     |
-| 1.2665        | 3.0   | 114  | 1.0585          | 0.7397    | 0.7237 | 0.7274 | 0.7294   | 0.7237        | 0.2706     |
-| 0.8572        | 4.0   | 152  | 0.5839          | 0.9467    | 0.9408 | 0.9417 | 0.9449   | 0.9408        | 0.0551     |
-| 0.4337        | 5.0   | 190  | 0.2339          | 0.9820    | 0.9803 | 0.9802 | 0.9818   | 0.9803        | 0.0182     |
-| 0.1569        | 6.0   | 228  | 0.0949          | 0.9739    | 0.9737 | 0.9735 | 0.9756   | 0.9737        | 0.0244     |
-| 0.0577        | 7.0   | 266  | 0.0434          | 0.9872    | 0.9868 | 0.9867 | 0.9879   | 0.9868        | 0.0121     |
-| 0.0172        | 8.0   | 304  | 0.0380          | 0.9870    | 0.9868 | 0.9868 | 0.9877   | 0.9868        | 0.0123     |
-| 0.0208        | 9.0   | 342  | 0.0530          | 0.9876    | 0.9868 | 0.9868 | 0.9879   | 0.9868        | 0.0121     |
-| 0.0071        | 10.0  | 380  | 0.0987          | 0.9716    | 0.9671 | 0.9669 | 0.9697   | 0.9671        | 0.0303     |
-| 0.0062        | 11.0  | 418  | 0.0340          | 0.9936    | 0.9934 | 0.9934 | 0.9939   | 0.9934        | 0.0061     |
-| 0.0165        | 12.0  | 456  | 0.0649          | 0.9809    | 0.9803 | 0.9799 | 0.9818   | 0.9803        | 0.0182     |
-| 0.0057        | 13.0  | 494  | 0.0375          | 0.9936    | 0.9934 | 0.9934 | 0.9939   | 0.9934        | 0.0061     |
-| 0.0038        | 14.0  | 532  | 0.0377          | 0.9936    | 0.9934 | 0.9934 | 0.9939   | 0.9934        | 0.0061     |
+| 1.6093        | 1.0   | 38   | 1.4340          | 0.4769    | 0.4342 | 0.4066 | 0.4149   | 0.4342        | 0.5851     |
+| 1.2908        | 2.0   | 76   | 1.1747          | 0.6587    | 0.6118 | 0.6160 | 0.6161   | 0.6118        | 0.3839     |
+| 1.0409        | 3.0   | 114  | 0.9174          | 0.7382    | 0.7303 | 0.7293 | 0.7425   | 0.7303        | 0.2575     |
+| 0.781         | 4.0   | 152  | 0.6528          | 0.8632    | 0.8618 | 0.8622 | 0.8650   | 0.8618        | 0.1350     |
+| 0.5429        | 5.0   | 190  | 0.4112          | 0.9417    | 0.9408 | 0.9405 | 0.9443   | 0.9408        | 0.0557     |
+| 0.328         | 6.0   | 228  | 0.2229          | 0.9809    | 0.9803 | 0.9802 | 0.9811   | 0.9803        | 0.0189     |
+| 0.1837        | 7.0   | 266  | 0.1181          | 0.9871    | 0.9868 | 0.9868 | 0.9878   | 0.9868        | 0.0122     |
+| 0.1131        | 8.0   | 304  | 0.0680          | 0.9937    | 0.9934 | 0.9934 | 0.9944   | 0.9934        | 0.0056     |
+| 0.0526        | 9.0   | 342  | 0.0387          | 0.9937    | 0.9934 | 0.9934 | 0.9944   | 0.9934        | 0.0056     |
+| 0.0283        | 10.0  | 380  | 0.0328          | 0.9873    | 0.9868 | 0.9869 | 0.9878   | 0.9868        | 0.0122     |
+| 0.019         | 11.0  | 418  | 0.0224          | 0.9873    | 0.9868 | 0.9868 | 0.9889   | 0.9868        | 0.0111     |
+| 0.0148        | 12.0  | 456  | 0.0201          | 0.9873    | 0.9868 | 0.9868 | 0.9889   | 0.9868        | 0.0111     |
+| 0.0095        | 13.0  | 494  | 0.0396          | 0.9871    | 0.9868 | 0.9868 | 0.9878   | 0.9868        | 0.0122     |
+| 0.007         | 14.0  | 532  | 0.0048          | 1.0       | 1.0    | 1.0    | 1.0      | 1.0           | 0.0        |
+| 0.011         | 15.0  | 570  | 0.0036          | 1.0       | 1.0    | 1.0    | 1.0      | 1.0           | 0.0        |
+| 0.0071        | 16.0  | 608  | 0.0092          | 0.9936    | 0.9934 | 0.9934 | 0.9941   | 0.9934        | 0.0059     |
+| 0.0103        | 17.0  | 646  | 0.0148          | 0.9936    | 0.9934 | 0.9934 | 0.9944   | 0.9934        | 0.0056     |
 
 
