End of training

.gitattributes

@@ -33,3 +33,7 @@ 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
+classification_report.png filter=lfs diff=lfs merge=lfs -text
+evaluation/clf_bar.png filter=lfs diff=lfs merge=lfs -text
+evaluation/confusion_matrix.png filter=lfs diff=lfs merge=lfs -text
+train_and_eval.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: microsoft/resnet-50
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: 2025-02-05-21-58-41-resnet-50
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# 2025-02-05-21-58-41-resnet-50
+
+This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0762
+- Precision: 0.9810
+- Recall: 0.9805
+- F1: 0.9804
+- Accuracy: 0.9766
+- Top1 Accuracy: 0.9805
+- Error Rate: 0.0234
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 3407
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy | Top1 Accuracy | Error Rate |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------------:|:----------:|
+| 2.4636        | 1.0   | 103  | 2.1548          | 0.6867    | 0.6293 | 0.5929 | 0.5824   | 0.6293        | 0.4176     |
+| 1.3967        | 2.0   | 206  | 0.5586          | 0.8893    | 0.8780 | 0.8770 | 0.8743   | 0.8780        | 0.1257     |
+| 0.4328        | 3.0   | 309  | 0.2100          | 0.9565    | 0.9512 | 0.9518 | 0.9524   | 0.9512        | 0.0476     |
+| 0.2544        | 4.0   | 412  | 0.1414          | 0.9628    | 0.9610 | 0.9613 | 0.9588   | 0.9610        | 0.0412     |
+| 0.171         | 5.0   | 515  | 0.1127          | 0.9690    | 0.9683 | 0.9683 | 0.9638   | 0.9683        | 0.0362     |
+| 0.1556        | 6.0   | 618  | 0.0976          | 0.9715    | 0.9707 | 0.9706 | 0.9681   | 0.9707        | 0.0319     |
+| 0.118         | 7.0   | 721  | 0.0762          | 0.9810    | 0.9805 | 0.9804 | 0.9766   | 0.9805        | 0.0234     |
+| 0.1142        | 8.0   | 824  | 0.0853          | 0.9809    | 0.9805 | 0.9804 | 0.9813   | 0.9805        | 0.0187     |
+| 0.0978        | 9.0   | 927  | 0.0798          | 0.9808    | 0.9805 | 0.9803 | 0.9788   | 0.9805        | 0.0212     |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,28 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.9765634013174265,
+    "eval_error_rate": 0.02343659868257353,
+    "eval_f1": 0.9804014205399844,
+    "eval_loss": 0.07615971565246582,
+    "eval_precision": 0.9810152386446259,
+    "eval_recall": 0.9804878048780488,
+    "eval_runtime": 8.7366,
+    "eval_samples_per_second": 46.929,
+    "eval_steps_per_second": 1.488,
+    "eval_top1_accuracy": 0.9804878048780488,
+    "test_accuracy": 0.9736256821907545,
+    "test_error_rate": 0.026374317809245484,
+    "test_f1": 0.975524936170449,
+    "test_loss": 0.07458387315273285,
+    "test_precision": 0.9770910372814001,
+    "test_recall": 0.975609756097561,
+    "test_runtime": 9.7731,
+    "test_samples_per_second": 41.952,
+    "test_steps_per_second": 1.33,
+    "test_top1_accuracy": 0.975609756097561,
+    "total_flos": 6.268961276565443e+17,
+    "train_loss": 0.578233896850125,
+    "train_runtime": 713.8479,
+    "train_samples_per_second": 45.906,
+    "train_steps_per_second": 1.443
+}

