End of training

README.md

@@ -0,0 +1,117 @@
+---
+license: apache-2.0
+base_model: microsoft/swinv2-tiny-patch4-window8-256
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: swinv2-tiny-patch4-window8-256-Diabetic-Retinopathy
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8090909090909091
+---
+
+<!-- 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. -->
+
+# swinv2-tiny-patch4-window8-256-Diabetic-Retinopathy
+
+This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5203
+- Accuracy: 0.8091
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 40
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 5    | 1.6054          | 0.4909   |
+| 1.6039        | 2.0   | 10   | 1.5774          | 0.4909   |
+| 1.6039        | 3.0   | 15   | 1.4627          | 0.4909   |
+| 1.4766        | 4.0   | 20   | 1.3211          | 0.4909   |
+| 1.4766        | 5.0   | 25   | 1.2294          | 0.4909   |
+| 1.2308        | 6.0   | 30   | 1.0657          | 0.4909   |
+| 1.2308        | 7.0   | 35   | 0.9504          | 0.6545   |
+| 1.017         | 8.0   | 40   | 0.8463          | 0.7364   |
+| 1.017         | 9.0   | 45   | 0.7463          | 0.7455   |
+| 0.8345        | 10.0  | 50   | 0.6948          | 0.7455   |
+| 0.8345        | 11.0  | 55   | 0.6460          | 0.7545   |
+| 0.7594        | 12.0  | 60   | 0.6403          | 0.7545   |
+| 0.7594        | 13.0  | 65   | 0.6319          | 0.7545   |
+| 0.7228        | 14.0  | 70   | 0.5999          | 0.7455   |
+| 0.7228        | 15.0  | 75   | 0.5922          | 0.7545   |
+| 0.6851        | 16.0  | 80   | 0.5955          | 0.7636   |
+| 0.6851        | 17.0  | 85   | 0.5731          | 0.7545   |
+| 0.6549        | 18.0  | 90   | 0.5603          | 0.7818   |
+| 0.6549        | 19.0  | 95   | 0.5386          | 0.7818   |
+| 0.643         | 20.0  | 100  | 0.5424          | 0.7727   |
+| 0.643         | 21.0  | 105  | 0.5295          | 0.7909   |
+| 0.5951        | 22.0  | 110  | 0.5203          | 0.8091   |
+| 0.5951        | 23.0  | 115  | 0.5162          | 0.7909   |
+| 0.5913        | 24.0  | 120  | 0.5095          | 0.7818   |
+| 0.5913        | 25.0  | 125  | 0.5140          | 0.7909   |
+| 0.5462        | 26.0  | 130  | 0.5167          | 0.7636   |
+| 0.5462        | 27.0  | 135  | 0.4943          | 0.7909   |
+| 0.5538        | 28.0  | 140  | 0.4844          | 0.7636   |
+| 0.5538        | 29.0  | 145  | 0.4821          | 0.7727   |
+| 0.5497        | 30.0  | 150  | 0.4952          | 0.7727   |
+| 0.5497        | 31.0  | 155  | 0.4995          | 0.7818   |
+| 0.4923        | 32.0  | 160  | 0.4910          | 0.7727   |
+| 0.4923        | 33.0  | 165  | 0.5029          | 0.7818   |
+| 0.5228        | 34.0  | 170  | 0.5083          | 0.7818   |
+| 0.5228        | 35.0  | 175  | 0.4984          | 0.7909   |
+| 0.4986        | 36.0  | 180  | 0.4914          | 0.7909   |
+| 0.4986        | 37.0  | 185  | 0.4926          | 0.7909   |
+| 0.5154        | 38.0  | 190  | 0.4915          | 0.8      |
+| 0.5154        | 39.0  | 195  | 0.4886          | 0.8      |
+| 0.5081        | 40.0  | 200  | 0.4875          | 0.8      |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 40.0,
+    "eval_accuracy": 0.8090909090909091,
+    "eval_loss": 0.5203222036361694,
+    "eval_runtime": 0.6076,
+    "eval_samples_per_second": 181.031,
+    "eval_steps_per_second": 6.583,
+    "train_loss": 0.750064127445221,
+    "train_runtime": 356.9379,
+    "train_samples_per_second": 69.816,
+    "train_steps_per_second": 0.56
+}

