End of training

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: WinKawaks/vit-small-patch16-224
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: vit-small-patch16-224-finetuned-Cifar10
+  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. -->
+
+# vit-small-patch16-224-finetuned-Cifar10
+
+This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0460
+- Accuracy: 0.9866
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.3253        | 1.0   | 351  | 0.0657          | 0.9784   |
+| 0.266         | 2.0   | 703  | 0.0460          | 0.9866   |
+| 0.2298        | 2.99  | 1053 | 0.0418          | 0.9862   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.99,
+    "eval_accuracy": 0.9866,
+    "eval_loss": 0.046029962599277496,
+    "eval_runtime": 60.7502,
+    "eval_samples_per_second": 82.304,
+    "eval_steps_per_second": 2.584,
+    "total_flos": 2.636946768879747e+18,
+    "train_loss": 0.3514244137552955,
+    "train_runtime": 1744.8692,
+    "train_samples_per_second": 77.37,
+    "train_steps_per_second": 0.603
+}

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "WinKawaks/vit-small-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "airplane",
+    "1": "automobile",
+    "2": "bird",
+    "3": "cat",
+    "4": "deer",
+    "5": "dog",
+    "6": "frog",
+    "7": "horse",
+    "8": "ship",
+    "9": "truck"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "airplane": 0,
+    "automobile": 1,
+    "bird": 2,
+    "cat": 3,
+    "deer": 4,
+    "dog": 5,
+    "frog": 6,
+    "horse": 7,
+    "ship": 8,
+    "truck": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 6,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.99,
+    "eval_accuracy": 0.9866,
+    "eval_loss": 0.046029962599277496,
+    "eval_runtime": 60.7502,
+    "eval_samples_per_second": 82.304,
+    "eval_steps_per_second": 2.584
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cf75ca2281a0d5246f1dcf463ddd4efd4a1ab6a9d268529d14ce4190dcb6a2
+size 86700952

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Apr06_20-02-09_b854fac66b3a/events.out.tfevents.1712433774.b854fac66b3a.712.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd11fcafe665fa721ac030defaea08693b9b606b70b053b2862f6ca76b7cd6a
+size 28366

runs/Apr06_20-02-09_b854fac66b3a/events.out.tfevents.1712435663.b854fac66b3a.712.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e99f4d3ae833fa256fdf1bba76f7fe77beb74ecf8da75cb3c71d85eb0d826c
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.99,
+    "total_flos": 2.636946768879747e+18,
+    "train_loss": 0.3514244137552955,
+    "train_runtime": 1744.8692,
+    "train_samples_per_second": 77.37,
+    "train_steps_per_second": 0.603
+}

trainer_state.json

@@ -0,0 +1,792 @@
+{
+  "best_metric": 0.9866,
+  "best_model_checkpoint": "vit-small-patch16-224-finetuned-Cifar10/checkpoint-703",
+  "epoch": 2.9936034115138592,
+  "eval_steps": 500,
+  "global_step": 1053,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "grad_norm": 11.993635177612305,
+      "learning_rate": 4.716981132075472e-06,
+      "loss": 2.7466,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.214780807495117,
+      "learning_rate": 9.433962264150944e-06,
+      "loss": 2.4372,
+      "step": 20
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 8.453407287597656,
+      "learning_rate": 1.4150943396226415e-05,
+      "loss": 2.0196,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 7.144883155822754,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 1.5377,
+      "step": 40
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.839055061340332,
+      "learning_rate": 2.358490566037736e-05,
+      "loss": 0.9774,
+      "step": 50
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 5.836381912231445,
+      "learning_rate": 2.830188679245283e-05,
+      "loss": 0.6557,
+      "step": 60
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 7.173834323883057,
+      "learning_rate": 3.30188679245283e-05,
+      "loss": 0.5304,
+      "step": 70
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 5.7883830070495605,
+      "learning_rate": 3.7735849056603776e-05,
+      "loss": 0.4689,
+      "step": 80
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 7.019888401031494,
+      "learning_rate": 4.245283018867925e-05,
+      "loss": 0.4659,
+      "step": 90
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.123730182647705,
+      "learning_rate": 4.716981132075472e-05,
+      "loss": 0.4127,
+      "step": 100
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 6.988221645355225,
+      "learning_rate": 4.978880675818374e-05,
+      "loss": 0.4155,
+      "step": 110
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 6.683491230010986,
+      "learning_rate": 4.9260823653643085e-05,
+      "loss": 0.3546,
+      "step": 120
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 7.395442962646484,
+      "learning_rate": 4.8732840549102435e-05,
+      "loss": 0.3745,
+      "step": 130
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.838753700256348,
+      "learning_rate": 4.820485744456177e-05,
+      "loss": 0.3529,
+      "step": 140
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.989682674407959,
+      "learning_rate": 4.767687434002112e-05,