 ### Framework versions
 
-- Transformers 4.45.2
+- Transformers 4.44.2
 - Pytorch 2.3.1+cu121
 - Datasets 3.0.1
-- Tokenizers 0.20.1
+- Tokenizers 0.19.1

all_results.json

@@ -1,19 +1,18 @@
 {
-    "epoch": 14.0,
-    "eval_accuracy": 0.9939393939393939,
-    "eval_error_rate": 0.0060606060606061,
-    "eval_f1": 0.993419541966282,
-    "eval_loss": 0.03395003080368042,
-    "eval_model_preparation_time": 0.008,
-    "eval_precision": 0.9936145510835913,
-    "eval_recall": 0.993421052631579,
-    "eval_runtime": 62.4572,
-    "eval_samples_per_second": 2.434,
-    "eval_steps_per_second": 0.08,
-    "eval_top1_accuracy": 0.993421052631579,
-    "total_flos": 1.319259102551212e+18,
-    "train_loss": 0.4395476876008779,
-    "train_runtime": 10817.4486,
-    "train_samples_per_second": 3.372,
-    "train_steps_per_second": 0.105
+    "epoch": 17.0,
+    "eval_accuracy": 1.0,
+    "eval_error_rate": 0.0,
+    "eval_f1": 1.0,
+    "eval_loss": 0.003647729055956006,
+    "eval_precision": 1.0,
+    "eval_recall": 1.0,
+    "eval_runtime": 63.8492,
+    "eval_samples_per_second": 2.381,
+    "eval_steps_per_second": 0.298,
+    "eval_top1_accuracy": 1.0,
+    "total_flos": 1.601957481669329e+18,
+    "train_loss": 0.3558414801263219,
+    "train_runtime": 14288.2591,
+    "train_samples_per_second": 2.553,
+    "train_steps_per_second": 0.08
 }

config.json

@@ -34,5 +34,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.45.2"
+  "transformers_version": "4.44.2"
 }

eval_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 14.0,
-    "eval_accuracy": 0.9939393939393939,
-    "eval_error_rate": 0.0060606060606061,
-    "eval_f1": 0.993419541966282,
-    "eval_loss": 0.03395003080368042,
-    "eval_precision": 0.9936145510835913,
-    "eval_recall": 0.993421052631579,
-    "eval_runtime": 62.4572,
-    "eval_samples_per_second": 2.434,
-    "eval_steps_per_second": 0.08,
-    "eval_top1_accuracy": 0.993421052631579
+    "epoch": 17.0,
+    "eval_accuracy": 1.0,
+    "eval_error_rate": 0.0,
+    "eval_f1": 1.0,
+    "eval_loss": 0.003647729055956006,
+    "eval_precision": 1.0,
+    "eval_recall": 1.0,
+    "eval_runtime": 63.8492,
+    "eval_samples_per_second": 2.381,
+    "eval_steps_per_second": 0.298,
+    "eval_top1_accuracy": 1.0
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8b7d00aba59d6176b6560b26fd8fafe32180a89f3d001465ff90a2d2a48ba0
+oid sha256:095e519b8fe95230c057af31cba64f9087271dc9aea96438255c92d1b61d4810
 size 343233204

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 14.0,
-    "total_flos": 1.319259102551212e+18,
-    "train_loss": 0.4395476876008779,
-    "train_runtime": 10817.4486,
-    "train_samples_per_second": 3.372,
-    "train_steps_per_second": 0.105
+    "epoch": 17.0,
+    "total_flos": 1.601957481669329e+18,
+    "train_loss": 0.3558414801263219,
+    "train_runtime": 14288.2591,
+    "train_samples_per_second": 2.553,
+    "train_steps_per_second": 0.08
 }

trainer_state.json

@@ -1,374 +1,449 @@
 {
-  "best_metric": 0.03395003080368042,
-  "best_model_checkpoint": "vit-base-patch16-224-finetuned-barkley\\checkpoint-418",
-  "epoch": 14.0,
+  "best_metric": 0.003647729055956006,
+  "best_model_checkpoint": "vit-base-patch16-224-finetuned-barkley\\checkpoint-570",
+  "epoch": 17.0,
   "eval_steps": 500,
-  "global_step": 532,
+  "global_step": 646,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "train_accuracy": 0.21134868421052633