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "microsoft/swinv2-tiny-patch4-window8-256",
+  "architectures": [
+    "Swinv2ForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    6,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 96,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Mild",
+    "1": "Moderate",
+    "2": "No_DR",
+    "3": "Proliferate_DR",
+    "4": "Severe"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Mild": 0,
+    "Moderate": 1,
+    "No_DR": 2,
+    "Proliferate_DR": 3,
+    "Severe": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swinv2",
+  "num_channels": 3,
+  "num_heads": [
+    3,
+    6,
+    12,
+    24
+  ],
+  "num_layers": 4,
+  "patch_size": 4,
+  "path_norm": true,
+  "pretrained_window_sizes": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_absolute_embeddings": false,
+  "window_size": 8
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 40.0,
+    "eval_accuracy": 0.8090909090909091,
+    "eval_loss": 0.5203222036361694,
+    "eval_runtime": 0.6076,
+    "eval_samples_per_second": 181.031,
+    "eval_steps_per_second": 6.583
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1f96515fab9dc9e7f57e7ccdd219306116ce8deddbbea81b330b3249533682
+size 110359372

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 256,
+    "width": 256
+  }
+}

runs/Oct12_17-58-48_DESKTOP-SKBE9FB/events.out.tfevents.1728777529.DESKTOP-SKBE9FB.14652.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9792bc671787aa2b7cce2e68160e97fc5dd15bbe2de4196ddceb48ac222355a
+size 21112

runs/Oct12_17-58-48_DESKTOP-SKBE9FB/events.out.tfevents.1728777886.DESKTOP-SKBE9FB.14652.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f2f25b487b50e2eae2515b87ceec72618266c72689d8ae66e6ecec54783027d
+size 411

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 40.0,
+    "train_loss": 0.750064127445221,
+    "train_runtime": 356.9379,
+    "train_samples_per_second": 69.816,
+    "train_steps_per_second": 0.56
+}