+      "loss": 0.3487,
+      "step": 150
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 6.224100589752197,
+      "learning_rate": 4.7148891235480466e-05,
+      "loss": 0.3452,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 6.418895721435547,
+      "learning_rate": 4.662090813093981e-05,
+      "loss": 0.3545,
+      "step": 170
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 5.342619895935059,
+      "learning_rate": 4.609292502639916e-05,
+      "loss": 0.3171,
+      "step": 180
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.573193550109863,
+      "learning_rate": 4.55649419218585e-05,
+      "loss": 0.3242,
+      "step": 190
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 5.019192218780518,
+      "learning_rate": 4.503695881731785e-05,
+      "loss": 0.3241,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.130370140075684,
+      "learning_rate": 4.45089757127772e-05,
+      "loss": 0.3316,
+      "step": 210
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 6.118399620056152,
+      "learning_rate": 4.398099260823654e-05,
+      "loss": 0.331,
+      "step": 220
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 4.279905796051025,
+      "learning_rate": 4.3453009503695884e-05,
+      "loss": 0.3276,
+      "step": 230
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.9065074920654297,
+      "learning_rate": 4.292502639915523e-05,
+      "loss": 0.2719,
+      "step": 240
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.098165988922119,
+      "learning_rate": 4.239704329461457e-05,
+      "loss": 0.3026,
+      "step": 250
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 5.796530723571777,
+      "learning_rate": 4.186906019007392e-05,
+      "loss": 0.2795,
+      "step": 260
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 5.165294647216797,
+      "learning_rate": 4.1341077085533265e-05,
+      "loss": 0.3337,
+      "step": 270
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.210253715515137,
+      "learning_rate": 4.081309398099261e-05,
+      "loss": 0.2845,
+      "step": 280
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 6.663649559020996,
+      "learning_rate": 4.028511087645195e-05,
+      "loss": 0.3021,
+      "step": 290
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 7.552988529205322,
+      "learning_rate": 3.97571277719113e-05,
+      "loss": 0.3157,
+      "step": 300
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.279345989227295,
+      "learning_rate": 3.9229144667370646e-05,
+      "loss": 0.2724,
+      "step": 310
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 6.712580680847168,
+      "learning_rate": 3.870116156282999e-05,
+      "loss": 0.3492,
+      "step": 320
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 5.240344524383545,
+      "learning_rate": 3.817317845828934e-05,
+      "loss": 0.2719,
+      "step": 330
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 6.162644386291504,
+      "learning_rate": 3.764519535374868e-05,
+      "loss": 0.2594,
+      "step": 340
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.918422222137451,
+      "learning_rate": 3.711721224920803e-05,
+      "loss": 0.3253,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9784,
+      "eval_loss": 0.06568869948387146,
+      "eval_runtime": 49.9126,
+      "eval_samples_per_second": 100.175,
+      "eval_steps_per_second": 3.145,
+      "step": 351
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 5.946422576904297,
+      "learning_rate": 3.658922914466738e-05,
+      "loss": 0.2393,
+      "step": 360
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 4.802185535430908,
+      "learning_rate": 3.6061246040126714e-05,
+      "loss": 0.3089,
+      "step": 370
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 6.8064351081848145,
+      "learning_rate": 3.5533262935586064e-05,
+      "loss": 0.3038,
+      "step": 380
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 4.575678825378418,
+      "learning_rate": 3.500527983104541e-05,
+      "loss": 0.267,
+      "step": 390
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.146677494049072,
+      "learning_rate": 3.447729672650475e-05,
+      "loss": 0.2544,
+      "step": 400
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 5.48955774307251,
+      "learning_rate": 3.3949313621964095e-05,
+      "loss": 0.2901,
+      "step": 410
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 5.2598490715026855,
+      "learning_rate": 3.3421330517423445e-05,
+      "loss": 0.2599,
+      "step": 420
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 3.1469264030456543,
+      "learning_rate": 3.289334741288279e-05,
+      "loss": 0.2696,
+      "step": 430
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 4.3553266525268555,
+      "learning_rate": 3.236536430834213e-05,
+      "loss": 0.2813,
+      "step": 440
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 5.741024017333984,
+      "learning_rate": 3.183738120380148e-05,
+      "loss": 0.2886,
+      "step": 450
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 5.031249046325684,
+      "learning_rate": 3.130939809926082e-05,
+      "loss": 0.2721,
+      "step": 460
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 4.464756488800049,
