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-DA
+  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-DA
+
+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: 0.6974
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.5987        | 1.0   | 23   | 1.5683          | 0.4909   |
+| 1.4137        | 2.0   | 46   | 1.2639          | 0.4909   |
+| 1.1988        | 3.0   | 69   | 0.8726          | 0.7636   |
+| 0.8533        | 4.0   | 92   | 0.6361          | 0.7545   |
+| 0.8042        | 5.0   | 115  | 0.5985          | 0.7545   |
+| 0.7349        | 6.0   | 138  | 0.5943          | 0.7545   |
+| 0.7003        | 7.0   | 161  | 0.5178          | 0.7636   |
+| 0.6641        | 8.0   | 184  | 0.5058          | 0.7545   |
+| 0.641         | 9.0   | 207  | 0.5092          | 0.7909   |
+| 0.6571        | 10.0  | 230  | 0.5319          | 0.7636   |
+| 0.6522        | 11.0  | 253  | 0.5726          | 0.7909   |
+| 0.5659        | 12.0  | 276  | 0.5490          | 0.7727   |
+| 0.5511        | 13.0  | 299  | 0.5465          | 0.8      |
+| 0.5435        | 14.0  | 322  | 0.5728          | 0.7909   |
+| 0.5259        | 15.0  | 345  | 0.6047          | 0.7636   |
+| 0.5496        | 16.0  | 368  | 0.6479          | 0.7818   |
+| 0.543         | 17.0  | 391  | 0.6040          | 0.7727   |
+| 0.4646        | 18.0  | 414  | 0.6269          | 0.7818   |
+| 0.4867        | 19.0  | 437  | 0.6535          | 0.7909   |
+| 0.4357        | 20.0  | 460  | 0.6991          | 0.7727   |
+| 0.4392        | 21.0  | 483  | 0.7127          | 0.7636   |
+| 0.4403        | 22.0  | 506  | 0.6974          | 0.8091   |
+| 0.4358        | 23.0  | 529  | 0.6883          | 0.7818   |
+| 0.4094        | 24.0  | 552  | 0.6768          | 0.8      |
+| 0.3913        | 25.0  | 575  | 0.7270          | 0.7636   |
+| 0.3686        | 26.0  | 598  | 0.7104          | 0.7727   |
+| 0.3679        | 27.0  | 621  | 0.7115          | 0.7818   |
+| 0.378         | 28.0  | 644  | 0.8020          | 0.8091   |
+| 0.3583        | 29.0  | 667  | 0.7524          | 0.7909   |
+| 0.3299        | 30.0  | 690  | 0.7783          | 0.7909   |
+| 0.3672        | 31.0  | 713  | 0.8193          | 0.7909   |
+| 0.3567        | 32.0  | 736  | 0.8095          | 0.7909   |
+| 0.3585        | 33.0  | 759  | 0.8324          | 0.7909   |
+| 0.3191        | 34.0  | 782  | 0.8042          | 0.7909   |
+| 0.3144        | 35.0  | 805  | 0.8189          | 0.7909   |
+| 0.3452        | 36.0  | 828  | 0.8377          | 0.7909   |
+| 0.3263        | 37.0  | 851  | 0.8204          | 0.7909   |
+| 0.2939        | 38.0  | 874  | 0.8103          | 0.7909   |
+| 0.3152        | 39.0  | 897  | 0.8184          | 0.7818   |
+| 0.2787        | 40.0  | 920  | 0.8241          | 0.7818   |
+
+
+### 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": 0.6974316239356995,
+    "eval_runtime": 0.6742,
+    "eval_samples_per_second": 163.163,
+    "eval_steps_per_second": 5.933,
+    "train_loss": 0.5426292188789533,
+    "train_runtime": 1410.8495,
+    "train_samples_per_second": 83.326,
+    "train_steps_per_second": 0.652
+}

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": 0.6974316239356995,
+    "eval_runtime": 0.6742,
+    "eval_samples_per_second": 163.163,
+    "eval_steps_per_second": 5.933
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:895a48e889531812cac0cf571535863249257a3f00e2c2c94e6cc38547193626
+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_18-07-36_DESKTOP-SKBE9FB/events.out.tfevents.1728778058.DESKTOP-SKBE9FB.19200.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4d23023ce0cca38176c71d71a57e3e9887ebca434db45ba4c04a8a42ebf9ff
