End of training

README.md

@@ -0,0 +1,116 @@
+---
+base_model: MBZUAI/swiftformer-xs
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: SF-RHS-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: 0.822429906542056
+---
+
+<!-- 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. -->
+
+# SF-RHS-DA
+
+This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5233
+- Accuracy: 0.8224
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.693         | 0.99  | 35   | 0.6927          | 0.6822   |
+| 0.6919        | 2.0   | 71   | 0.6910          | 0.6916   |
+| 0.6872        | 2.99  | 106  | 0.6821          | 0.6822   |
+| 0.6613        | 4.0   | 142  | 0.6552          | 0.6542   |
+| 0.6196        | 4.99  | 177  | 0.6403          | 0.6168   |
+| 0.5695        | 6.0   | 213  | 0.6128          | 0.6449   |
+| 0.5436        | 6.99  | 248  | 0.6765          | 0.5701   |
+| 0.4836        | 8.0   | 284  | 0.6075          | 0.6542   |
+| 0.4902        | 8.99  | 319  | 0.5788          | 0.6355   |
+| 0.4759        | 10.0  | 355  | 0.5284          | 0.7196   |
+| 0.4746        | 10.99 | 390  | 0.5532          | 0.6822   |
+| 0.4067        | 12.0  | 426  | 0.5356          | 0.7383   |
+| 0.4138        | 12.99 | 461  | 0.5042          | 0.7477   |
+| 0.3752        | 14.0  | 497  | 0.5063          | 0.7383   |
+| 0.4158        | 14.99 | 532  | 0.4952          | 0.7570   |
+| 0.3646        | 16.0  | 568  | 0.5440          | 0.7383   |
+| 0.3644        | 16.99 | 603  | 0.5146          | 0.7757   |
+| 0.3411        | 18.0  | 639  | 0.5208          | 0.7757   |
+| 0.3052        | 18.99 | 674  | 0.5785          | 0.7383   |
+| 0.3398        | 20.0  | 710  | 0.5366          | 0.7383   |
+| 0.3103        | 20.99 | 745  | 0.5751          | 0.7290   |
+| 0.3168        | 22.0  | 781  | 0.5194          | 0.7664   |
+| 0.2927        | 22.99 | 816  | 0.5008          | 0.7944   |
+| 0.2874        | 24.0  | 852  | 0.5216          | 0.7944   |
+| 0.3021        | 24.99 | 887  | 0.5695          | 0.7570   |
+| 0.2978        | 26.0  | 923  | 0.5643          | 0.7570   |
+| 0.2743        | 26.99 | 958  | 0.5767          | 0.7570   |
+| 0.2753        | 28.0  | 994  | 0.5125          | 0.7664   |
+| 0.2773        | 28.99 | 1029 | 0.5246          | 0.7664   |
+| 0.2775        | 30.0  | 1065 | 0.5473          | 0.7850   |
+| 0.268         | 30.99 | 1100 | 0.5286          | 0.7664   |
+| 0.2586        | 32.0  | 1136 | 0.5233          | 0.7850   |
+| 0.2458        | 32.99 | 1171 | 0.5451          | 0.7757   |
+| 0.2524        | 34.0  | 1207 | 0.5268          | 0.7850   |
+| 0.2438        | 34.99 | 1242 | 0.5228          | 0.7757   |
+| 0.2429        | 36.0  | 1278 | 0.5391          | 0.7664   |
+| 0.2689        | 36.99 | 1313 | 0.5237          | 0.7850   |
+| 0.2362        | 38.0  | 1349 | 0.5561          | 0.7664   |
+| 0.2656        | 38.99 | 1384 | 0.5233          | 0.8224   |
+| 0.264         | 39.44 | 1400 | 0.5112          | 0.8037   |
+
+
+### 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": 39.44,
+    "eval_accuracy": 0.822429906542056,
+    "eval_loss": 0.5233157277107239,
+    "eval_runtime": 3.2558,
+    "eval_samples_per_second": 32.865,
+    "eval_steps_per_second": 2.15,
+    "train_loss": 0.38540612884930203,
+    "train_runtime": 1009.3205,
+    "train_samples_per_second": 89.486,
+    "train_steps_per_second": 1.387
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "MBZUAI/swiftformer-xs",
+  "architectures": [
+    "SwiftFormerForImageClassification"
+  ],
+  "batch_norm_eps": 1e-05,
+  "depths": [
+    3,
+    3,
+    6,
+    4
+  ],
+  "down_pad": 1,
+  "down_patch_size": 3,
+  "down_stride": 2,
+  "downsamples": [
+    true,
+    true,
+    true,
+    true
+  ],
+  "drop_path_rate": 0.0,
+  "embed_dims": [
+    48,
+    56,
+    112,
+    220
+  ],
+  "hidden_act": "gelu",
+  "id2label": {
+    "0": "HR",
+    "1": "No HR"
+  },
+  "label2id": {
+    "HR": 0,
+    "No HR": 1
+  },
+  "layer_scale_init_value": 1e-05,
+  "mlp_ratio": 4,
+  "model_type": "swiftformer",
+  "num_channels": 3,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_layer_scale": true
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 39.44,
+    "eval_accuracy": 0.822429906542056,
+    "eval_loss": 0.5233157277107239,
