ChrisGuarino/cats

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+model-index:
+- name: cat_ds
+  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. -->
+
+# cat_ds
+
+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.
+
+## 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: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2
+- Datasets 2.16.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.12354437162478765,
+    "train_runtime": 816.8581,
+    "train_samples_per_second": 1.131,
+    "train_steps_per_second": 0.073
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_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": "prim",
+    "1": "rupe"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "prim": "0",
+    "rupe": "1"
+  },
+  "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": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5472cbd618ef0d3c3b04e83047187bc72de0f548d053a6148232410589ba0f33
+size 343223968

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 +1,7 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.12354437162478765,
+    "train_runtime": 816.8581,
+    "train_samples_per_second": 1.131,
+    "train_steps_per_second": 0.073
+}

trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 100,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.5123,
+      "step": 10
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.1132,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0663,
+      "step": 30
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.024,
+      "step": 40
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0122,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.0131,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "step": 60,
+      "total_flos": 7.160259840388301e+16,
+      "train_loss": 0.12354437162478765,
+      "train_runtime": 816.8581,
+      "train_samples_per_second": 1.131,
+      "train_steps_per_second": 0.073
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "total_flos": 7.160259840388301e+16,
+  "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 sha256:61371cd75b4f638b15ec45c535d3fe4ceb885a5adcccc6832a649781076427f3
+size 4664