+size 32545

runs/Oct12_18-07-36_DESKTOP-SKBE9FB/events.out.tfevents.1728779469.DESKTOP-SKBE9FB.19200.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cf092e0d8e079f2830f1a9867173a87f69dd934f1e3ba76ee83c8adf6c04c17
+size 411

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 40.0,
+    "train_loss": 0.5426292188789533,
+    "train_runtime": 1410.8495,
+    "train_samples_per_second": 83.326,
+    "train_steps_per_second": 0.652
+}

trainer_state.json

@@ -0,0 +1,942 @@
+{
+  "best_metric": 0.8090909090909091,
+  "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-Diabetic-Retinopathy-DA\\checkpoint-506",
+  "epoch": 40.0,
+  "eval_steps": 500,
+  "global_step": 920,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 1.6086,
+      "step": 10
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 1.5987,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4909090909090909,
+      "eval_loss": 1.5683298110961914,
+      "eval_runtime": 1.0793,
+      "eval_samples_per_second": 101.92,
+      "eval_steps_per_second": 3.706,
+      "step": 23
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.630434782608696e-05,
+      "loss": 1.5503,
+      "step": 30
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 1.4137,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4909090909090909,
+      "eval_loss": 1.263899564743042,
+      "eval_runtime": 0.6653,
+      "eval_samples_per_second": 165.342,
+      "eval_steps_per_second": 6.012,
+      "step": 46
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 2.7173913043478262e-05,
+      "loss": 1.3316,
+      "step": 50
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 1.1988,
+      "step": 60
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7636363636363637,
+      "eval_loss": 0.8725916743278503,
+      "eval_runtime": 0.6051,
+      "eval_samples_per_second": 181.777,
+      "eval_steps_per_second": 6.61,
+      "step": 69
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 3.804347826086957e-05,
+      "loss": 1.058,
+      "step": 70
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.9368,
+      "step": 80
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 4.891304347826087e-05,
+      "loss": 0.8533,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7545454545454545,
+      "eval_loss": 0.6361170411109924,
+      "eval_runtime": 0.6021,
+      "eval_samples_per_second": 182.679,
+      "eval_steps_per_second": 6.643,
+      "step": 92
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 4.9516908212560386e-05,
+      "loss": 0.852,
+      "step": 100
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 4.891304347826087e-05,
+      "loss": 0.8042,
+      "step": 110
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7545454545454545,
+      "eval_loss": 0.5984649658203125,
+      "eval_runtime": 0.6091,
+      "eval_samples_per_second": 180.58,
+      "eval_steps_per_second": 6.567,
+      "step": 115
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 4.830917874396135e-05,
+      "loss": 0.7697,
+      "step": 120
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 4.770531400966184e-05,
+      "loss": 0.7349,
+      "step": 130
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7545454545454545,
+      "eval_loss": 0.5943260788917542,
+      "eval_runtime": 0.6065,
+      "eval_samples_per_second": 181.376,
+      "eval_steps_per_second": 6.595,
+      "step": 138
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 4.710144927536232e-05,
+      "loss": 0.7623,
+      "step": 140