+    "eval_runtime": 3.2558,
+    "eval_samples_per_second": 32.865,
+    "eval_steps_per_second": 2.15
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224e7b3e7abdefa605d22d4e16b31b8fd73cde8d299cc2a0dec2b65e49d9a7da
+size 12200096

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": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Dec04_10-53-43_DESKTOP-SKBE9FB/events.out.tfevents.1733331224.DESKTOP-SKBE9FB.18260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0048968b2e3fb5fc97279289c7d040b10fdc3b0e0651e0621fd324c221e30f
+size 5512

runs/Dec04_10-55-17_DESKTOP-SKBE9FB/events.out.tfevents.1733331318.DESKTOP-SKBE9FB.13376.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeddd3d0f55c4395d1be8dbb26c9f55c98dcb0bdea941c97c59e27f05e792f2c
+size 9606

runs/Dec04_10-58-21_DESKTOP-SKBE9FB/events.out.tfevents.1733331502.DESKTOP-SKBE9FB.928.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cabd8d63f09561292f1c75ea040fc134618e5dbbb98b96e9f18d4eaf6d7079d9
+size 5358

runs/Dec04_10-59-46_DESKTOP-SKBE9FB/events.out.tfevents.1733331587.DESKTOP-SKBE9FB.484.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf37de7eab1b6cd87923f3eea6b9d1b4b40cf8b1bced0ea0e74a3a07f7470683
+size 5513

runs/Dec04_11-01-18_DESKTOP-SKBE9FB/events.out.tfevents.1733331679.DESKTOP-SKBE9FB.4544.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e70a08265e862ec8784ecd70fcec98f79a85a0d7c4b6768d83f40feb7ba40a
+size 7382

runs/Dec04_11-03-19_DESKTOP-SKBE9FB/events.out.tfevents.1733331800.DESKTOP-SKBE9FB.18832.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ffb222e04fa7b78a4d17b3972a454bf886ee30296873389de70a94ea3b5585
+size 5667

runs/Dec04_11-04-32_DESKTOP-SKBE9FB/events.out.tfevents.1733331873.DESKTOP-SKBE9FB.19164.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aad82008a779a9de12cb61b7d6e517d8fe777cb2c034fc41513d153802432de
+size 10078

runs/Dec04_11-07-47_DESKTOP-SKBE9FB/events.out.tfevents.1733332069.DESKTOP-SKBE9FB.18696.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39608675118410950227a1473d58f4130d1ade537169f5e9ada2a303aaf73c0
+size 39624

runs/Dec04_11-07-47_DESKTOP-SKBE9FB/events.out.tfevents.1733333081.DESKTOP-SKBE9FB.18696.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad4c871b07559f6f5d7ba946fd6ad13b7abc3b18668a1f6fa9a654946326f5b
+size 411

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 39.44,
+    "train_loss": 0.38540612884930203,
+    "train_runtime": 1009.3205,
+    "train_samples_per_second": 89.486,
+    "train_steps_per_second": 1.387
+}

trainer_state.json

@@ -0,0 +1,1230 @@
+{
+  "best_metric": 0.822429906542056,
+  "best_model_checkpoint": "SF-RHS-DA\\checkpoint-1384",
+  "epoch": 39.436619718309856,
+  "eval_steps": 500,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.6931,
+      "step": 10
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.6931,
+      "step": 20
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 6.428571428571429e-06,
+      "loss": 0.693,
+      "step": 30
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.6822429906542056,
+      "eval_loss": 0.6927286386489868,
+      "eval_runtime": 2.3546,
+      "eval_samples_per_second": 45.444,
+      "eval_steps_per_second": 2.973,
+      "step": 35
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.6929,
+      "step": 40
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.6927,
+      "step": 50
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.6925,
+      "step": 60
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.5e-05,
+      "loss": 0.6919,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6915887850467289,
+      "eval_loss": 0.6909971237182617,
+      "eval_runtime": 2.6496,
+      "eval_samples_per_second": 40.383,
+      "eval_steps_per_second": 2.642,
+      "step": 71
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.6912,
+      "step": 80
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 0.6896,
+      "step": 90
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.6872,
+      "step": 100
+    },
+    {
+      "epoch": 2.99,
+      "eval_accuracy": 0.6822429906542056,
+      "eval_loss": 0.6820780634880066,
+      "eval_runtime": 2.8722,
+      "eval_samples_per_second": 37.254,
+      "eval_steps_per_second": 2.437,
+      "step": 106