+      "learning_rate": 3.078141499472017e-05,
+      "loss": 0.2496,
+      "step": 470
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 3.4022979736328125,
+      "learning_rate": 3.0253431890179517e-05,
+      "loss": 0.245,
+      "step": 480
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 5.276814937591553,
+      "learning_rate": 2.972544878563886e-05,
+      "loss": 0.2651,
+      "step": 490
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.5680410861968994,
+      "learning_rate": 2.9197465681098207e-05,
+      "loss": 0.2351,
+      "step": 500
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 3.921807050704956,
+      "learning_rate": 2.8669482576557548e-05,
+      "loss": 0.2667,
+      "step": 510
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 3.4071061611175537,
+      "learning_rate": 2.8141499472016898e-05,
+      "loss": 0.252,
+      "step": 520
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 4.332042694091797,
+      "learning_rate": 2.7613516367476245e-05,
+      "loss": 0.2868,
+      "step": 530
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 4.950148105621338,
+      "learning_rate": 2.7085533262935585e-05,
+      "loss": 0.2966,
+      "step": 540
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 4.6252312660217285,
+      "learning_rate": 2.6557550158394935e-05,
+      "loss": 0.2718,
+      "step": 550
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 3.9921112060546875,
+      "learning_rate": 2.6029567053854276e-05,
+      "loss": 0.2457,
+      "step": 560
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.575648784637451,
+      "learning_rate": 2.5501583949313622e-05,
+      "loss": 0.2488,
+      "step": 570
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 5.220016002655029,
+      "learning_rate": 2.497360084477297e-05,
+      "loss": 0.2482,
+      "step": 580
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 4.158516883850098,
+      "learning_rate": 2.4445617740232313e-05,
+      "loss": 0.2519,
+      "step": 590
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 4.686926364898682,
+      "learning_rate": 2.391763463569166e-05,
+      "loss": 0.2796,
+      "step": 600
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 5.014163017272949,
+      "learning_rate": 2.3389651531151003e-05,
+      "loss": 0.2195,
+      "step": 610
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 5.498648643493652,
+      "learning_rate": 2.286166842661035e-05,
+      "loss": 0.2881,
+      "step": 620
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 5.010299205780029,
+      "learning_rate": 2.2333685322069694e-05,
+      "loss": 0.2537,
+      "step": 630
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 4.682175636291504,
+      "learning_rate": 2.180570221752904e-05,
+      "loss": 0.2691,
+      "step": 640
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.073044776916504,
+      "learning_rate": 2.1277719112988384e-05,
+      "loss": 0.2358,
+      "step": 650
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 5.119712829589844,
+      "learning_rate": 2.074973600844773e-05,
+      "loss": 0.2496,
+      "step": 660
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 4.570176124572754,
+      "learning_rate": 2.0221752903907075e-05,
+      "loss": 0.2327,
+      "step": 670
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 4.677672386169434,
+      "learning_rate": 1.9693769799366422e-05,
+      "loss": 0.2265,
+      "step": 680
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 4.625946521759033,
+      "learning_rate": 1.9165786694825765e-05,
+      "loss": 0.2248,
+      "step": 690
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 4.514760971069336,
+      "learning_rate": 1.863780359028511e-05,
+      "loss": 0.266,
+      "step": 700
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9866,
+      "eval_loss": 0.046029962599277496,
+      "eval_runtime": 49.803,
+      "eval_samples_per_second": 100.396,
+      "eval_steps_per_second": 3.152,
+      "step": 703
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 3.862548589706421,
+      "learning_rate": 1.810982048574446e-05,
+      "loss": 0.2284,
+      "step": 710
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 4.738348007202148,
+      "learning_rate": 1.7581837381203803e-05,
+      "loss": 0.2416,
+      "step": 720
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.671838760375977,
+      "learning_rate": 1.7053854276663146e-05,
+      "loss": 0.2409,
+      "step": 730
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.9875543117523193,
+      "learning_rate": 1.6525871172122493e-05,
+      "loss": 0.2188,
+      "step": 740
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 3.695639133453369,
+      "learning_rate": 1.5997888067581837e-05,
+      "loss": 0.2498,
+      "step": 750
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 3.4530131816864014,
+      "learning_rate": 1.5469904963041184e-05,
+      "loss": 0.2152,
+      "step": 760
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.31766414642334,
+      "learning_rate": 1.4941921858500529e-05,
+      "loss": 0.2374,
+      "step": 770
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.569504261016846,