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 4.64975845410628e-05,
+      "loss": 0.7249,
+      "step": 150
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 4.589371980676328e-05,
+      "loss": 0.7003,
+      "step": 160
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7636363636363637,
+      "eval_loss": 0.5177913904190063,
+      "eval_runtime": 0.6592,
+      "eval_samples_per_second": 166.881,
+      "eval_steps_per_second": 6.068,
+      "step": 161
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 4.528985507246377e-05,
+      "loss": 0.6755,
+      "step": 170
+    },
+    {
+      "epoch": 7.83,
+      "learning_rate": 4.4685990338164255e-05,
+      "loss": 0.6641,
+      "step": 180
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7545454545454545,
+      "eval_loss": 0.5058346390724182,
+      "eval_runtime": 0.6561,
+      "eval_samples_per_second": 167.65,
+      "eval_steps_per_second": 6.096,
+      "step": 184
+    },
+    {
+      "epoch": 8.26,
+      "learning_rate": 4.408212560386474e-05,
+      "loss": 0.6263,
+      "step": 190
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.641,
+      "step": 200
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.5091794729232788,
+      "eval_runtime": 0.6128,
+      "eval_samples_per_second": 179.502,
+      "eval_steps_per_second": 6.527,
+      "step": 207
+    },
+    {
+      "epoch": 9.13,
+      "learning_rate": 4.2874396135265707e-05,
+      "loss": 0.6213,
+      "step": 210
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 4.2270531400966186e-05,
+      "loss": 0.599,
+      "step": 220
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.6571,
+      "step": 230
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7636363636363637,
+      "eval_loss": 0.5319333076477051,
+      "eval_runtime": 0.6289,
+      "eval_samples_per_second": 174.897,
+      "eval_steps_per_second": 6.36,
+      "step": 230
+    },
+    {
+      "epoch": 10.43,
+      "learning_rate": 4.106280193236715e-05,
+      "loss": 0.626,
+      "step": 240
+    },
+    {
+      "epoch": 10.87,
+      "learning_rate": 4.045893719806764e-05,
+      "loss": 0.6522,
+      "step": 250
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.5725868344306946,
+      "eval_runtime": 0.7147,
+      "eval_samples_per_second": 153.916,
+      "eval_steps_per_second": 5.597,
+      "step": 253
+    },
+    {
+      "epoch": 11.3,
+      "learning_rate": 3.985507246376812e-05,
+      "loss": 0.5859,
+      "step": 260
+    },
+    {
+      "epoch": 11.74,
+      "learning_rate": 3.92512077294686e-05,
+      "loss": 0.5659,
+      "step": 270
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.7727272727272727,
+      "eval_loss": 0.5489825010299683,
+      "eval_runtime": 0.6332,
+      "eval_samples_per_second": 173.73,
+      "eval_steps_per_second": 6.317,
+      "step": 276
+    },
+    {
+      "epoch": 12.17,
+      "learning_rate": 3.864734299516908e-05,
+      "loss": 0.556,
+      "step": 280
+    },
+    {
+      "epoch": 12.61,
+      "learning_rate": 3.804347826086957e-05,
+      "loss": 0.5511,
+      "step": 290
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.546451210975647,
+      "eval_runtime": 0.6251,
+      "eval_samples_per_second": 175.96,
+      "eval_steps_per_second": 6.399,
+      "step": 299
+    },
+    {
+      "epoch": 13.04,
+      "learning_rate": 3.743961352657005e-05,
+      "loss": 0.5614,
+      "step": 300
+    },
+    {
+      "epoch": 13.48,
+      "learning_rate": 3.6835748792270534e-05,
+      "loss": 0.5552,
+      "step": 310
+    },
+    {