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 2.357142857142857e-05,
+      "loss": 0.6841,
+      "step": 110
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 0.6761,
+      "step": 120
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 2.7857142857142858e-05,
+      "loss": 0.6671,
+      "step": 130
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 3e-05,
+      "loss": 0.6613,
+      "step": 140
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6542056074766355,
+      "eval_loss": 0.6552135348320007,
+      "eval_runtime": 2.5956,
+      "eval_samples_per_second": 41.223,
+      "eval_steps_per_second": 2.697,
+      "step": 142
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 2.9761904761904762e-05,
+      "loss": 0.6416,
+      "step": 150
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 2.9523809523809523e-05,
+      "loss": 0.6301,
+      "step": 160
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 2.9285714285714284e-05,
+      "loss": 0.6196,
+      "step": 170
+    },
+    {
+      "epoch": 4.99,
+      "eval_accuracy": 0.616822429906542,
+      "eval_loss": 0.6403455138206482,
+      "eval_runtime": 2.3884,
+      "eval_samples_per_second": 44.801,
+      "eval_steps_per_second": 2.931,
+      "step": 177
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 2.904761904761905e-05,
+      "loss": 0.6023,
+      "step": 180
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 2.880952380952381e-05,
+      "loss": 0.5858,
+      "step": 190
+    },
+    {
+      "epoch": 5.63,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.5762,
+      "step": 200
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 2.8333333333333332e-05,
+      "loss": 0.5695,
+      "step": 210
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6448598130841121,
+      "eval_loss": 0.612833559513092,
+      "eval_runtime": 2.4301,
+      "eval_samples_per_second": 44.032,
+      "eval_steps_per_second": 2.881,
+      "step": 213
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 2.8095238095238096e-05,
+      "loss": 0.5664,
+      "step": 220
+    },
+    {
+      "epoch": 6.48,
+      "learning_rate": 2.7857142857142858e-05,
+      "loss": 0.5482,
+      "step": 230
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 2.761904761904762e-05,
+      "loss": 0.5436,
+      "step": 240
+    },
+    {
+      "epoch": 6.99,
+      "eval_accuracy": 0.5700934579439252,
+      "eval_loss": 0.6765128374099731,
+      "eval_runtime": 2.4356,
+      "eval_samples_per_second": 43.932,
+      "eval_steps_per_second": 2.874,
+      "step": 248
+    },
+    {
+      "epoch": 7.04,
+      "learning_rate": 2.738095238095238e-05,
+      "loss": 0.5434,
+      "step": 250
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 2.7142857142857144e-05,
+      "loss": 0.5175,
+      "step": 260
+    },
+    {
+      "epoch": 7.61,
+      "learning_rate": 2.6904761904761905e-05,
+      "loss": 0.5149,
+      "step": 270
+    },
+    {
+      "epoch": 7.89,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.4836,
+      "step": 280
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6542056074766355,
+      "eval_loss": 0.6075218319892883,
+      "eval_runtime": 2.3996,
+      "eval_samples_per_second": 44.591,
+      "eval_steps_per_second": 2.917,
+      "step": 284
+    },
+    {
+      "epoch": 8.17,
+      "learning_rate": 2.6428571428571428e-05,
+      "loss": 0.4856,
+      "step": 290
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 2.6190476190476192e-05,
+      "loss": 0.5027,
+      "step": 300
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 2.5952380952380953e-05,
+      "loss": 0.4902,
+      "step": 310
+    },
+    {
+      "epoch": 8.99,
+      "eval_accuracy": 0.6355140186915887,
+      "eval_loss": 0.578782856464386,
+      "eval_runtime": 2.6977,
+      "eval_samples_per_second": 39.663,
+      "eval_steps_per_second": 2.595,
+      "step": 319
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 0.5014,
+      "step": 320
+    },
+    {
+      "epoch": 9.3,
+      "learning_rate": 2.5476190476190476e-05,
+      "loss": 0.4682,
+      "step": 330
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 2.523809523809524e-05,
+      "loss": 0.4744,
