End of training

README.md

@@ -0,0 +1,83 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: 21BAI1229
+  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. -->
+
+# 21BAI1229
+
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4078
+- Accuracy: 0.8734
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| 2.6034        | 0.9873  | 39   | 2.0544          | 0.4520   |
+| 1.4429        | 2.0     | 79   | 0.7736          | 0.7849   |
+| 0.8307        | 2.9873  | 118  | 0.5456          | 0.8413   |
+| 0.6814        | 4.0     | 158  | 0.4881          | 0.8516   |
+| 0.6199        | 4.9873  | 197  | 0.4614          | 0.8528   |
+| 0.5578        | 6.0     | 237  | 0.4419          | 0.8615   |
+| 0.5198        | 6.9873  | 276  | 0.4485          | 0.8603   |
+| 0.4811        | 8.0     | 316  | 0.4355          | 0.8659   |
+| 0.4568        | 8.9873  | 355  | 0.4182          | 0.8651   |
+| 0.4268        | 10.0    | 395  | 0.4094          | 0.8702   |
+| 0.4281        | 10.9873 | 434  | 0.4158          | 0.8706   |
+| 0.4143        | 12.0    | 474  | 0.4078          | 0.8734   |
+| 0.4009        | 12.9873 | 513  | 0.4066          | 0.8714   |
+| 0.3642        | 14.0    | 553  | 0.4131          | 0.8683   |
+| 0.3659        | 14.9873 | 592  | 0.4047          | 0.8726   |
+| 0.3487        | 16.0    | 632  | 0.4054          | 0.8710   |
+| 0.35          | 16.9873 | 671  | 0.4107          | 0.8722   |
+| 0.3291        | 18.0    | 711  | 0.4099          | 0.8698   |
+| 0.338         | 18.9873 | 750  | 0.4063          | 0.8718   |
+| 0.3419        | 19.7468 | 780  | 0.4066          | 0.8702   |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 19.746835443037973,
+    "eval_accuracy": 0.8734126984126984,
+    "eval_loss": 0.40782999992370605,
+    "eval_runtime": 35.112,
+    "eval_samples_per_second": 71.77,
+    "eval_steps_per_second": 1.139,
+    "total_flos": 1.5428282771770638e+19,
+    "train_loss": 0.6176073722350292,
+    "train_runtime": 7965.5555,
+    "train_samples_per_second": 25.309,
+    "train_steps_per_second": 0.098
+}

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "calling",
+    "1": "clapping",
+    "2": "cycling",
+    "3": "dancing",
+    "4": "drinking",
+    "5": "eating",
+    "6": "fighting",
+    "7": "hugging",
+    "8": "laughing",
+    "9": "listening_to_music",
+    "10": "running",
+    "11": "sitting",
+    "12": "sleeping",
+    "13": "texting",
+    "14": "using_laptop"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "calling": 0,
+    "clapping": 1,
+    "cycling": 2,
+    "dancing": 3,
+    "drinking": 4,
+    "eating": 5,
+    "fighting": 6,
+    "hugging": 7,
+    "laughing": 8,
+    "listening_to_music": 9,
+    "running": 10,
+    "sitting": 11,
+    "sleeping": 12,
+    "texting": 13,
+    "using_laptop": 14
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 19.746835443037973,
+    "eval_accuracy": 0.8734126984126984,
+    "eval_loss": 0.40782999992370605,
+    "eval_runtime": 35.112,
+    "eval_samples_per_second": 71.77,
+    "eval_steps_per_second": 1.139
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b26f3402a9152e42107553fd514e55ab8e64a82692e28366ba23cd1d130247aa
+size 343263964

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/Nov14_22-59-20_24484a158615/events.out.tfevents.1731625166.24484a158615.168.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73f7e706417ed98f4bcc9bdb3ab38bc5be539d9855ef6b0e7a2448aed06660c
+size 16632

runs/Nov14_22-59-20_24484a158615/events.out.tfevents.1731633168.24484a158615.168.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7557bd00bd01e5e2a650902e2408110eb44c937039e20ab2849ba3f682d1caba
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 19.746835443037973,
+    "total_flos": 1.5428282771770638e+19,
+    "train_loss": 0.6176073722350292,
+    "train_runtime": 7965.5555,
+    "train_samples_per_second": 25.309,
+    "train_steps_per_second": 0.098
+}