+      "epoch": 13.91,
+      "learning_rate": 3.6231884057971014e-05,
+      "loss": 0.5435,
+      "step": 320
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.5727524757385254,
+      "eval_runtime": 0.6272,
+      "eval_samples_per_second": 175.393,
+      "eval_steps_per_second": 6.378,
+      "step": 322
+    },
+    {
+      "epoch": 14.35,
+      "learning_rate": 3.56280193236715e-05,
+      "loss": 0.5447,
+      "step": 330
+    },
+    {
+      "epoch": 14.78,
+      "learning_rate": 3.502415458937198e-05,
+      "loss": 0.5259,
+      "step": 340
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.7636363636363637,
+      "eval_loss": 0.6047121286392212,
+      "eval_runtime": 0.6091,
+      "eval_samples_per_second": 180.583,
+      "eval_steps_per_second": 6.567,
+      "step": 345
+    },
+    {
+      "epoch": 15.22,
+      "learning_rate": 3.4420289855072465e-05,
+      "loss": 0.507,
+      "step": 350
+    },
+    {
+      "epoch": 15.65,
+      "learning_rate": 3.381642512077295e-05,
+      "loss": 0.5496,
+      "step": 360
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.6479418873786926,
+      "eval_runtime": 0.6141,
+      "eval_samples_per_second": 179.113,
+      "eval_steps_per_second": 6.513,
+      "step": 368
+    },
+    {
+      "epoch": 16.09,
+      "learning_rate": 3.321256038647343e-05,
+      "loss": 0.5197,
+      "step": 370
+    },
+    {
+      "epoch": 16.52,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.4831,
+      "step": 380
+    },
+    {
+      "epoch": 16.96,
+      "learning_rate": 3.2004830917874396e-05,
+      "loss": 0.543,
+      "step": 390
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.7727272727272727,
+      "eval_loss": 0.6039574146270752,
+      "eval_runtime": 0.6076,
+      "eval_samples_per_second": 181.028,
+      "eval_steps_per_second": 6.583,
+      "step": 391
+    },
+    {
+      "epoch": 17.39,
+      "learning_rate": 3.140096618357488e-05,
+      "loss": 0.4882,
+      "step": 400
+    },
+    {
+      "epoch": 17.83,
+      "learning_rate": 3.079710144927536e-05,
+      "loss": 0.4646,
+      "step": 410
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.6269252896308899,
+      "eval_runtime": 0.6351,
+      "eval_samples_per_second": 173.193,
+      "eval_steps_per_second": 6.298,
+      "step": 414
+    },
+    {
+      "epoch": 18.26,
+      "learning_rate": 3.0193236714975848e-05,
+      "loss": 0.4597,
+      "step": 420
+    },
+    {
+      "epoch": 18.7,
+      "learning_rate": 2.9589371980676327e-05,
+      "loss": 0.4867,
+      "step": 430
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.6535181403160095,
+      "eval_runtime": 0.6591,
+      "eval_samples_per_second": 166.882,
+      "eval_steps_per_second": 6.068,
+      "step": 437
+    },
+    {
+      "epoch": 19.13,
+      "learning_rate": 2.8985507246376814e-05,
+      "loss": 0.4751,
+      "step": 440
+    },
+    {
+      "epoch": 19.57,
+      "learning_rate": 2.8381642512077293e-05,
+      "loss": 0.4354,
+      "step": 450
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.4357,
+      "step": 460
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.7727272727272727,
+      "eval_loss": 0.6990672945976257,
+      "eval_runtime": 0.6056,
+      "eval_samples_per_second": 181.624,
+      "eval_steps_per_second": 6.605,
+      "step": 460
+    },
+    {
+      "epoch": 20.43,
+      "learning_rate": 2.7173913043478262e-05,
+      "loss": 0.4275,
+      "step": 470
+    },
+    {
+      "epoch": 20.87,
+      "learning_rate": 2.6570048309178748e-05,
+      "loss": 0.4392,