classification_report.csv

@@ -0,0 +1,17 @@
+,precision,recall,f1-score,support
+Acacia,0.9090909090909091,1.0,0.9523809523809523,30.0
+Coconut,1.0,0.9444444444444444,0.9714285714285714,36.0
+Dau,1.0,0.9354838709677419,0.9666666666666667,31.0
+Dita,0.9512195121951219,1.0,0.975,39.0
+Ilang-ilang,0.9333333333333333,1.0,0.9655172413793104,28.0
+Macarthur,1.0,1.0,1.0,34.0
+Mango,1.0,0.9545454545454546,0.9767441860465116,44.0
+Mulawin,1.0,0.8571428571428571,0.9230769230769231,21.0
+Narra,0.9333333333333333,0.9655172413793104,0.9491525423728814,29.0
+Palmera,1.0,1.0,1.0,39.0
+Royal Palm,1.0,1.0,1.0,24.0
+Santol,1.0,1.0,1.0,29.0
+Tabebuia,0.9629629629629629,1.0,0.9811320754716981,26.0
+accuracy,0.975609756097561,0.975609756097561,0.975609756097561,0.975609756097561
+macro avg,0.97614923468582,0.9736256821907545,0.9739307045248858,410.0
+weighted avg,0.9770910372814001,0.975609756097561,0.975524936170449,410.0

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "microsoft/resnet-50",
+  "architectures": [
+    "ResNetForImageClassification"
+  ],
+  "depths": [
+    3,
+    4,
+    6,
+    3
+  ],
+  "downsample_in_bottleneck": false,
+  "downsample_in_first_stage": false,
+  "embedding_size": 64,
+  "hidden_act": "relu",
+  "hidden_sizes": [
+    256,
+    512,
+    1024,
+    2048
+  ],
+  "id2label": {
+    "0": "Acacia",
+    "1": "Coconut",
+    "2": "Dau",
+    "3": "Dita",
+    "4": "Ilang-ilang",
+    "5": "Macarthur",
+    "6": "Mango",
+    "7": "Mulawin",
+    "8": "Narra",
+    "9": "Palmera",
+    "10": "Royal Palm",
+    "11": "Santol",
+    "12": "Tabebuia"
+  },
+  "label2id": {
+    "Acacia": 0,
+    "Coconut": 1,
+    "Dau": 2,
+    "Dita": 3,
+    "Ilang-ilang": 4,
+    "Macarthur": 5,
+    "Mango": 6,
+    "Mulawin": 7,
+    "Narra": 8,
+    "Palmera": 9,
+    "Royal Palm": 10,
+    "Santol": 11,
+    "Tabebuia": 12
+  },
+  "layer_type": "bottleneck",
+  "model_type": "resnet",
+  "num_channels": 3,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2"
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.9765634013174265,
+    "eval_error_rate": 0.02343659868257353,
+    "eval_f1": 0.9804014205399844,
+    "eval_loss": 0.07615971565246582,
+    "eval_precision": 0.9810152386446259,
+    "eval_recall": 0.9804878048780488,
+    "eval_runtime": 8.7366,
+    "eval_samples_per_second": 46.929,
+    "eval_steps_per_second": 1.488,
+    "eval_top1_accuracy": 0.9804878048780488
+}

evaluation/classification_report.csv

@@ -0,0 +1,17 @@
+,precision,recall,f1-score,support
+Acacia,0.9090909090909091,1.0,0.9523809523809523,30.0
+Coconut,1.0,0.9444444444444444,0.9714285714285714,36.0
+Dau,1.0,0.9354838709677419,0.9666666666666667,31.0
+Dita,0.9512195121951219,1.0,0.975,39.0
+Ilang-ilang,0.9333333333333333,1.0,0.9655172413793104,28.0
+Macarthur,1.0,1.0,1.0,34.0
+Mango,1.0,0.9545454545454546,0.9767441860465116,44.0
+Mulawin,1.0,0.8571428571428571,0.9230769230769231,21.0
+Narra,0.9333333333333333,0.9655172413793104,0.9491525423728814,29.0
+Palmera,1.0,1.0,1.0,39.0
+Royal Palm,1.0,1.0,1.0,24.0
+Santol,1.0,1.0,1.0,29.0
+Tabebuia,0.9629629629629629,1.0,0.9811320754716981,26.0
+accuracy,0.975609756097561,0.975609756097561,0.975609756097561,0.975609756097561
+macro avg,0.97614923468582,0.9736256821907545,0.9739307045248858,410.0
+weighted avg,0.9770910372814001,0.975609756097561,0.975524936170449,410.0