+      "step": 340
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4759,
+      "step": 350
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.719626168224299,
+      "eval_loss": 0.5284451842308044,
+      "eval_runtime": 2.3275,
+      "eval_samples_per_second": 45.971,
+      "eval_steps_per_second": 3.007,
+      "step": 355
+    },
+    {
+      "epoch": 10.14,
+      "learning_rate": 2.4761904761904762e-05,
+      "loss": 0.5062,
+      "step": 360
+    },
+    {
+      "epoch": 10.42,
+      "learning_rate": 2.4523809523809523e-05,
+      "loss": 0.4543,
+      "step": 370
+    },
+    {
+      "epoch": 10.7,
+      "learning_rate": 2.4285714285714288e-05,
+      "loss": 0.463,
+      "step": 380
+    },
+    {
+      "epoch": 10.99,
+      "learning_rate": 2.404761904761905e-05,
+      "loss": 0.4746,
+      "step": 390
+    },
+    {
+      "epoch": 10.99,
+      "eval_accuracy": 0.6822429906542056,
+      "eval_loss": 0.5532112121582031,
+      "eval_runtime": 2.302,
+      "eval_samples_per_second": 46.48,
+      "eval_steps_per_second": 3.041,
+      "step": 390
+    },
+    {
+      "epoch": 11.27,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.4488,
+      "step": 400
+    },
+    {
+      "epoch": 11.55,
+      "learning_rate": 2.357142857142857e-05,
+      "loss": 0.4454,
+      "step": 410
+    },
+    {
+      "epoch": 11.83,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.4067,
+      "step": 420
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.7383177570093458,
+      "eval_loss": 0.5355571508407593,
+      "eval_runtime": 2.2815,
+      "eval_samples_per_second": 46.898,
+      "eval_steps_per_second": 3.068,
+      "step": 426
+    },
+    {
+      "epoch": 12.11,
+      "learning_rate": 2.3095238095238097e-05,
+      "loss": 0.4181,
+      "step": 430
+    },
+    {
+      "epoch": 12.39,
+      "learning_rate": 2.2857142857142858e-05,
+      "loss": 0.4448,
+      "step": 440
+    },
+    {
+      "epoch": 12.68,
+      "learning_rate": 2.261904761904762e-05,
+      "loss": 0.4621,
+      "step": 450
+    },
+    {
+      "epoch": 12.96,
+      "learning_rate": 2.238095238095238e-05,
+      "loss": 0.4138,
+      "step": 460
+    },
+    {
+      "epoch": 12.99,
+      "eval_accuracy": 0.7476635514018691,
+      "eval_loss": 0.5042079091072083,
+      "eval_runtime": 2.239,
+      "eval_samples_per_second": 47.789,
+      "eval_steps_per_second": 3.126,
+      "step": 461
+    },
+    {
+      "epoch": 13.24,
+      "learning_rate": 2.2142857142857145e-05,
+      "loss": 0.4153,
+      "step": 470
+    },
+    {
+      "epoch": 13.52,
+      "learning_rate": 2.1904761904761903e-05,
+      "loss": 0.3879,
+      "step": 480
+    },
+    {
+      "epoch": 13.8,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 0.3752,
+      "step": 490
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.7383177570093458,
+      "eval_loss": 0.5062668919563293,
+      "eval_runtime": 2.265,
+      "eval_samples_per_second": 47.24,
+      "eval_steps_per_second": 3.09,
+      "step": 497
+    },
+    {
+      "epoch": 14.08,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.4201,
+      "step": 500
+    },
+    {
+      "epoch": 14.37,
+      "learning_rate": 2.1190476190476193e-05,
+      "loss": 0.3522,
+      "step": 510
+    },
+    {
+      "epoch": 14.65,
+      "learning_rate": 2.095238095238095e-05,
+      "loss": 0.3762,
+      "step": 520
+    },
+    {
+      "epoch": 14.93,
+      "learning_rate": 2.0714285714285715e-05,
+      "loss": 0.4158,
+      "step": 530
+    },
+    {
+      "epoch": 14.99,
+      "eval_accuracy": 0.7570093457943925,
+      "eval_loss": 0.49523478746414185,
+      "eval_runtime": 2.3011,
+      "eval_samples_per_second": 46.5,
+      "eval_steps_per_second": 3.042,
+      "step": 532
+    },
+    {
+      "epoch": 15.21,
+      "learning_rate": 2.0476190476190476e-05,
+      "loss": 0.3994,
+      "step": 540
+    },
+    {
+      "epoch": 15.49,
+      "learning_rate": 2.023809523809524e-05,
+      "loss": 0.3707,
+      "step": 550
+    },
+    {
+      "epoch": 15.77,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 0.3646,
+      "step": 560
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.7383177570093458,