+      "train_accuracy": 0.26398026315789475
     },
     {
       "epoch": 1.0,
-      "grad_norm": 7.52012300491333,
-      "learning_rate": 1.1659108139509125e-06,
-      "loss": 1.7463,
+      "grad_norm": 6.455413341522217,
+      "learning_rate": 2.0914608267470257e-06,
+      "loss": 1.6093,
       "step": 38
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.21856060606060607,
-      "eval_error_rate": 0.781439393939394,
-      "eval_f1": 0.19295495348680888,
-      "eval_loss": 1.701319694519043,
-      "eval_precision": 0.2142622862160236,
-      "eval_recall": 0.21710526315789475,
-      "eval_runtime": 46.6936,
-      "eval_samples_per_second": 3.255,
-      "eval_steps_per_second": 0.107,
-      "eval_top1_accuracy": 0.21710526315789475,
+      "eval_accuracy": 0.4148818501759678,
+      "eval_error_rate": 0.5851181498240322,
+      "eval_f1": 0.406583244487493,
+      "eval_loss": 1.4340049028396606,
+      "eval_precision": 0.47685010008788203,
+      "eval_recall": 0.4342105263157895,
+      "eval_runtime": 80.0768,
+      "eval_samples_per_second": 1.898,
+      "eval_steps_per_second": 0.237,
+      "eval_top1_accuracy": 0.4342105263157895,
       "step": 38
     },
     {
       "epoch": 2.0,
-      "train_accuracy": 0.30409356725146197
+      "train_accuracy": 0.5095029239766082
     },
     {
       "epoch": 2.0,
-      "grad_norm": 6.449554920196533,
-      "learning_rate": 2.23574935501902e-06,
-      "loss": 1.5581,
+      "grad_norm": 6.083907127380371,
+      "learning_rate": 2.365146216752351e-06,
+      "loss": 1.2908,
       "step": 76
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.36818181818181817,
-      "eval_error_rate": 0.6318181818181818,
-      "eval_f1": 0.328691576484973,
-      "eval_loss": 1.4481072425842285,
-      "eval_precision": 0.3511731503217571,
-      "eval_recall": 0.34868421052631576,
-      "eval_runtime": 63.7667,
-      "eval_samples_per_second": 2.384,
-      "eval_steps_per_second": 0.078,
-      "eval_top1_accuracy": 0.34868421052631576,
+      "eval_accuracy": 0.6161337355455003,
+      "eval_error_rate": 0.3838662644544997,
+      "eval_f1": 0.615989993007031,
+      "eval_loss": 1.1747227907180786,
+      "eval_precision": 0.6587479462326463,
+      "eval_recall": 0.6118421052631579,
+      "eval_runtime": 62.2988,
+      "eval_samples_per_second": 2.44,
+      "eval_steps_per_second": 0.305,
+      "eval_top1_accuracy": 0.6118421052631579,
       "step": 76
     },
     {
       "epoch": 3.0,
-      "train_accuracy": 0.5197368421052632
+      "train_accuracy": 0.7017543859649122
     },
     {
       "epoch": 3.0,
-      "grad_norm": 5.767495155334473,
-      "learning_rate": 3.927960312504679e-06,
-      "loss": 1.2665,
+      "grad_norm": 5.073782444000244,
+      "learning_rate": 2.8189702123460904e-06,
+      "loss": 1.0409,
       "step": 114
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7293560606060607,
-      "eval_error_rate": 0.27064393939393927,
-      "eval_f1": 0.7273905235235443,
-      "eval_loss": 1.0585086345672607,
-      "eval_precision": 0.7397410035407469,
-      "eval_recall": 0.7236842105263158,
-      "eval_runtime": 47.8118,
-      "eval_samples_per_second": 3.179,
-      "eval_steps_per_second": 0.105,
-      "eval_top1_accuracy": 0.7236842105263158,
+      "eval_accuracy": 0.7424685771744596,
+      "eval_error_rate": 0.2575314228255404,
+      "eval_f1": 0.7293001164996891,
+      "eval_loss": 0.9174113869667053,
