End of training

README.md

@@ -0,0 +1,89 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: asl_aplhabet_img_classifier
+  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. -->
+
+# asl_aplhabet_img_classifier
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9586
+- Accuracy: 0.2692
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 26   | 3.2666          | 0.0385   |
+| No log        | 2.0   | 52   | 3.2701          | 0.0385   |
+| No log        | 3.0   | 78   | 3.2713          | 0.0288   |
+| No log        | 4.0   | 104  | 3.2701          | 0.0769   |
+| No log        | 5.0   | 130  | 3.2584          | 0.0385   |
+| No log        | 6.0   | 156  | 3.2537          | 0.0577   |
+| No log        | 7.0   | 182  | 3.2402          | 0.0577   |
+| No log        | 8.0   | 208  | 3.2364          | 0.0577   |
+| No log        | 9.0   | 234  | 3.2055          | 0.0769   |
+| No log        | 10.0  | 260  | 3.1794          | 0.0769   |
+| No log        | 11.0  | 286  | 3.1851          | 0.1346   |
+| No log        | 12.0  | 312  | 3.1811          | 0.1058   |
+| No log        | 13.0  | 338  | 3.1594          | 0.1346   |
+| No log        | 14.0  | 364  | 3.1269          | 0.1635   |
+| No log        | 15.0  | 390  | 3.1082          | 0.125    |
+| No log        | 16.0  | 416  | 3.1019          | 0.2019   |
+| No log        | 17.0  | 442  | 3.0886          | 0.2019   |
+| No log        | 18.0  | 468  | 3.0599          | 0.2115   |
+| No log        | 19.0  | 494  | 3.0622          | 0.1731   |
+| 3.0197        | 20.0  | 520  | 3.0474          | 0.1538   |
+| 3.0197        | 21.0  | 546  | 3.0245          | 0.2115   |
+| 3.0197        | 22.0  | 572  | 3.0386          | 0.1923   |
+| 3.0197        | 23.0  | 598  | 3.0236          | 0.1923   |
+| 3.0197        | 24.0  | 624  | 3.0201          | 0.1923   |
+| 3.0197        | 25.0  | 650  | 3.0056          | 0.2212   |
+| 3.0197        | 26.0  | 676  | 2.9649          | 0.25     |
+| 3.0197        | 27.0  | 702  | 2.9900          | 0.2212   |
+| 3.0197        | 28.0  | 728  | 2.9823          | 0.2308   |
+| 3.0197        | 29.0  | 754  | 2.9782          | 0.2115   |
+| 3.0197        | 30.0  | 780  | 3.0136          | 0.1635   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,80 @@
+{
+  "_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": "A",
+    "1": "B",
+    "10": "K",
+    "11": "L",
+    "12": "M",
+    "13": "N",
+    "14": "O",
+    "15": "P",
+    "16": "Q",
+    "17": "R",
+    "18": "S",
+    "19": "T",
+    "2": "C",
+    "20": "U",
+    "21": "V",
+    "22": "W",
+    "23": "X",
+    "24": "Y",
+    "25": "Z",
+    "3": "D",
+    "4": "E",
+    "5": "F",
+    "6": "G",
+    "7": "H",
+    "8": "I",
+    "9": "J"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "A": "0",
+    "B": "1",
+    "C": "2",
+    "D": "3",
+    "E": "4",
+    "F": "5",
+    "G": "6",
+    "H": "7",
+    "I": "8",
+    "J": "9",
+    "K": "10",
+    "L": "11",
+    "M": "12",
+    "N": "13",
+    "O": "14",
+    "P": "15",
+    "Q": "16",
+    "R": "17",
+    "S": "18",
+    "T": "19",
+    "U": "20",
+    "V": "21",
+    "W": "22",
+    "X": "23",
+    "Y": "24",
+    "Z": "25"
+  },
+  "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": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6a5e443d7155a0e561b91d3caa5152e70fc3be9059dd7507c6432a10d6fc30
+size 343297800

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/Mar17_18-55-40_df1c186cd307/events.out.tfevents.1710701754.df1c186cd307.237.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7e95ba83bf4dbb253c92dea4001ce21f2f0283aac670f14675d63df437b57b
+size 15529

runs/Mar17_18-55-40_df1c186cd307/events.out.tfevents.1710702509.df1c186cd307.237.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb94bdece10b82beb4c537d003e7b097df9f427128140795ec966bda5bc068f
+size 411

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f2ffd3df424426ed2af993dea95342f028c15ab56c4f5da2c6004a1a43509f
+size 4920