+      "eval_loss": 0.5439864993095398,
+      "eval_runtime": 2.286,
+      "eval_samples_per_second": 46.806,
+      "eval_steps_per_second": 3.062,
+      "step": 568
+    },
+    {
+      "epoch": 16.06,
+      "learning_rate": 1.9761904761904763e-05,
+      "loss": 0.3574,
+      "step": 570
+    },
+    {
+      "epoch": 16.34,
+      "learning_rate": 1.9523809523809524e-05,
+      "loss": 0.3817,
+      "step": 580
+    },
+    {
+      "epoch": 16.62,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 0.3769,
+      "step": 590
+    },
+    {
+      "epoch": 16.9,
+      "learning_rate": 1.9047619047619046e-05,
+      "loss": 0.3644,
+      "step": 600
+    },
+    {
+      "epoch": 16.99,
+      "eval_accuracy": 0.7757009345794392,
+      "eval_loss": 0.5146493911743164,
+      "eval_runtime": 2.4036,
+      "eval_samples_per_second": 44.517,
+      "eval_steps_per_second": 2.912,
+      "step": 603
+    },
+    {
+      "epoch": 17.18,
+      "learning_rate": 1.880952380952381e-05,
+      "loss": 0.3914,
+      "step": 610
+    },
+    {
+      "epoch": 17.46,
+      "learning_rate": 1.8571428571428572e-05,
+      "loss": 0.3649,
+      "step": 620
+    },
+    {
+      "epoch": 17.75,
+      "learning_rate": 1.8333333333333336e-05,
+      "loss": 0.3411,
+      "step": 630
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.7757009345794392,
+      "eval_loss": 0.520774245262146,
+      "eval_runtime": 2.3841,
+      "eval_samples_per_second": 44.881,
+      "eval_steps_per_second": 2.936,
+      "step": 639
+    },
+    {
+      "epoch": 18.03,
+      "learning_rate": 1.8095238095238094e-05,
+      "loss": 0.364,
+      "step": 640
+    },
+    {
+      "epoch": 18.31,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 0.3429,
+      "step": 650
+    },
+    {
+      "epoch": 18.59,
+      "learning_rate": 1.761904761904762e-05,
+      "loss": 0.3262,
+      "step": 660
+    },
+    {
+      "epoch": 18.87,
+      "learning_rate": 1.7380952380952384e-05,
+      "loss": 0.3052,
+      "step": 670
+    },
+    {
+      "epoch": 18.99,
+      "eval_accuracy": 0.7383177570093458,
+      "eval_loss": 0.5784975290298462,
+      "eval_runtime": 2.3582,
+      "eval_samples_per_second": 45.374,
+      "eval_steps_per_second": 2.968,
+      "step": 674
+    },
+    {
+      "epoch": 19.15,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.33,
+      "step": 680
+    },
+    {
+      "epoch": 19.44,
+      "learning_rate": 1.6904761904761906e-05,
+      "loss": 0.3185,
+      "step": 690
+    },
+    {
+      "epoch": 19.72,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.3355,
+      "step": 700
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 1.6428571428571432e-05,
+      "loss": 0.3398,
+      "step": 710
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.7383177570093458,
+      "eval_loss": 0.5366288423538208,
+      "eval_runtime": 2.243,
+      "eval_samples_per_second": 47.704,
+      "eval_steps_per_second": 3.121,
+      "step": 710
+    },
+    {
+      "epoch": 20.28,
+      "learning_rate": 1.619047619047619e-05,
+      "loss": 0.3025,
+      "step": 720
+    },
+    {
+      "epoch": 20.56,
+      "learning_rate": 1.5952380952380954e-05,
+      "loss": 0.3167,
+      "step": 730
+    },
+    {
+      "epoch": 20.85,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 0.3103,
+      "step": 740
+    },
+    {
+      "epoch": 20.99,
+      "eval_accuracy": 0.7289719626168224,
+      "eval_loss": 0.5751203298568726,
+      "eval_runtime": 2.5146,
+      "eval_samples_per_second": 42.551,
+      "eval_steps_per_second": 2.784,
+      "step": 745
+    },
+    {
+      "epoch": 21.13,
+      "learning_rate": 1.547619047619048e-05,
+      "loss": 0.2846,
+      "step": 750
+    },
+    {
+      "epoch": 21.41,
+      "learning_rate": 1.5238095238095238e-05,
+      "loss": 0.3186,
+      "step": 760
+    },
+    {
+      "epoch": 21.69,
+      "learning_rate": 1.5e-05,
+      "loss": 0.2833,
+      "step": 770
+    },
+    {
+      "epoch": 21.97,
+      "learning_rate": 1.4761904761904761e-05,
+      "loss": 0.3168,
+      "step": 780
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.7663551401869159,
+      "eval_loss": 0.5194119811058044,