trainer_state.json

@@ -0,0 +1,362 @@
+{
+  "best_metric": 0.8734126984126984,
+  "best_model_checkpoint": "21BAI1229/checkpoint-474",
+  "epoch": 19.746835443037973,
+  "eval_steps": 500,
+  "global_step": 780,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9873417721518988,
+      "grad_norm": 11.754476547241211,
+      "learning_rate": 2.5e-05,
+      "loss": 2.6034,
+      "step": 39
+    },
+    {
+      "epoch": 0.9873417721518988,
+      "eval_accuracy": 0.451984126984127,
+      "eval_loss": 2.054410696029663,
+      "eval_runtime": 36.1954,
+      "eval_samples_per_second": 69.622,
+      "eval_steps_per_second": 1.105,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.275434970855713,
+      "learning_rate": 4.992877492877493e-05,
+      "loss": 1.4429,
+      "step": 79
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7849206349206349,
+      "eval_loss": 0.7735527157783508,
+      "eval_runtime": 35.4184,
+      "eval_samples_per_second": 71.149,
+      "eval_steps_per_second": 1.129,
+      "step": 79
+    },
+    {
+      "epoch": 2.9873417721518987,
+      "grad_norm": 7.623991012573242,
+      "learning_rate": 4.7150997150997157e-05,
+      "loss": 0.8307,
+      "step": 118
+    },
+    {
+      "epoch": 2.9873417721518987,
+      "eval_accuracy": 0.8412698412698413,
+      "eval_loss": 0.5455929636955261,
+      "eval_runtime": 35.3707,
+      "eval_samples_per_second": 71.245,
+      "eval_steps_per_second": 1.131,
+      "step": 118
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.973851203918457,
+      "learning_rate": 4.4301994301994304e-05,
+      "loss": 0.6814,
+      "step": 158
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8515873015873016,
+      "eval_loss": 0.48805657029151917,
+      "eval_runtime": 35.4085,
+      "eval_samples_per_second": 71.169,
+      "eval_steps_per_second": 1.13,
+      "step": 158
+    },
+    {
+      "epoch": 4.987341772151899,
+      "grad_norm": 8.185949325561523,
+      "learning_rate": 4.152421652421652e-05,
+      "loss": 0.6199,
+      "step": 197
+    },
+    {
+      "epoch": 4.987341772151899,
+      "eval_accuracy": 0.8527777777777777,
+      "eval_loss": 0.46135592460632324,
+      "eval_runtime": 35.2536,
+      "eval_samples_per_second": 71.482,
+      "eval_steps_per_second": 1.135,
+      "step": 197
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 11.136569023132324,
+      "learning_rate": 3.867521367521368e-05,
+      "loss": 0.5578,
+      "step": 237
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8615079365079366,
+      "eval_loss": 0.44191327691078186,
+      "eval_runtime": 35.2038,
+      "eval_samples_per_second": 71.583,
+      "eval_steps_per_second": 1.136,
+      "step": 237
+    },
+    {
+      "epoch": 6.987341772151899,
+      "grad_norm": 6.935160160064697,
+      "learning_rate": 3.58974358974359e-05,
+      "loss": 0.5198,
+      "step": 276
+    },
+    {
+      "epoch": 6.987341772151899,
+      "eval_accuracy": 0.8603174603174604,
+      "eval_loss": 0.4485108256340027,
+      "eval_runtime": 35.2921,
+      "eval_samples_per_second": 71.404,
+      "eval_steps_per_second": 1.133,
+      "step": 276
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 7.163381576538086,
+      "learning_rate": 3.304843304843305e-05,
+      "loss": 0.4811,
+      "step": 316
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8658730158730159,
+      "eval_loss": 0.4355041980743408,
+      "eval_runtime": 35.4396,
+      "eval_samples_per_second": 71.107,
+      "eval_steps_per_second": 1.129,
+      "step": 316
+    },
+    {
+      "epoch": 8.987341772151899,
+      "grad_norm": 7.22255277633667,
+      "learning_rate": 3.0270655270655275e-05,
+      "loss": 0.4568,
+      "step": 355
+    },
+    {
+      "epoch": 8.987341772151899,
+      "eval_accuracy": 0.8650793650793651,
+      "eval_loss": 0.4182125926017761,
+      "eval_runtime": 35.5074,
+      "eval_samples_per_second": 70.971,
+      "eval_steps_per_second": 1.127,
+      "step": 355
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 7.7428879737854,
+      "learning_rate": 2.7421652421652423e-05,
+      "loss": 0.4268,
+      "step": 395
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8702380952380953,
+      "eval_loss": 0.4093915522098541,
+      "eval_runtime": 35.1709,
+      "eval_samples_per_second": 71.65,
+      "eval_steps_per_second": 1.137,
+      "step": 395
+    },
+    {
+      "epoch": 10.987341772151899,
+      "grad_norm": 8.56812572479248,
+      "learning_rate": 2.4643874643874645e-05,
+      "loss": 0.4281,
+      "step": 434
+    },
