🍻 cheers

README.md

@@ -0,0 +1,97 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: test-trainer
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: Chess
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9107142857142857
+    - name: F1
+      type: f1
+      value: 0.9121670865142396
+    - name: Precision
+      type: precision
+      value: 0.9171626984126985
+    - name: Recall
+      type: recall
+      value: 0.9107142857142857
+---
+
+<!-- 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. -->
+
+# test-trainer
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the Chess dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7291
+- Accuracy: 0.9107
+- F1: 0.9122
+- Precision: 0.9172
+- Recall: 0.9107
+
+## 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: 2e-05
+- train_batch_size: 10
+- eval_batch_size: 4
+- seed: 42
+- 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
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 50   | 1.6720          | 0.4821   | 0.4134 | 0.3870    | 0.4821 |
+| No log        | 2.0   | 100  | 1.4652          | 0.6429   | 0.6126 | 0.7414    | 0.6429 |
+| No log        | 3.0   | 150  | 1.1742          | 0.7321   | 0.7210 | 0.7792    | 0.7321 |
+| No log        | 4.0   | 200  | 0.9813          | 0.8393   | 0.8433 | 0.8589    | 0.8393 |
+| No log        | 5.0   | 250  | 0.8312          | 0.8214   | 0.8164 | 0.8516    | 0.8214 |
+| No log        | 6.0   | 300  | 0.7291          | 0.9107   | 0.9122 | 0.9172    | 0.9107 |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.2.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "total_flos": 2.3108939745841152e+17,
+    "train_loss": 1.2372085571289062,
+    "train_runtime": 74.6152,
+    "train_samples_per_second": 199.825,
+    "train_steps_per_second": 20.103
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Bishop",
+    "1": "King",
+    "2": "Knight",
+    "3": "Pawn",
+    "4": "Queen",
+    "5": "Rook"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Bishop": 0,
+    "King": 1,
+    "Knight": 2,
+    "Pawn": 3,
+    "Queen": 4,
+    "Rook": 5
+  },
+  "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"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1bb1780e5120299da07c8a94a870963b865b5bd2ace81821659d676ca19222b
+size 343236280

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
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "total_flos": 2.3108939745841152e+17,
+    "train_loss": 1.2372085571289062,
+    "train_runtime": 74.6152,
+    "train_samples_per_second": 199.825,
+    "train_steps_per_second": 20.103
+}

trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_metric": 0.9107142857142857,
+  "best_model_checkpoint": "test-trainer/checkpoint-300",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.48214285714285715,
+      "eval_f1": 0.41339955022488756,
+      "eval_loss": 1.6720179319381714,
+      "eval_precision": 0.38696741854636585,
+      "eval_recall": 0.48214285714285715,
+      "eval_runtime": 1.2456,
+      "eval_samples_per_second": 44.958,
+      "eval_steps_per_second": 11.24,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6428571428571429,
+      "eval_f1": 0.6126473922902493,
+      "eval_loss": 1.4651685953140259,
+      "eval_precision": 0.7413690476190476,
+      "eval_recall": 0.6428571428571429,
+      "eval_runtime": 1.2147,
+      "eval_samples_per_second": 46.104,
+      "eval_steps_per_second": 11.526,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7321428571428571,
+      "eval_f1": 0.7210389711440132,
+      "eval_loss": 1.1741597652435303,
+      "eval_precision": 0.7791524943310657,
+      "eval_recall": 0.7321428571428571,
+      "eval_runtime": 1.2504,
+      "eval_samples_per_second": 44.787,
+      "eval_steps_per_second": 11.197,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8392857142857143,
+      "eval_f1": 0.8433130175146982,
+      "eval_loss": 0.9812522530555725,
+      "eval_precision": 0.858866084312513,
+      "eval_recall": 0.8392857142857143,
+      "eval_runtime": 1.2079,
+      "eval_samples_per_second": 46.361,
+      "eval_steps_per_second": 11.59,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8214285714285714,
+      "eval_f1": 0.8163565426170468,
+      "eval_loss": 0.8311730027198792,
+      "eval_precision": 0.8515512265512265,
+      "eval_recall": 0.8214285714285714,
+      "eval_runtime": 1.2437,
+      "eval_samples_per_second": 45.027,
+      "eval_steps_per_second": 11.257,
+      "step": 250
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9107142857142857,
+      "eval_f1": 0.9121670865142396,
+      "eval_loss": 0.7291183471679688,
+      "eval_precision": 0.9171626984126985,
+      "eval_recall": 0.9107142857142857,
+      "eval_runtime": 1.2203,
+      "eval_samples_per_second": 45.89,
+      "eval_steps_per_second": 11.472,
+      "step": 300
+    },
+    {
+      "epoch": 6.0,
+      "step": 300,
+      "total_flos": 2.3108939745841152e+17,
+      "train_loss": 1.2372085571289062,
+      "train_runtime": 74.6152,
+      "train_samples_per_second": 199.825,
+      "train_steps_per_second": 20.103
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 1.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3108939745841152e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef88edba6af581510201d1a66ea3d97022b96a8fa04892b4840bdea7fe286935
+size 5240