+      "eval_runtime": 2.4472,
+      "eval_samples_per_second": 43.723,
+      "eval_steps_per_second": 2.86,
+      "step": 781
+    },
+    {
+      "epoch": 22.25,
+      "learning_rate": 1.4523809523809524e-05,
+      "loss": 0.3255,
+      "step": 790
+    },
+    {
+      "epoch": 22.54,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.3148,
+      "step": 800
+    },
+    {
+      "epoch": 22.82,
+      "learning_rate": 1.4047619047619048e-05,
+      "loss": 0.2927,
+      "step": 810
+    },
+    {
+      "epoch": 22.99,
+      "eval_accuracy": 0.794392523364486,
+      "eval_loss": 0.5008327960968018,
+      "eval_runtime": 2.8195,
+      "eval_samples_per_second": 37.949,
+      "eval_steps_per_second": 2.483,
+      "step": 816
+    },
+    {
+      "epoch": 23.1,
+      "learning_rate": 1.380952380952381e-05,
+      "loss": 0.3163,
+      "step": 820
+    },
+    {
+      "epoch": 23.38,
+      "learning_rate": 1.3571428571428572e-05,
+      "loss": 0.2708,
+      "step": 830
+    },
+    {
+      "epoch": 23.66,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.2927,
+      "step": 840
+    },
+    {
+      "epoch": 23.94,
+      "learning_rate": 1.3095238095238096e-05,
+      "loss": 0.2874,
+      "step": 850
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.794392523364486,
+      "eval_loss": 0.5215777158737183,
+      "eval_runtime": 2.3666,
+      "eval_samples_per_second": 45.213,
+      "eval_steps_per_second": 2.958,
+      "step": 852
+    },
+    {
+      "epoch": 24.23,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.3009,
+      "step": 860
+    },
+    {
+      "epoch": 24.51,
+      "learning_rate": 1.261904761904762e-05,
+      "loss": 0.3082,
+      "step": 870
+    },
+    {
+      "epoch": 24.79,
+      "learning_rate": 1.2380952380952381e-05,
+      "loss": 0.3021,
+      "step": 880
+    },
+    {
+      "epoch": 24.99,
+      "eval_accuracy": 0.7570093457943925,
+      "eval_loss": 0.5695382952690125,
+      "eval_runtime": 2.2945,
+      "eval_samples_per_second": 46.632,
+      "eval_steps_per_second": 3.051,
+      "step": 887
+    },
+    {
+      "epoch": 25.07,
+      "learning_rate": 1.2142857142857144e-05,
+      "loss": 0.2771,
+      "step": 890
+    },
+    {
+      "epoch": 25.35,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.2882,
+      "step": 900
+    },
+    {
+      "epoch": 25.63,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.3067,
+      "step": 910
+    },
+    {
+      "epoch": 25.92,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.2978,
+      "step": 920
+    },
+    {
+      "epoch": 26.0,
+      "eval_accuracy": 0.7570093457943925,
+      "eval_loss": 0.5642871856689453,
+      "eval_runtime": 2.3556,
+      "eval_samples_per_second": 45.425,
+      "eval_steps_per_second": 2.972,
+      "step": 923
+    },
+    {
+      "epoch": 26.2,
+      "learning_rate": 1.119047619047619e-05,
+      "loss": 0.2787,
+      "step": 930
+    },
+    {
+      "epoch": 26.48,
+      "learning_rate": 1.0952380952380951e-05,
+      "loss": 0.2857,
+      "step": 940
+    },
+    {
+      "epoch": 26.76,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.2743,
+      "step": 950
+    },
+    {
+      "epoch": 26.99,
+      "eval_accuracy": 0.7570093457943925,
+      "eval_loss": 0.5767267346382141,
+      "eval_runtime": 2.7372,
+      "eval_samples_per_second": 39.092,
+      "eval_steps_per_second": 2.557,
+      "step": 958
+    },
+    {
+      "epoch": 27.04,
+      "learning_rate": 1.0476190476190475e-05,
+      "loss": 0.2486,
+      "step": 960
+    },
+    {
+      "epoch": 27.32,
+      "learning_rate": 1.0238095238095238e-05,
+      "loss": 0.2884,
+      "step": 970
+    },
+    {
+      "epoch": 27.61,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 0.308,
+      "step": 980
+    },
+    {
+      "epoch": 27.89,
+      "learning_rate": 9.761904761904762e-06,
+      "loss": 0.2753,
+      "step": 990
+    },
+    {
+      "epoch": 28.0,
+      "eval_accuracy": 0.7663551401869159,
+      "eval_loss": 0.5124983787536621,
+      "eval_runtime": 3.3973,
+      "eval_samples_per_second": 31.496,
+      "eval_steps_per_second": 2.06,
+      "step": 994
+    },
+    {