+      "eval_precision": 0.7381704260651629,
+      "eval_recall": 0.7302631578947368,
+      "eval_runtime": 63.0328,
+      "eval_samples_per_second": 2.411,
+      "eval_steps_per_second": 0.301,
+      "eval_top1_accuracy": 0.7302631578947368,
       "step": 114
     },
     {
       "epoch": 4.0,
-      "train_accuracy": 0.8062865497076024
+      "train_accuracy": 0.8172514619883041
     },
     {
       "epoch": 4.0,
-      "grad_norm": 12.979792594909668,
-      "learning_rate": 6.113544042901594e-06,
-      "loss": 0.8572,
+      "grad_norm": 4.503601551055908,
+      "learning_rate": 3.449473887042014e-06,
+      "loss": 0.781,
       "step": 152
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9448863636363637,
-      "eval_error_rate": 0.05511363636363631,
-      "eval_f1": 0.9416857901577765,
-      "eval_loss": 0.58392333984375,
-      "eval_precision": 0.9467451523545707,
-      "eval_recall": 0.9407894736842105,
-      "eval_runtime": 46.5589,
-      "eval_samples_per_second": 3.265,
-      "eval_steps_per_second": 0.107,
-      "eval_top1_accuracy": 0.9407894736842105,
+      "eval_accuracy": 0.8650025138260432,
+      "eval_error_rate": 0.1349974861739568,
+      "eval_f1": 0.862176726467179,
+      "eval_loss": 0.6527765989303589,
+      "eval_precision": 0.8632378661708033,
+      "eval_recall": 0.8618421052631579,
+      "eval_runtime": 64.1793,
+      "eval_samples_per_second": 2.368,
+      "eval_steps_per_second": 0.296,
+      "eval_top1_accuracy": 0.8618421052631579,
       "step": 152
     },
     {
       "epoch": 5.0,
-      "train_accuracy": 0.9466374269005848
+      "train_accuracy": 0.9027777777777778
     },
     {
       "epoch": 5.0,
-      "grad_norm": 4.086988925933838,
-      "learning_rate": 8.62589039584572e-06,
-      "loss": 0.4337,
+      "grad_norm": 3.8262150287628174,
+      "learning_rate": 4.251851708560589e-06,
+      "loss": 0.5429,
       "step": 190
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9818181818181818,
-      "eval_error_rate": 0.018181818181818188,
-      "eval_f1": 0.9802351026820783,
-      "eval_loss": 0.23391342163085938,
-      "eval_precision": 0.9819548872180451,
-      "eval_recall": 0.9802631578947368,
-      "eval_runtime": 48.9157,
-      "eval_samples_per_second": 3.107,
-      "eval_steps_per_second": 0.102,
-      "eval_top1_accuracy": 0.9802631578947368,
+      "eval_accuracy": 0.9442885872297637,
+      "eval_error_rate": 0.05571141277023628,
+      "eval_f1": 0.9404774954713644,
+      "eval_loss": 0.41116613149642944,
+      "eval_precision": 0.9416901233513075,
+      "eval_recall": 0.9407894736842105,
+      "eval_runtime": 64.0989,
+      "eval_samples_per_second": 2.371,
+      "eval_steps_per_second": 0.296,
+      "eval_top1_accuracy": 0.9407894736842105,
       "step": 190
     },
     {
       "epoch": 6.0,
-      "train_accuracy": 0.9846491228070176
+      "train_accuracy": 0.9568713450292398
     },
     {
       "epoch": 6.0,
-      "grad_norm": 1.9588254690170288,
-      "learning_rate": 1.1273479642392808e-05,
-      "loss": 0.1569,
+      "grad_norm": 2.5020029544830322,
+      "learning_rate": 5.219988165325166e-06,
+      "loss": 0.328,
       "step": 228
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9755681818181818,
-      "eval_error_rate": 0.024431818181818166,
-      "eval_f1": 0.9734739448002901,
-      "eval_loss": 0.09490276873111725,
-      "eval_precision": 0.9738519848439453,