trainer_state.json

@@ -0,0 +1,510 @@
+{
+  "best_metric": 0.8090909090909091,
+  "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-Diabetic-Retinopathy\\checkpoint-110",
+  "epoch": 40.0,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4909090909090909,
+      "eval_loss": 1.6053773164749146,
+      "eval_runtime": 1.1664,
+      "eval_samples_per_second": 94.304,
+      "eval_steps_per_second": 3.429,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.5e-05,
+      "loss": 1.6039,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4909090909090909,
+      "eval_loss": 1.577444314956665,
+      "eval_runtime": 0.6246,
+      "eval_samples_per_second": 176.117,
+      "eval_steps_per_second": 6.404,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4909090909090909,
+      "eval_loss": 1.4627095460891724,
+      "eval_runtime": 0.6237,
+      "eval_samples_per_second": 176.372,
+      "eval_steps_per_second": 6.414,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 5e-05,
+      "loss": 1.4766,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4909090909090909,
+      "eval_loss": 1.3211016654968262,
+      "eval_runtime": 0.5963,
+      "eval_samples_per_second": 184.459,
+      "eval_steps_per_second": 6.708,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4909090909090909,
+      "eval_loss": 1.2294203042984009,
+      "eval_runtime": 0.6045,
+      "eval_samples_per_second": 181.978,
+      "eval_steps_per_second": 6.617,
+      "step": 25
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 1.2308,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4909090909090909,
+      "eval_loss": 1.0656994581222534,
+      "eval_runtime": 0.6274,
+      "eval_samples_per_second": 175.336,
+      "eval_steps_per_second": 6.376,
+      "step": 30
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6545454545454545,
+      "eval_loss": 0.9504080414772034,
+      "eval_runtime": 0.6116,
+      "eval_samples_per_second": 179.842,
+      "eval_steps_per_second": 6.54,
+      "step": 35
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.017,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7363636363636363,
+      "eval_loss": 0.8463379740715027,
+      "eval_runtime": 0.6133,
+      "eval_samples_per_second": 179.362,
+      "eval_steps_per_second": 6.522,
+      "step": 40
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7454545454545455,
+      "eval_loss": 0.7462926506996155,
+      "eval_runtime": 0.6373,
+      "eval_samples_per_second": 172.596,
+      "eval_steps_per_second": 6.276,
+      "step": 45
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.8345,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7454545454545455,
+      "eval_loss": 0.6947882771492004,
+      "eval_runtime": 0.6097,
+      "eval_samples_per_second": 180.42,
+      "eval_steps_per_second": 6.561,
+      "step": 50
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.7545454545454545,
+      "eval_loss": 0.6460423469543457,
+      "eval_runtime": 0.6052,
+      "eval_samples_per_second": 181.744,
+      "eval_steps_per_second": 6.609,
+      "step": 55
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.7594,
+      "step": 60
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.7545454545454545,
+      "eval_loss": 0.6403194069862366,
+      "eval_runtime": 0.6016,
+      "eval_samples_per_second": 182.831,
+      "eval_steps_per_second": 6.648,
+      "step": 60
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.7545454545454545,
+      "eval_loss": 0.631945788860321,
+      "eval_runtime": 0.6046,
+      "eval_samples_per_second": 181.926,
+      "eval_steps_per_second": 6.615,
+      "step": 65
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 3.611111111111111e-05,
+      "loss": 0.7228,
+      "step": 70
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.7454545454545455,
+      "eval_loss": 0.5999094843864441,
+      "eval_runtime": 0.6056,
+      "eval_samples_per_second": 181.624,
+      "eval_steps_per_second": 6.605,
+      "step": 70
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.7545454545454545,
+      "eval_loss": 0.5922093391418457,
+      "eval_runtime": 0.5972,
+      "eval_samples_per_second": 184.202,
+      "eval_steps_per_second": 6.698,
+      "step": 75
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6851,
+      "step": 80
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.7636363636363637,
+      "eval_loss": 0.5955119132995605,
+      "eval_runtime": 0.6011,
+      "eval_samples_per_second": 182.985,
+      "eval_steps_per_second": 6.654,
+      "step": 80
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.7545454545454545,
+      "eval_loss": 0.573071300983429,
+      "eval_runtime": 0.6051,
+      "eval_samples_per_second": 181.777,
+      "eval_steps_per_second": 6.61,
+      "step": 85
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.6549,
+      "step": 90
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.5602535605430603,
+      "eval_runtime": 0.7062,
+      "eval_samples_per_second": 155.768,
+      "eval_steps_per_second": 5.664,
+      "step": 90
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.5386339426040649,
+      "eval_runtime": 0.6221,
+      "eval_samples_per_second": 176.809,
+      "eval_steps_per_second": 6.429,
+      "step": 95
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.643,
+      "step": 100
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.7727272727272727,
+      "eval_loss": 0.5423626899719238,
+      "eval_runtime": 0.6072,
+      "eval_samples_per_second": 181.171,
+      "eval_steps_per_second": 6.588,
+      "step": 100
+    },
+    {
+      "epoch": 21.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.5295349955558777,
+      "eval_runtime": 0.6772,
+      "eval_samples_per_second": 162.427,
+      "eval_steps_per_second": 5.906,
+      "step": 105
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5951,