+      "step": 480
+    },
+    {
+      "epoch": 21.0,
+      "eval_accuracy": 0.7636363636363637,
+      "eval_loss": 0.7126674056053162,
+      "eval_runtime": 0.6271,
+      "eval_samples_per_second": 175.399,
+      "eval_steps_per_second": 6.378,
+      "step": 483
+    },
+    {
+      "epoch": 21.3,
+      "learning_rate": 2.5966183574879227e-05,
+      "loss": 0.4595,
+      "step": 490
+    },
+    {
+      "epoch": 21.74,
+      "learning_rate": 2.5362318840579714e-05,
+      "loss": 0.4403,
+      "step": 500
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.8090909090909091,
+      "eval_loss": 0.6974316239356995,
+      "eval_runtime": 0.6812,
+      "eval_samples_per_second": 161.491,
+      "eval_steps_per_second": 5.872,
+      "step": 506
+    },
+    {
+      "epoch": 22.17,
+      "learning_rate": 2.4758454106280193e-05,
+      "loss": 0.4305,
+      "step": 510
+    },
+    {
+      "epoch": 22.61,
+      "learning_rate": 2.4154589371980676e-05,
+      "loss": 0.4358,
+      "step": 520
+    },
+    {
+      "epoch": 23.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.688274085521698,
+      "eval_runtime": 0.6268,
+      "eval_samples_per_second": 175.487,
+      "eval_steps_per_second": 6.381,
+      "step": 529
+    },
+    {
+      "epoch": 23.04,
+      "learning_rate": 2.355072463768116e-05,
+      "loss": 0.4054,
+      "step": 530
+    },
+    {
+      "epoch": 23.48,
+      "learning_rate": 2.294685990338164e-05,
+      "loss": 0.4162,
+      "step": 540
+    },
+    {
+      "epoch": 23.91,
+      "learning_rate": 2.2342995169082127e-05,
+      "loss": 0.4094,
+      "step": 550
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.6768017411231995,
+      "eval_runtime": 0.6762,
+      "eval_samples_per_second": 162.682,
+      "eval_steps_per_second": 5.916,
+      "step": 552
+    },
+    {
+      "epoch": 24.35,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.3892,
+      "step": 560
+    },
+    {
+      "epoch": 24.78,
+      "learning_rate": 2.1135265700483093e-05,
+      "loss": 0.3913,
+      "step": 570
+    },
+    {
+      "epoch": 25.0,
+      "eval_accuracy": 0.7636363636363637,
+      "eval_loss": 0.7269611954689026,
+      "eval_runtime": 0.6222,
+      "eval_samples_per_second": 176.803,
+      "eval_steps_per_second": 6.429,
+      "step": 575
+    },
+    {
+      "epoch": 25.22,
+      "learning_rate": 2.0531400966183576e-05,
+      "loss": 0.3916,
+      "step": 580
+    },
+    {
+      "epoch": 25.65,
+      "learning_rate": 1.992753623188406e-05,
+      "loss": 0.3686,
+      "step": 590
+    },
+    {
+      "epoch": 26.0,
+      "eval_accuracy": 0.7727272727272727,
+      "eval_loss": 0.7104293704032898,
+      "eval_runtime": 0.6272,
+      "eval_samples_per_second": 175.395,
+      "eval_steps_per_second": 6.378,
+      "step": 598
+    },
+    {
+      "epoch": 26.09,
+      "learning_rate": 1.932367149758454e-05,
+      "loss": 0.4003,
+      "step": 600
+    },
+    {
+      "epoch": 26.52,
+      "learning_rate": 1.8719806763285024e-05,
+      "loss": 0.3857,
+      "step": 610
+    },
+    {
+      "epoch": 26.96,
+      "learning_rate": 1.8115942028985507e-05,
+      "loss": 0.3679,
+      "step": 620
+    },
+    {
+      "epoch": 27.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.7115088701248169,
+      "eval_runtime": 0.6281,
+      "eval_samples_per_second": 175.12,
+      "eval_steps_per_second": 6.368,
+      "step": 621
+    },
+    {
+      "epoch": 27.39,
+      "learning_rate": 1.751207729468599e-05,
+      "loss": 0.3723,
+      "step": 630