-      "eval_recall": 0.9736842105263158,
-      "eval_runtime": 62.9862,
-      "eval_samples_per_second": 2.413,
-      "eval_steps_per_second": 0.079,
-      "eval_top1_accuracy": 0.9736842105263158,
+      "eval_accuracy": 0.981111111111111,
+      "eval_error_rate": 0.018888888888888955,
+      "eval_f1": 0.980233547031901,
+      "eval_loss": 0.22286705672740936,
+      "eval_precision": 0.9808624413887572,
+      "eval_recall": 0.9802631578947368,
+      "eval_runtime": 65.9742,
+      "eval_samples_per_second": 2.304,
+      "eval_steps_per_second": 0.288,
+      "eval_top1_accuracy": 0.9802631578947368,
       "step": 228
     },
     {
       "epoch": 7.0,
-      "train_accuracy": 0.9890350877192983
+      "train_accuracy": 0.9707602339181286
     },
     {
       "epoch": 7.0,
-      "grad_norm": 4.820840835571289,
-      "learning_rate": 1.3854482295832083e-05,
-      "loss": 0.0577,
+      "grad_norm": 3.700869560241699,
+      "learning_rate": 6.346504377274108e-06,
+      "loss": 0.1837,
       "step": 266
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.9878787878787879,
-      "eval_error_rate": 0.012121212121212088,
-      "eval_f1": 0.9867362170674966,
-      "eval_loss": 0.04335561394691467,
-      "eval_precision": 0.9872349657566376,
+      "eval_accuracy": 0.9877777777777779,
+      "eval_error_rate": 0.012222222222222134,
+      "eval_f1": 0.9868484170131115,
+      "eval_loss": 0.11809363961219788,
+      "eval_precision": 0.9870857699805068,
       "eval_recall": 0.9868421052631579,
-      "eval_runtime": 60.8368,
-      "eval_samples_per_second": 2.498,
-      "eval_steps_per_second": 0.082,
+      "eval_runtime": 64.4539,
+      "eval_samples_per_second": 2.358,
+      "eval_steps_per_second": 0.295,
       "eval_top1_accuracy": 0.9868421052631579,
       "step": 266
     },
     {
       "epoch": 8.0,
-      "train_accuracy": 0.9978070175438597
+      "train_accuracy": 0.9766081871345029
     },
     {
       "epoch": 8.0,
-      "grad_norm": 0.17172254621982574,
-      "learning_rate": 1.6172144859969913e-05,
-      "loss": 0.0172,
+      "grad_norm": 1.4798824787139893,
+      "learning_rate": 7.622814335733349e-06,
+      "loss": 0.1131,
       "step": 304
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.9876893939393939,
-      "eval_error_rate": 0.012310606060606077,
-      "eval_f1": 0.9868389880173071,
-      "eval_loss": 0.038041990250349045,
-      "eval_precision": 0.9870356037151703,
-      "eval_recall": 0.9868421052631579,
-      "eval_runtime": 52.1078,
-      "eval_samples_per_second": 2.917,
-      "eval_steps_per_second": 0.096,
-      "eval_top1_accuracy": 0.9868421052631579,
+      "eval_accuracy": 0.9944444444444445,
+      "eval_error_rate": 0.005555555555555536,
+      "eval_f1": 0.99343678755752,
+      "eval_loss": 0.06803914159536362,
+      "eval_precision": 0.9936647173489279,
+      "eval_recall": 0.993421052631579,
+      "eval_runtime": 66.8397,
+      "eval_samples_per_second": 2.274,
+      "eval_steps_per_second": 0.284,
+      "eval_top1_accuracy": 0.993421052631579,
       "step": 304
     },
     {
       "epoch": 9.0,
-      "train_accuracy": 0.993421052631579
+      "train_accuracy": 0.9912280701754386
     },
     {
       "epoch": 9.0,
-      "grad_norm": 0.35163307189941406,
-      "learning_rate": 1.8049788627450628e-05,
-      "loss": 0.0208,
+      "grad_norm": 0.24450232088565826,
+      "learning_rate": 9.039190343704055e-06,
+      "loss": 0.0526,