evaluation/confusion_matrix.csv

@@ -0,0 +1,14 @@
+,Acacia,Coconut,Dau,Dita,Ilang-ilang,Macarthur,Mango,Mulawin,Narra,Palmera,Royal Palm,Santol,Tabebuia
+Acacia,30,0,0,0,0,0,0,0,0,0,0,0,0
+Coconut,1,34,0,1,0,0,0,0,0,0,0,0,0
+Dau,0,0,29,0,2,0,0,0,0,0,0,0,0
+Dita,0,0,0,39,0,0,0,0,0,0,0,0,0
+Ilang-ilang,0,0,0,0,28,0,0,0,0,0,0,0,0
+Macarthur,0,0,0,0,0,34,0,0,0,0,0,0,0
+Mango,0,0,0,0,0,0,42,0,2,0,0,0,0
+Mulawin,2,0,0,1,0,0,0,18,0,0,0,0,0
+Narra,0,0,0,0,0,0,0,0,28,0,0,0,1
+Palmera,0,0,0,0,0,0,0,0,0,39,0,0,0
+Royal Palm,0,0,0,0,0,0,0,0,0,0,24,0,0
+Santol,0,0,0,0,0,0,0,0,0,0,0,29,0
+Tabebuia,0,0,0,0,0,0,0,0,0,0,0,0,26

evaluation/results.log

@@ -0,0 +1,22 @@
+2025-02-05 22:13:23,203 - INFO - plot_confusion_matrix - Confusion Matrix:
+[[30  0  0  0  0  0  0  0  0  0  0  0  0]
+ [ 1 34  0  1  0  0  0  0  0  0  0  0  0]
+ [ 0  0 29  0  2  0  0  0  0  0  0  0  0]
+ [ 0  0  0 39  0  0  0  0  0  0  0  0  0]
+ [ 0  0  0  0 28  0  0  0  0  0  0  0  0]
+ [ 0  0  0  0  0 34  0  0  0  0  0  0  0]
+ [ 0  0  0  0  0  0 42  0  2  0  0  0  0]
+ [ 2  0  0  1  0  0  0 18  0  0  0  0  0]
+ [ 0  0  0  0  0  0  0  0 28  0  0  0  1]
+ [ 0  0  0  0  0  0  0  0  0 39  0  0  0]
+ [ 0  0  0  0  0  0  0  0  0  0 24  0  0]
+ [ 0  0  0  0  0  0  0  0  0  0  0 29  0]
+ [ 0  0  0  0  0  0  0  0  0  0  0  0 26]]
+2025-02-05 22:13:23,764 - INFO - plot_confusion_matrix - Confusion matrix saved to 2025-02-05-21-58-41-resnet-50/evaluation/confusion_matrix.png
+2025-02-05 22:13:23,922 - INFO - plot_confusion_matrix - Confusion matrix report saved to 2025-02-05-21-58-41-resnet-50/evaluation/confusion_matrix.csv
+2025-02-05 22:13:28,873 - INFO - classification_report_bar - Classification report saved to 2025-02-05-21-58-41-resnet-50/evaluation/classification_report.csv
+2025-02-05 22:13:29,374 - INFO - classification_report_bar - Classification report bar chart saved to 2025-02-05-21-58-41-resnet-50/evaluation/clf_bar.png
+2025-02-05 22:13:29,375 - INFO - classification_report_bar - Overall Accuracy: 0.976
+2025-02-05 22:13:32,675 - INFO - plot_classification_report_heatmap - Classification report heatmap saved to 2025-02-05-21-58-41-resnet-50/classification_report.png
+2025-02-05 22:13:32,796 - INFO - plot_classification_report_heatmap - Classification report saved to 2025-02-05-21-58-41-resnet-50/classification_report.csv
+2025-02-05 22:13:40,000 - INFO - plot_results - Training metrics saved to 2025-02-05-21-58-41-resnet-50/training_metrics.csv

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5292c1c7eb947a6efd76ae4eab8cbac9c75dc73a9f37c08baad88f638ea1a04c
+size 94393148