+      "epoch": 28.17,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 0.2838,
+      "step": 1000
+    },
+    {
+      "epoch": 28.45,
+      "learning_rate": 9.285714285714286e-06,
+      "loss": 0.2619,
+      "step": 1010
+    },
+    {
+      "epoch": 28.73,
+      "learning_rate": 9.047619047619047e-06,
+      "loss": 0.2773,
+      "step": 1020
+    },
+    {
+      "epoch": 28.99,
+      "eval_accuracy": 0.7663551401869159,
+      "eval_loss": 0.5245658159255981,
+      "eval_runtime": 2.8221,
+      "eval_samples_per_second": 37.914,
+      "eval_steps_per_second": 2.48,
+      "step": 1029
+    },
+    {
+      "epoch": 29.01,
+      "learning_rate": 8.80952380952381e-06,
+      "loss": 0.2854,
+      "step": 1030
+    },
+    {
+      "epoch": 29.3,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.256,
+      "step": 1040
+    },
+    {
+      "epoch": 29.58,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.2634,
+      "step": 1050
+    },
+    {
+      "epoch": 29.86,
+      "learning_rate": 8.095238095238095e-06,
+      "loss": 0.2775,
+      "step": 1060
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.7850467289719626,
+      "eval_loss": 0.5473499298095703,
+      "eval_runtime": 2.4506,
+      "eval_samples_per_second": 43.664,
+      "eval_steps_per_second": 2.856,
+      "step": 1065
+    },
+    {
+      "epoch": 30.14,
+      "learning_rate": 7.857142857142858e-06,
+      "loss": 0.294,
+      "step": 1070
+    },
+    {
+      "epoch": 30.42,
+      "learning_rate": 7.619047619047619e-06,
+      "loss": 0.2702,
+      "step": 1080
+    },
+    {
+      "epoch": 30.7,
+      "learning_rate": 7.380952380952381e-06,
+      "loss": 0.2726,
+      "step": 1090
+    },
+    {
+      "epoch": 30.99,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.268,
+      "step": 1100
+    },
+    {
+      "epoch": 30.99,
+      "eval_accuracy": 0.7663551401869159,
+      "eval_loss": 0.5285843014717102,
+      "eval_runtime": 2.4786,
+      "eval_samples_per_second": 43.17,
+      "eval_steps_per_second": 2.824,
+      "step": 1100
+    },
+    {
+      "epoch": 31.27,
+      "learning_rate": 6.904761904761905e-06,
+      "loss": 0.2843,
+      "step": 1110
+    },
+    {
+      "epoch": 31.55,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.2584,
+      "step": 1120
+    },
+    {
+      "epoch": 31.83,
+      "learning_rate": 6.428571428571429e-06,
+      "loss": 0.2586,
+      "step": 1130
+    },
+    {
+      "epoch": 32.0,
+      "eval_accuracy": 0.7850467289719626,
+      "eval_loss": 0.5232648849487305,
+      "eval_runtime": 2.341,
+      "eval_samples_per_second": 45.706,
+      "eval_steps_per_second": 2.99,
+      "step": 1136
+    },
+    {
+      "epoch": 32.11,
+      "learning_rate": 6.190476190476191e-06,
+      "loss": 0.2735,
+      "step": 1140
+    },
+    {
+      "epoch": 32.39,
+      "learning_rate": 5.9523809523809525e-06,
+      "loss": 0.2499,
+      "step": 1150
+    },
+    {
+      "epoch": 32.68,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.2677,
+      "step": 1160
+    },
+    {
+      "epoch": 32.96,
+      "learning_rate": 5.476190476190476e-06,
+      "loss": 0.2458,
+      "step": 1170
+    },
+    {
+      "epoch": 32.99,
+      "eval_accuracy": 0.7757009345794392,
+      "eval_loss": 0.5451497435569763,
+      "eval_runtime": 2.6154,
+      "eval_samples_per_second": 40.912,
+      "eval_steps_per_second": 2.676,
+      "step": 1171
+    },
+    {
+      "epoch": 33.24,
+      "learning_rate": 5.238095238095238e-06,
+      "loss": 0.2611,
+      "step": 1180
+    },
+    {
+      "epoch": 33.52,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 0.2872,
+      "step": 1190
+    },
+    {
+      "epoch": 33.8,
+      "learning_rate": 4.7619047619047615e-06,
+      "loss": 0.2524,
+      "step": 1200
+    },
+    {
+      "epoch": 34.0,
+      "eval_accuracy": 0.7850467289719626,
+      "eval_loss": 0.5268486738204956,
+      "eval_runtime": 2.4496,
+      "eval_samples_per_second": 43.681,
+      "eval_steps_per_second": 2.858,
+      "step": 1207
+    },
+    {
+      "epoch": 34.08,
+      "learning_rate": 4.5238095238095235e-06,
+      "loss": 0.2762,
+      "step": 1210
+    },
+    {
+      "epoch": 34.37,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.2541,