       "step": 342
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.9878787878787879,
-      "eval_error_rate": 0.012121212121212088,
-      "eval_f1": 0.986835875199362,
-      "eval_loss": 0.05302947387099266,
-      "eval_precision": 0.9876160990712075,
-      "eval_recall": 0.9868421052631579,
-      "eval_runtime": 62.895,
-      "eval_samples_per_second": 2.417,
-      "eval_steps_per_second": 0.079,
-      "eval_top1_accuracy": 0.9868421052631579,
+      "eval_accuracy": 0.9944444444444445,
+      "eval_error_rate": 0.005555555555555536,
+      "eval_f1": 0.99343678755752,
+      "eval_loss": 0.0387217253446579,
+      "eval_precision": 0.9936647173489279,
+      "eval_recall": 0.993421052631579,
+      "eval_runtime": 62.2983,
+      "eval_samples_per_second": 2.44,
+      "eval_steps_per_second": 0.305,
+      "eval_top1_accuracy": 0.993421052631579,
       "step": 342
     },
     {
       "epoch": 10.0,
-      "train_accuracy": 0.9985380116959064
+      "train_accuracy": 0.9948830409356725
     },
     {
       "epoch": 10.0,
-      "grad_norm": 0.4090166985988617,
-      "learning_rate": 1.9344278148426573e-05,
-      "loss": 0.0071,
+      "grad_norm": 0.18834975361824036,
+      "learning_rate": 1.0584837157796744e-05,
+      "loss": 0.0283,
       "step": 380
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.9696969696969697,
-      "eval_error_rate": 0.030303030303030276,
-      "eval_f1": 0.9669489564967301,
-      "eval_loss": 0.09868758916854858,
-      "eval_precision": 0.9715504978662873,
-      "eval_recall": 0.9671052631578947,
-      "eval_runtime": 62.4085,
-      "eval_samples_per_second": 2.436,
-      "eval_steps_per_second": 0.08,
-      "eval_top1_accuracy": 0.9671052631578947,
+      "eval_accuracy": 0.9877777777777779,
+      "eval_error_rate": 0.012222222222222134,
+      "eval_f1": 0.9868641519390525,
+      "eval_loss": 0.032834384590387344,
+      "eval_precision": 0.9873294346978557,
+      "eval_recall": 0.9868421052631579,
+      "eval_runtime": 65.4882,
+      "eval_samples_per_second": 2.321,
+      "eval_steps_per_second": 0.29,
+      "eval_top1_accuracy": 0.9868421052631579,
       "step": 380
     },
     {
       "epoch": 11.0,
-      "train_accuracy": 0.9948830409356725
+      "train_accuracy": 0.9956140350877193
     },
     {
       "epoch": 11.0,
-      "grad_norm": 0.16305039823055267,
-      "learning_rate": 1.995693264909124e-05,
-      "loss": 0.0062,
+      "grad_norm": 0.2787030041217804,
+      "learning_rate": 1.2247974266721769e-05,
+      "loss": 0.019,
       "step": 418
     },
     {
       "epoch": 11.0,
-      "eval_accuracy": 0.9939393939393939,
-      "eval_error_rate": 0.0060606060606061,
-      "eval_f1": 0.993419541966282,
-      "eval_loss": 0.03395003080368042,
-      "eval_precision": 0.9936145510835913,
-      "eval_recall": 0.993421052631579,
-      "eval_runtime": 47.4116,
-      "eval_samples_per_second": 3.206,
-      "eval_steps_per_second": 0.105,
-      "eval_top1_accuracy": 0.993421052631579,
+      "eval_accuracy": 0.9888888888888889,
+      "eval_error_rate": 0.011111111111111072,
+      "eval_f1": 0.9867701266776593,
+      "eval_loss": 0.0223978441208601,
+      "eval_precision": 0.9872979940891655,
+      "eval_recall": 0.9868421052631579,
+      "eval_runtime": 66.7371,
+      "eval_samples_per_second": 2.278,
+      "eval_steps_per_second": 0.285,
+      "eval_top1_accuracy": 0.9868421052631579,
       "step": 418
     },
     {