+    {
+      "epoch": 10.987341772151899,
+      "eval_accuracy": 0.8706349206349207,
+      "eval_loss": 0.41577932238578796,
+      "eval_runtime": 35.2893,
+      "eval_samples_per_second": 71.41,
+      "eval_steps_per_second": 1.133,
+      "step": 434
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 9.711762428283691,
+      "learning_rate": 2.1794871794871795e-05,
+      "loss": 0.4143,
+      "step": 474
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.8734126984126984,
+      "eval_loss": 0.40782999992370605,
+      "eval_runtime": 35.0211,
+      "eval_samples_per_second": 71.957,
+      "eval_steps_per_second": 1.142,
+      "step": 474
+    },
+    {
+      "epoch": 12.987341772151899,
+      "grad_norm": 7.874723434448242,
+      "learning_rate": 1.9017094017094017e-05,
+      "loss": 0.4009,
+      "step": 513
+    },
+    {
+      "epoch": 12.987341772151899,
+      "eval_accuracy": 0.8714285714285714,
+      "eval_loss": 0.4066493511199951,
+      "eval_runtime": 35.2449,
+      "eval_samples_per_second": 71.5,
+      "eval_steps_per_second": 1.135,
+      "step": 513
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 8.416353225708008,
+      "learning_rate": 1.6168091168091168e-05,
+      "loss": 0.3642,
+      "step": 553
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.8682539682539683,
+      "eval_loss": 0.4131360352039337,
+      "eval_runtime": 35.3914,
+      "eval_samples_per_second": 71.204,
+      "eval_steps_per_second": 1.13,
+      "step": 553
+    },
+    {
+      "epoch": 14.987341772151899,
+      "grad_norm": 8.845190048217773,
+      "learning_rate": 1.3390313390313392e-05,
+      "loss": 0.3659,
+      "step": 592
+    },
+    {
+      "epoch": 14.987341772151899,
+      "eval_accuracy": 0.8726190476190476,
+      "eval_loss": 0.40469926595687866,
+      "eval_runtime": 35.2434,
+      "eval_samples_per_second": 71.503,
+      "eval_steps_per_second": 1.135,
+      "step": 592
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 7.056828022003174,
+      "learning_rate": 1.0541310541310543e-05,
+      "loss": 0.3487,
+      "step": 632
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.871031746031746,
+      "eval_loss": 0.4053677022457123,
+      "eval_runtime": 35.2106,
+      "eval_samples_per_second": 71.569,
+      "eval_steps_per_second": 1.136,
+      "step": 632
+    },
+    {
+      "epoch": 16.9873417721519,
+      "grad_norm": 7.8862199783325195,
+      "learning_rate": 7.763532763532765e-06,
+      "loss": 0.35,
+      "step": 671
+    },
+    {
+      "epoch": 16.9873417721519,
+      "eval_accuracy": 0.8722222222222222,
+      "eval_loss": 0.41073036193847656,
+      "eval_runtime": 35.125,
+      "eval_samples_per_second": 71.744,
+      "eval_steps_per_second": 1.139,
+      "step": 671
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 9.344978332519531,
+      "learning_rate": 4.914529914529915e-06,
+      "loss": 0.3291,
+      "step": 711
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.8698412698412699,
+      "eval_loss": 0.40985915064811707,
+      "eval_runtime": 35.2658,
+      "eval_samples_per_second": 71.457,
+      "eval_steps_per_second": 1.134,
+      "step": 711
+    },
+    {
+      "epoch": 18.9873417721519,
+      "grad_norm": 6.548698902130127,
+      "learning_rate": 2.136752136752137e-06,
+      "loss": 0.338,
+      "step": 750
+    },
+    {
+      "epoch": 18.9873417721519,
+      "eval_accuracy": 0.8718253968253968,
+      "eval_loss": 0.40625905990600586,
+      "eval_runtime": 35.4023,
+      "eval_samples_per_second": 71.182,
+      "eval_steps_per_second": 1.13,
+      "step": 750
+    },
+    {
+      "epoch": 19.746835443037973,
+      "grad_norm": 6.30403470993042,
+      "learning_rate": 0.0,
+      "loss": 0.3419,
+      "step": 780
+    },
+    {
+      "epoch": 19.746835443037973,
+      "eval_accuracy": 0.8702380952380953,
+      "eval_loss": 0.4066447913646698,
+      "eval_runtime": 35.3364,
+      "eval_samples_per_second": 71.315,
+      "eval_steps_per_second": 1.132,
+      "step": 780
+    },
+    {
+      "epoch": 19.746835443037973,
+      "step": 780,
+      "total_flos": 1.5428282771770638e+19,
+      "train_loss": 0.6176073722350292,
+      "train_runtime": 7965.5555,
+      "train_samples_per_second": 25.309,
+      "train_steps_per_second": 0.098
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 780,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5428282771770638e+19,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ed54e17dab6d903d84db67320e8c81985da9a8f2c71c234b43a7fd55efd247
+size 5240