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "crop_pct": 0.875,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ConvNextImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

test_results.json

@@ -0,0 +1,12 @@
+{
+    "test_accuracy": 0.9736256821907545,
+    "test_error_rate": 0.026374317809245484,
+    "test_f1": 0.975524936170449,
+    "test_loss": 0.07458387315273285,
+    "test_precision": 0.9770910372814001,
+    "test_recall": 0.975609756097561,
+    "test_runtime": 9.7731,
+    "test_samples_per_second": 41.952,
+    "test_steps_per_second": 1.33,
+    "test_top1_accuracy": 0.975609756097561
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.0,
+    "total_flos": 6.268961276565443e+17,
+    "train_loss": 0.578233896850125,
+    "train_runtime": 713.8479,
+    "train_samples_per_second": 45.906,
+    "train_steps_per_second": 1.443
+}

trainer_state.json

@@ -0,0 +1,276 @@
+{
+  "best_metric": 0.07615971565246582,
+  "best_model_checkpoint": "2025-02-05-21-58-41-resnet-50/checkpoint-721",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 927,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "train_accuracy": 0.28471162648764115
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.584263563156128,
+      "learning_rate": 0.0002,
+      "loss": 2.4636,
+      "step": 103
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5823726629787873,
+      "eval_error_rate": 0.4176273370212127,
+      "eval_f1": 0.5929270791957494,
+      "eval_loss": 2.154754877090454,
+      "eval_precision": 0.6866708444643892,
+      "eval_recall": 0.6292682926829268,
+      "eval_runtime": 10.0935,
+      "eval_samples_per_second": 40.62,
+      "eval_steps_per_second": 1.288,
+      "eval_top1_accuracy": 0.6292682926829268,
+      "step": 103
+    },
+    {
+      "epoch": 2.0,
+      "train_accuracy": 0.720368863574722
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.2492337226867676,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 1.3967,
+      "step": 206
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8743437160779054,
+      "eval_error_rate": 0.1256562839220946,
+      "eval_f1": 0.8769823548484003,
+      "eval_loss": 0.5585801601409912,
+      "eval_precision": 0.8893317170713972,
+      "eval_recall": 0.8780487804878049,
+      "eval_runtime": 8.1523,
+      "eval_samples_per_second": 50.292,
+      "eval_steps_per_second": 1.595,
+      "eval_top1_accuracy": 0.8780487804878049,
+      "step": 206
+    },
+    {
+      "epoch": 3.0,
+      "train_accuracy": 0.8866286954163276
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.393784761428833,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.4328,
+      "step": 309
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9524324562338874,
+      "eval_error_rate": 0.04756754376611261,
+      "eval_f1": 0.9518375743563098,
+      "eval_loss": 0.20998375117778778,
+      "eval_precision": 0.9565172518406057,
+      "eval_recall": 0.9512195121951219,
+      "eval_runtime": 8.4452,
+      "eval_samples_per_second": 48.548,
+      "eval_steps_per_second": 1.539,
+      "eval_top1_accuracy": 0.9512195121951219,
+      "step": 309
+    },
+    {
+      "epoch": 4.0,
+      "train_accuracy": 0.92324382967182
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.674211502075195,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.2544,
+      "step": 412
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.958823798940078,
+      "eval_error_rate": 0.041176201059922035,
+      "eval_f1": 0.9612761071488952,
+      "eval_loss": 0.1413789838552475,
+      "eval_precision": 0.9627985812350435,
+      "eval_recall": 0.9609756097560975,
+      "eval_runtime": 9.5611,
+      "eval_samples_per_second": 42.882,
+      "eval_steps_per_second": 1.36,
+      "eval_top1_accuracy": 0.9609756097560975,
+      "step": 412
+    },
+    {
+      "epoch": 5.0,
+      "train_accuracy": 0.9541632763764578
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.053682804107666,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.171,
+      "step": 515
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9638319094938057,
+      "eval_error_rate": 0.036168090506194295,
+      "eval_f1": 0.9682546818665395,
+      "eval_loss": 0.11268524825572968,