       "epoch": 12.0,
-      "train_accuracy": 0.993421052631579
+      "train_accuracy": 0.9963450292397661
     },
     {
       "epoch": 12.0,
-      "grad_norm": 3.5277631282806396,
-      "learning_rate": 1.9969660582486496e-05,
-      "loss": 0.0165,
+      "grad_norm": 1.9764137268066406,
+      "learning_rate": 1.401592567923113e-05,
+      "loss": 0.0148,
       "step": 456
     },
     {
       "epoch": 12.0,
-      "eval_accuracy": 0.9818181818181818,
-      "eval_error_rate": 0.018181818181818188,
-      "eval_f1": 0.979943544279758,
-      "eval_loss": 0.06494485586881638,
-      "eval_precision": 0.9808553804296839,
-      "eval_recall": 0.9802631578947368,
-      "eval_runtime": 56.3797,
-      "eval_samples_per_second": 2.696,
-      "eval_steps_per_second": 0.089,
-      "eval_top1_accuracy": 0.9802631578947368,
+      "eval_accuracy": 0.9888888888888889,
+      "eval_error_rate": 0.011111111111111072,
+      "eval_f1": 0.9867701266776593,
+      "eval_loss": 0.02013457380235195,
+      "eval_precision": 0.9872979940891655,
+      "eval_recall": 0.9868421052631579,
+      "eval_runtime": 62.9372,
+      "eval_samples_per_second": 2.415,
+      "eval_steps_per_second": 0.302,
+      "eval_top1_accuracy": 0.9868421052631579,
       "step": 456
     },
     {
       "epoch": 13.0,
-      "train_accuracy": 0.9956140350877193
+      "train_accuracy": 0.9963450292397661
     },
     {
       "epoch": 13.0,
-      "grad_norm": 0.053868379443883896,
-      "learning_rate": 1.980785357262109e-05,
-      "loss": 0.0057,
+      "grad_norm": 0.050672873854637146,
+      "learning_rate": 1.5875216537171772e-05,
+      "loss": 0.0095,
       "step": 494
     },
     {
       "epoch": 13.0,
-      "eval_accuracy": 0.9939393939393939,
-      "eval_error_rate": 0.0060606060606061,
-      "eval_f1": 0.993419541966282,
-      "eval_loss": 0.03750297427177429,
-      "eval_precision": 0.9936145510835913,
-      "eval_recall": 0.993421052631579,
-      "eval_runtime": 61.2882,
-      "eval_samples_per_second": 2.48,
-      "eval_steps_per_second": 0.082,
-      "eval_top1_accuracy": 0.993421052631579,
+      "eval_accuracy": 0.9877777777777779,
+      "eval_error_rate": 0.012222222222222134,
+      "eval_f1": 0.9868484170131115,
+      "eval_loss": 0.03958281874656677,
+      "eval_precision": 0.9870857699805068,
+      "eval_recall": 0.9868421052631579,
+      "eval_runtime": 63.5973,
+      "eval_samples_per_second": 2.39,
+      "eval_steps_per_second": 0.299,
+      "eval_top1_accuracy": 0.9868421052631579,
       "step": 494
     },
     {
       "epoch": 14.0,
-      "train_accuracy": 0.9985380116959064
+      "train_accuracy": 0.9978070175438597
     },
     {
       "epoch": 14.0,
-      "grad_norm": 0.02169680781662464,
-      "learning_rate": 1.950863907947058e-05,
-      "loss": 0.0038,
+      "grad_norm": 0.06194866821169853,
+      "learning_rate": 1.7811675817291163e-05,
+      "loss": 0.007,
       "step": 532
     },
     {
       "epoch": 14.0,
-      "eval_accuracy": 0.9939393939393939,
-      "eval_error_rate": 0.0060606060606061,
-      "eval_f1": 0.993419541966282,
-      "eval_loss": 0.037650275975465775,
-      "eval_precision": 0.9936145510835913,
+      "eval_accuracy": 1.0,
+      "eval_error_rate": 0.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.0047844694927334785,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 63.8972,
+      "eval_samples_per_second": 2.379,
+      "eval_steps_per_second": 0.297,