+    },
+    {
+      "epoch": 27.83,
+      "learning_rate": 1.6908212560386476e-05,
+      "loss": 0.378,
+      "step": 640
+    },
+    {
+      "epoch": 28.0,
+      "eval_accuracy": 0.8090909090909091,
+      "eval_loss": 0.8020210862159729,
+      "eval_runtime": 0.6672,
+      "eval_samples_per_second": 164.88,
+      "eval_steps_per_second": 5.996,
+      "step": 644
+    },
+    {
+      "epoch": 28.26,
+      "learning_rate": 1.630434782608696e-05,
+      "loss": 0.3979,
+      "step": 650
+    },
+    {
+      "epoch": 28.7,
+      "learning_rate": 1.570048309178744e-05,
+      "loss": 0.3583,
+      "step": 660
+    },
+    {
+      "epoch": 29.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.7524499893188477,
+      "eval_runtime": 0.6692,
+      "eval_samples_per_second": 164.387,
+      "eval_steps_per_second": 5.978,
+      "step": 667
+    },
+    {
+      "epoch": 29.13,
+      "learning_rate": 1.5096618357487924e-05,
+      "loss": 0.3708,
+      "step": 670
+    },
+    {
+      "epoch": 29.57,
+      "learning_rate": 1.4492753623188407e-05,
+      "loss": 0.3351,
+      "step": 680
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.3299,
+      "step": 690
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.7783340215682983,
+      "eval_runtime": 0.6563,
+      "eval_samples_per_second": 167.609,
+      "eval_steps_per_second": 6.095,
+      "step": 690
+    },
+    {
+      "epoch": 30.43,
+      "learning_rate": 1.3285024154589374e-05,
+      "loss": 0.3476,
+      "step": 700
+    },
+    {
+      "epoch": 30.87,
+      "learning_rate": 1.2681159420289857e-05,
+      "loss": 0.3672,
+      "step": 710
+    },
+    {
+      "epoch": 31.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.8193163871765137,
+      "eval_runtime": 0.6541,
+      "eval_samples_per_second": 168.158,
+      "eval_steps_per_second": 6.115,
+      "step": 713
+    },
+    {
+      "epoch": 31.3,
+      "learning_rate": 1.2077294685990338e-05,
+      "loss": 0.3257,
+      "step": 720
+    },
+    {
+      "epoch": 31.74,
+      "learning_rate": 1.147342995169082e-05,
+      "loss": 0.3567,
+      "step": 730
+    },
+    {
+      "epoch": 32.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.809545636177063,
+      "eval_runtime": 0.6397,
+      "eval_samples_per_second": 171.969,
+      "eval_steps_per_second": 6.253,
+      "step": 736
+    },
+    {
+      "epoch": 32.17,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.32,
+      "step": 740
+    },
+    {
+      "epoch": 32.61,
+      "learning_rate": 1.0265700483091788e-05,
+      "loss": 0.3585,
+      "step": 750
+    },
+    {
+      "epoch": 33.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.8323901295661926,
+      "eval_runtime": 0.6281,
+      "eval_samples_per_second": 175.12,
+      "eval_steps_per_second": 6.368,
+      "step": 759
+    },
+    {
+      "epoch": 33.04,
+      "learning_rate": 9.66183574879227e-06,
+      "loss": 0.3212,
+      "step": 760
+    },
+    {
+      "epoch": 33.48,
+      "learning_rate": 9.057971014492753e-06,
+      "loss": 0.3189,
+      "step": 770
+    },
+    {
+      "epoch": 33.91,
+      "learning_rate": 8.454106280193238e-06,
+      "loss": 0.3191,
+      "step": 780
+    },
+    {
+      "epoch": 34.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.8041682243347168,
+      "eval_runtime": 0.6299,
+      "eval_samples_per_second": 174.635,
+      "eval_steps_per_second": 6.35,
+      "step": 782
+    },
+    {
+      "epoch": 34.35,
+      "learning_rate": 7.85024154589372e-06,
+      "loss": 0.3019,