+      "eval_precision": 0.9690166293737246,
+      "eval_recall": 0.9682926829268292,
+      "eval_runtime": 9.0863,
+      "eval_samples_per_second": 45.123,
+      "eval_steps_per_second": 1.431,
+      "eval_top1_accuracy": 0.9682926829268292,
+      "step": 515
+    },
+    {
+      "epoch": 6.0,
+      "train_accuracy": 0.9582316246270681
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.191859245300293,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.1556,
+      "step": 618
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9680975082361487,
+      "eval_error_rate": 0.03190249176385129,
+      "eval_f1": 0.9706467840988272,
+      "eval_loss": 0.09764808416366577,
+      "eval_precision": 0.9715023474110591,
+      "eval_recall": 0.9707317073170731,
+      "eval_runtime": 7.867,
+      "eval_samples_per_second": 52.116,
+      "eval_steps_per_second": 1.652,
+      "eval_top1_accuracy": 0.9707317073170731,
+      "step": 618
+    },
+    {
+      "epoch": 7.0,
+      "train_accuracy": 0.9693517765120694
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 13.192668914794922,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.118,
+      "step": 721
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9765634013174265,
+      "eval_error_rate": 0.02343659868257353,
+      "eval_f1": 0.9804014205399844,
+      "eval_loss": 0.07615971565246582,
+      "eval_precision": 0.9810152386446259,
+      "eval_recall": 0.9804878048780488,
+      "eval_runtime": 10.4663,
+      "eval_samples_per_second": 39.173,
+      "eval_steps_per_second": 1.242,
+      "eval_top1_accuracy": 0.9804878048780488,
+      "step": 721
+    },
+    {
+      "epoch": 8.0,
+      "train_accuracy": 0.9712503390290209
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.4042465686798096,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.1142,
+      "step": 824
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9812897795903163,
+      "eval_error_rate": 0.01871022040968373,
+      "eval_f1": 0.9803571227304607,
+      "eval_loss": 0.08533048629760742,
+      "eval_precision": 0.9809065609961366,
+      "eval_recall": 0.9804878048780488,
+      "eval_runtime": 9.5505,
+      "eval_samples_per_second": 42.93,
+      "eval_steps_per_second": 1.361,
+      "eval_top1_accuracy": 0.9804878048780488,
+      "step": 824
+    },
+    {
+      "epoch": 9.0,
+      "train_accuracy": 0.9717927854624356
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 8.842650413513184,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.0978,
+      "step": 927
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9788130896136262,
+      "eval_error_rate": 0.02118691038637377,
+      "eval_f1": 0.9803389295415358,
+      "eval_loss": 0.07979268580675125,
+      "eval_precision": 0.980763088973181,
+      "eval_recall": 0.9804878048780488,
+      "eval_runtime": 8.3701,
+      "eval_samples_per_second": 48.984,
+      "eval_steps_per_second": 1.553,
+      "eval_top1_accuracy": 0.9804878048780488,
+      "step": 927
+    },
+    {
+      "epoch": 9.0,
+      "step": 927,
+      "total_flos": 6.268961276565443e+17,
+      "train_loss": 0.578233896850125,
+      "train_runtime": 713.8479,
+      "train_samples_per_second": 45.906,
+      "train_steps_per_second": 1.443
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1030,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 2
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.268961276565443e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74811b4d1d753ccb9394877c84bb953b0f78c54022cd3a1792ce50e5bb5449aa
+size 5176

training_metrics.csv

@@ -0,0 +1,10 @@
+Epoch,Train Loss,Eval Loss,Train Accuracy,Eval Accuracy
+1,2.4636,2.154754877090454,0.28471162648764115,0.5823726629787873
+2,1.3967,0.5585801601409912,0.720368863574722,0.8743437160779054
+3,0.4328,0.20998375117778778,0.8866286954163276,0.9524324562338874
+4,0.2544,0.1413789838552475,0.92324382967182,0.958823798940078
+5,0.171,0.11268524825572968,0.9541632763764578,0.9638319094938057
+6,0.1556,0.09764808416366577,0.9582316246270681,0.9680975082361487
+7,0.118,0.07615971565246582,0.9693517765120694,0.9765634013174265
+8,0.1142,0.08533048629760742,0.9712503390290209,0.9812897795903163
+9,0.0978,0.07979268580675125,0.9717927854624356,0.9788130896136262