+      "step": 110
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.8090909090909091,
+      "eval_loss": 0.5203222036361694,
+      "eval_runtime": 0.6067,
+      "eval_samples_per_second": 181.322,
+      "eval_steps_per_second": 6.594,
+      "step": 110
+    },
+    {
+      "epoch": 23.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.516213059425354,
+      "eval_runtime": 0.6272,
+      "eval_samples_per_second": 175.393,
+      "eval_steps_per_second": 6.378,
+      "step": 115
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.5913,
+      "step": 120
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.5094789862632751,
+      "eval_runtime": 0.6677,
+      "eval_samples_per_second": 164.747,
+      "eval_steps_per_second": 5.991,
+      "step": 120
+    },
+    {
+      "epoch": 25.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.5140318870544434,
+      "eval_runtime": 0.6572,
+      "eval_samples_per_second": 167.374,
+      "eval_steps_per_second": 6.086,
+      "step": 125
+    },
+    {
+      "epoch": 26.0,
+      "learning_rate": 1.9444444444444445e-05,
+      "loss": 0.5462,
+      "step": 130
+    },
+    {
+      "epoch": 26.0,
+      "eval_accuracy": 0.7636363636363637,
+      "eval_loss": 0.5167139768600464,
+      "eval_runtime": 0.7442,
+      "eval_samples_per_second": 147.801,
+      "eval_steps_per_second": 5.375,
+      "step": 130
+    },
+    {
+      "epoch": 27.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.49426034092903137,
+      "eval_runtime": 0.6102,
+      "eval_samples_per_second": 180.278,
+      "eval_steps_per_second": 6.556,
+      "step": 135
+    },
+    {
+      "epoch": 28.0,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.5538,
+      "step": 140
+    },
+    {
+      "epoch": 28.0,
+      "eval_accuracy": 0.7636363636363637,
+      "eval_loss": 0.4843919575214386,
+      "eval_runtime": 0.7542,
+      "eval_samples_per_second": 145.854,
+      "eval_steps_per_second": 5.304,
+      "step": 140
+    },
+    {
+      "epoch": 29.0,
+      "eval_accuracy": 0.7727272727272727,
+      "eval_loss": 0.4821490943431854,
+      "eval_runtime": 0.6238,
+      "eval_samples_per_second": 176.347,
+      "eval_steps_per_second": 6.413,
+      "step": 145
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.5497,
+      "step": 150
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.7727272727272727,
+      "eval_loss": 0.49517491459846497,
+      "eval_runtime": 0.6867,
+      "eval_samples_per_second": 160.188,
+      "eval_steps_per_second": 5.825,
+      "step": 150
+    },
+    {
+      "epoch": 31.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.499459445476532,
+      "eval_runtime": 0.6542,
+      "eval_samples_per_second": 168.144,
+      "eval_steps_per_second": 6.114,
+      "step": 155
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.4923,
+      "step": 160
+    },
+    {
+      "epoch": 32.0,
+      "eval_accuracy": 0.7727272727272727,
+      "eval_loss": 0.4910464286804199,
+      "eval_runtime": 0.6079,
+      "eval_samples_per_second": 180.941,
+      "eval_steps_per_second": 6.58,
+      "step": 160
+    },
+    {
+      "epoch": 33.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.5028622150421143,
+      "eval_runtime": 0.6106,
+      "eval_samples_per_second": 180.138,
+      "eval_steps_per_second": 6.55,
+      "step": 165
+    },
+    {
+      "epoch": 34.0,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.5228,
+      "step": 170
+    },
+    {
+      "epoch": 34.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.5083434581756592,
+      "eval_runtime": 0.6097,
+      "eval_samples_per_second": 180.422,
+      "eval_steps_per_second": 6.561,
+      "step": 170
+    },
+    {
+      "epoch": 35.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.49842116236686707,
+      "eval_runtime": 0.6153,
+      "eval_samples_per_second": 178.786,
+      "eval_steps_per_second": 6.501,
+      "step": 175
+    },
+    {
+      "epoch": 36.0,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.4986,
+      "step": 180
+    },
+    {
+      "epoch": 36.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.4914481043815613,
+      "eval_runtime": 0.6407,
+      "eval_samples_per_second": 171.693,
+      "eval_steps_per_second": 6.243,
+      "step": 180
+    },
+    {
+      "epoch": 37.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.4926435649394989,
+      "eval_runtime": 0.6131,
+      "eval_samples_per_second": 179.402,
+      "eval_steps_per_second": 6.524,
+      "step": 185
+    },
+    {
+      "epoch": 38.0,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 0.5154,
+      "step": 190
+    },
+    {
+      "epoch": 38.0,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.49148377776145935,
+      "eval_runtime": 0.6154,
+      "eval_samples_per_second": 178.737,
+      "eval_steps_per_second": 6.5,
+      "step": 190
+    },
+    {
+      "epoch": 39.0,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.4885866641998291,
+      "eval_runtime": 0.636,
+      "eval_samples_per_second": 172.961,
+      "eval_steps_per_second": 6.289,
+      "step": 195
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 0.0,
+      "loss": 0.5081,
+      "step": 200
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.48748189210891724,
+      "eval_runtime": 0.5972,
+      "eval_samples_per_second": 184.204,
+      "eval_steps_per_second": 6.698,
+      "step": 200
+    },
+    {
+      "epoch": 40.0,
+      "step": 200,
+      "total_flos": 8.108232849122918e+17,
+      "train_loss": 0.750064127445221,
+      "train_runtime": 356.9379,
+      "train_samples_per_second": 69.816,
+      "train_steps_per_second": 0.56
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 8.108232849122918e+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 sha256:1da300db61b98a7ddf001c7458ae82ed135715be936217a23a82db8c397b1644
+size 4792