+      "step": 790
+    },
+    {
+      "epoch": 34.78,
+      "learning_rate": 7.246376811594203e-06,
+      "loss": 0.3144,
+      "step": 800
+    },
+    {
+      "epoch": 35.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.8189137578010559,
+      "eval_runtime": 0.6467,
+      "eval_samples_per_second": 170.106,
+      "eval_steps_per_second": 6.186,
+      "step": 805
+    },
+    {
+      "epoch": 35.22,
+      "learning_rate": 6.642512077294687e-06,
+      "loss": 0.333,
+      "step": 810
+    },
+    {
+      "epoch": 35.65,
+      "learning_rate": 6.038647342995169e-06,
+      "loss": 0.3452,
+      "step": 820
+    },
+    {
+      "epoch": 36.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.8377164006233215,
+      "eval_runtime": 0.6036,
+      "eval_samples_per_second": 182.227,
+      "eval_steps_per_second": 6.626,
+      "step": 828
+    },
+    {
+      "epoch": 36.09,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.2989,
+      "step": 830
+    },
+    {
+      "epoch": 36.52,
+      "learning_rate": 4.830917874396135e-06,
+      "loss": 0.2819,
+      "step": 840
+    },
+    {
+      "epoch": 36.96,
+      "learning_rate": 4.227053140096619e-06,
+      "loss": 0.3263,
+      "step": 850
+    },
+    {
+      "epoch": 37.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.8204471468925476,
+      "eval_runtime": 0.6006,
+      "eval_samples_per_second": 183.137,
+      "eval_steps_per_second": 6.66,
+      "step": 851
+    },
+    {
+      "epoch": 37.39,
+      "learning_rate": 3.6231884057971017e-06,
+      "loss": 0.3016,
+      "step": 860
+    },
+    {
+      "epoch": 37.83,
+      "learning_rate": 3.0193236714975845e-06,
+      "loss": 0.2939,
+      "step": 870
+    },
+    {
+      "epoch": 38.0,
+      "eval_accuracy": 0.7909090909090909,
+      "eval_loss": 0.810295581817627,
+      "eval_runtime": 0.6091,
+      "eval_samples_per_second": 180.583,
+      "eval_steps_per_second": 6.567,
+      "step": 874
+    },
+    {
+      "epoch": 38.26,
+      "learning_rate": 2.4154589371980677e-06,
+      "loss": 0.2872,
+      "step": 880
+    },
+    {
+      "epoch": 38.7,
+      "learning_rate": 1.8115942028985508e-06,
+      "loss": 0.3152,
+      "step": 890
+    },
+    {
+      "epoch": 39.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.8183740973472595,
+      "eval_runtime": 0.6091,
+      "eval_samples_per_second": 180.583,
+      "eval_steps_per_second": 6.567,
+      "step": 897
+    },
+    {
+      "epoch": 39.13,
+      "learning_rate": 1.2077294685990338e-06,
+      "loss": 0.3059,
+      "step": 900
+    },
+    {
+      "epoch": 39.57,
+      "learning_rate": 6.038647342995169e-07,
+      "loss": 0.3041,
+      "step": 910
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 0.0,
+      "loss": 0.2787,
+      "step": 920
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy": 0.7818181818181819,
+      "eval_loss": 0.8240975141525269,
+      "eval_runtime": 0.6032,
+      "eval_samples_per_second": 182.376,
+      "eval_steps_per_second": 6.632,
+      "step": 920
+    },
+    {
+      "epoch": 40.0,
+      "step": 920,
+      "total_flos": 3.825055592868741e+18,
+      "train_loss": 0.5426292188789533,
+      "train_runtime": 1410.8495,
+      "train_samples_per_second": 83.326,
+      "train_steps_per_second": 0.652
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 920,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 3.825055592868741e+18,
+  "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:b782ec53752d361856b7ec65955590b0c23d3b67232bb52a728031383b2985d8
+size 4792