+      "eval_top1_accuracy": 1.0,
+      "step": 532
+    },
+    {
+      "epoch": 15.0,
+      "train_accuracy": 0.9956140350877193
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.3071841597557068,
+      "learning_rate": 1.9810544339029155e-05,
+      "loss": 0.011,
+      "step": 570
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 1.0,
+      "eval_error_rate": 0.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.003647729055956006,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 65.5965,
+      "eval_samples_per_second": 2.317,
+      "eval_steps_per_second": 0.29,
+      "eval_top1_accuracy": 1.0,
+      "step": 570
+    },
+    {
+      "epoch": 16.0,
+      "train_accuracy": 0.9978070175438597
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.05617503821849823,
+      "learning_rate": 2.1856587255089357e-05,
+      "loss": 0.0071,
+      "step": 608
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.9941176470588236,
+      "eval_error_rate": 0.00588235294117645,
+      "eval_f1": 0.9934170172927719,
+      "eval_loss": 0.009170782752335072,
+      "eval_precision": 0.9935988620199147,
       "eval_recall": 0.993421052631579,
-      "eval_runtime": 64.509,
-      "eval_samples_per_second": 2.356,
-      "eval_steps_per_second": 0.078,
+      "eval_runtime": 66.4048,
+      "eval_samples_per_second": 2.289,
+      "eval_steps_per_second": 0.286,
       "eval_top1_accuracy": 0.993421052631579,
-      "step": 532
+      "step": 608
     },
     {
-      "epoch": 14.0,
-      "step": 532,
-      "total_flos": 1.319259102551212e+18,
-      "train_loss": 0.4395476876008779,
-      "train_runtime": 10817.4486,
-      "train_samples_per_second": 3.372,
-      "train_steps_per_second": 0.105
+      "epoch": 17.0,
+      "train_accuracy": 0.9963450292397661
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.02715430036187172,
+      "learning_rate": 2.393421016741653e-05,
+      "loss": 0.0103,
+      "step": 646
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.9944444444444445,
+      "eval_error_rate": 0.005555555555555536,
+      "eval_f1": 0.9934286478144102,
+      "eval_loss": 0.014811488799750805,
+      "eval_precision": 0.9936332767402377,
+      "eval_recall": 0.993421052631579,
+      "eval_runtime": 64.9042,
+      "eval_samples_per_second": 2.342,
+      "eval_steps_per_second": 0.293,
+      "eval_top1_accuracy": 0.993421052631579,
+      "step": 646
+    },
+    {
+      "epoch": 17.0,
+      "step": 646,
+      "total_flos": 1.601957481669329e+18,
+      "train_loss": 0.3558414801263219,
+      "train_runtime": 14288.2591,
+      "train_samples_per_second": 2.553,
+      "train_steps_per_second": 0.08
     }
   ],
-  "logging_steps": 500,
+  "logging_steps": 10,
   "max_steps": 1140,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
@@ -376,11 +451,11 @@
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
       "args": {
-        "early_stopping_patience": 3,
+        "early_stopping_patience": 2,
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 3
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -394,8 +469,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.319259102551212e+18,
-  "train_batch_size": 32,
+  "total_flos": 1.601957481669329e+18,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eb43bcfd2e0e3cbc7cac889051ecb5a72ca97601937778cbe86b8e6db9d07d1
+oid sha256:cf88fd2cbab55edfe4073469846fa48192ab595fedef138b7aa73e05d0927aad
 size 5176