+      "learning_rate": 1.4413938753959874e-05,
+      "loss": 0.2397,
+      "step": 780
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 3.1321048736572266,
+      "learning_rate": 1.388595564941922e-05,
+      "loss": 0.2367,
+      "step": 790
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 4.778504371643066,
+      "learning_rate": 1.3357972544878563e-05,
+      "loss": 0.1993,
+      "step": 800
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 4.513803482055664,
+      "learning_rate": 1.2829989440337912e-05,
+      "loss": 0.2197,
+      "step": 810
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 5.787839412689209,
+      "learning_rate": 1.2302006335797255e-05,
+      "loss": 0.2117,
+      "step": 820
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 4.725786209106445,
+      "learning_rate": 1.17740232312566e-05,
+      "loss": 0.2326,
+      "step": 830
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 4.849221706390381,
+      "learning_rate": 1.1246040126715946e-05,
+      "loss": 0.1853,
+      "step": 840
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 4.66175651550293,
+      "learning_rate": 1.0718057022175291e-05,
+      "loss": 0.2144,
+      "step": 850
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 3.1749322414398193,
+      "learning_rate": 1.0190073917634636e-05,
+      "loss": 0.2448,
+      "step": 860
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 5.343231678009033,
+      "learning_rate": 9.662090813093982e-06,
+      "loss": 0.1796,
+      "step": 870
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 4.883101463317871,
+      "learning_rate": 9.134107708553327e-06,
+      "loss": 0.1833,
+      "step": 880
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 4.559369087219238,
+      "learning_rate": 8.606124604012672e-06,
+      "loss": 0.2449,
+      "step": 890
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 6.445333480834961,
+      "learning_rate": 8.078141499472017e-06,
+      "loss": 0.2525,
+      "step": 900
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 3.946509599685669,
+      "learning_rate": 7.5501583949313625e-06,
+      "loss": 0.192,
+      "step": 910
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 3.9938108921051025,
+      "learning_rate": 7.022175290390708e-06,
+      "loss": 0.1893,
+      "step": 920
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.878434419631958,
+      "learning_rate": 6.494192185850054e-06,
+      "loss": 0.1843,
+      "step": 930
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 3.8179821968078613,
+      "learning_rate": 5.966209081309398e-06,
+      "loss": 0.2282,
+      "step": 940
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 5.556141376495361,
+      "learning_rate": 5.438225976768744e-06,
+      "loss": 0.18,
+      "step": 950
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 3.250397205352783,
+      "learning_rate": 4.910242872228089e-06,
+      "loss": 0.1947,
+      "step": 960
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 2.9559216499328613,
+      "learning_rate": 4.382259767687434e-06,
+      "loss": 0.1889,
+      "step": 970
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 4.601840972900391,
+      "learning_rate": 3.854276663146779e-06,
+      "loss": 0.1805,
+      "step": 980
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 4.955376148223877,
+      "learning_rate": 3.326293558606125e-06,
+      "loss": 0.2462,
+      "step": 990
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 3.84184193611145,
+      "learning_rate": 2.79831045406547e-06,
+      "loss": 0.194,
+      "step": 1000
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 3.8135769367218018,
+      "learning_rate": 2.2703273495248154e-06,
+      "loss": 0.2011,
+      "step": 1010
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 4.607426166534424,
+      "learning_rate": 1.7423442449841606e-06,
+      "loss": 0.1948,
+      "step": 1020
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 4.66074275970459,
+      "learning_rate": 1.2143611404435059e-06,
+      "loss": 0.1996,
+      "step": 1030
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 3.2419092655181885,
+      "learning_rate": 6.863780359028511e-07,
+      "loss": 0.1981,
+      "step": 1040
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 3.586371660232544,
+      "learning_rate": 1.5839493136219642e-07,
+      "loss": 0.2298,
+      "step": 1050
+    },
+    {
+      "epoch": 2.99,
+      "eval_accuracy": 0.9862,
+      "eval_loss": 0.04177713394165039,
+      "eval_runtime": 49.9847,
+      "eval_samples_per_second": 100.031,
+      "eval_steps_per_second": 3.141,
+      "step": 1053
+    },
+    {
+      "epoch": 2.99,
+      "step": 1053,
+      "total_flos": 2.636946768879747e+18,
+      "train_loss": 0.3514244137552955,
+      "train_runtime": 1744.8692,
+      "train_samples_per_second": 77.37,
+      "train_steps_per_second": 0.603
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1053,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.636946768879747e+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 sha256:2bc82a54430919bc50198875159242419c3e120b8f13286b58121b6673320a67
+size 4920