+      "step": 1220
+    },
+    {
+      "epoch": 34.65,
+      "learning_rate": 4.0476190476190474e-06,
+      "loss": 0.2055,
+      "step": 1230
+    },
+    {
+      "epoch": 34.93,
+      "learning_rate": 3.8095238095238094e-06,
+      "loss": 0.2438,
+      "step": 1240
+    },
+    {
+      "epoch": 34.99,
+      "eval_accuracy": 0.7757009345794392,
+      "eval_loss": 0.5228263735771179,
+      "eval_runtime": 2.4381,
+      "eval_samples_per_second": 43.887,
+      "eval_steps_per_second": 2.871,
+      "step": 1242
+    },
+    {
+      "epoch": 35.21,
+      "learning_rate": 3.5714285714285714e-06,
+      "loss": 0.2296,
+      "step": 1250
+    },
+    {
+      "epoch": 35.49,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.2462,
+      "step": 1260
+    },
+    {
+      "epoch": 35.77,
+      "learning_rate": 3.0952380952380953e-06,
+      "loss": 0.2429,
+      "step": 1270
+    },
+    {
+      "epoch": 36.0,
+      "eval_accuracy": 0.7663551401869159,
+      "eval_loss": 0.5391428470611572,
+      "eval_runtime": 2.4246,
+      "eval_samples_per_second": 44.132,
+      "eval_steps_per_second": 2.887,
+      "step": 1278
+    },
+    {
+      "epoch": 36.06,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.267,
+      "step": 1280
+    },
+    {
+      "epoch": 36.34,
+      "learning_rate": 2.619047619047619e-06,
+      "loss": 0.2715,
+      "step": 1290
+    },
+    {
+      "epoch": 36.62,
+      "learning_rate": 2.3809523809523808e-06,
+      "loss": 0.2528,
+      "step": 1300
+    },
+    {
+      "epoch": 36.9,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.2689,
+      "step": 1310
+    },
+    {
+      "epoch": 36.99,
+      "eval_accuracy": 0.7850467289719626,
+      "eval_loss": 0.5236551761627197,
+      "eval_runtime": 2.5225,
+      "eval_samples_per_second": 42.419,
+      "eval_steps_per_second": 2.775,
+      "step": 1313
+    },
+    {
+      "epoch": 37.18,
+      "learning_rate": 1.9047619047619047e-06,
+      "loss": 0.2637,
+      "step": 1320
+    },
+    {
+      "epoch": 37.46,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.2367,
+      "step": 1330
+    },
+    {
+      "epoch": 37.75,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.2362,
+      "step": 1340
+    },
+    {
+      "epoch": 38.0,
+      "eval_accuracy": 0.7663551401869159,
+      "eval_loss": 0.5561335682868958,
+      "eval_runtime": 2.5586,
+      "eval_samples_per_second": 41.82,
+      "eval_steps_per_second": 2.736,
+      "step": 1349
+    },
+    {
+      "epoch": 38.03,
+      "learning_rate": 1.1904761904761904e-06,
+      "loss": 0.2685,
+      "step": 1350
+    },
+    {
+      "epoch": 38.31,
+      "learning_rate": 9.523809523809523e-07,
+      "loss": 0.2447,
+      "step": 1360
+    },
+    {
+      "epoch": 38.59,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 0.2492,
+      "step": 1370
+    },
+    {
+      "epoch": 38.87,
+      "learning_rate": 4.761904761904762e-07,
+      "loss": 0.2656,
+      "step": 1380
+    },
+    {
+      "epoch": 38.99,
+      "eval_accuracy": 0.822429906542056,
+      "eval_loss": 0.5233157277107239,
+      "eval_runtime": 2.4536,
+      "eval_samples_per_second": 43.61,
+      "eval_steps_per_second": 2.853,
+      "step": 1384
+    },
+    {
+      "epoch": 39.15,
+      "learning_rate": 2.380952380952381e-07,
+      "loss": 0.2456,
+      "step": 1390
+    },
+    {
+      "epoch": 39.44,
+      "learning_rate": 0.0,
+      "loss": 0.264,
+      "step": 1400
+    },
+    {
+      "epoch": 39.44,
+      "eval_accuracy": 0.8037383177570093,
+      "eval_loss": 0.5111537575721741,
+      "eval_runtime": 2.5592,
+      "eval_samples_per_second": 41.809,
+      "eval_steps_per_second": 2.735,
+      "step": 1400
+    },
+    {
+      "epoch": 39.44,
+      "step": 1400,
+      "total_flos": 2.4404643889687757e+17,
+      "train_loss": 0.38540612884930203,
+      "train_runtime": 1009.3205,
+      "train_samples_per_second": 89.486,
+      "train_steps_per_second": 1.387
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 2.4404643889687757e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f0413bbc6b9037d7693638399e2031fc442b604c9cb7e1aae9f2910778ba35
+size 4728