Upload folder using huggingface_hub

checkpoint-470/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "dima806/wild_cats_image_detection",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LIONS",
+    "1": "CARACAL",
+    "2": "AFRICAN LEOPARD",
+    "3": "CHEETAH",
+    "4": "SNOW LEOPARD",
+    "5": "TIGER",
+    "6": "OCELOT",
+    "7": "JAGUAR",
+    "8": "PUMA",
+    "9": "CLOUDED LEOPARD"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "AFRICAN LEOPARD": 2,
+    "CARACAL": 1,
+    "CHEETAH": 3,
+    "CLOUDED LEOPARD": 9,
+    "JAGUAR": 7,
+    "LIONS": 0,
+    "OCELOT": 6,
+    "PUMA": 8,
+    "SNOW LEOPARD": 4,
+    "TIGER": 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": "4.39.2"
+}

checkpoint-470/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a444d7be5ab8a25e9ae5504e61e9abb3396ec6ab271aad76c37460cac31634b
+size 343248584

checkpoint-470/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8910e78659cb856d3c1bc0879ac891d703b6ce2b125a10583d078c397e6b1cbb
+size 686617605

checkpoint-470/preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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
+  }
+}

checkpoint-470/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ed7901332c0a72cbfc68bca97e11c9dc63d1d36628bc32ef0fdd5c41214e7b
+size 14575

checkpoint-470/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93849d1b1db9c9ec831593386d9feb98a86881bae26e71ea10aa88dbf9604a19
+size 627

checkpoint-470/trainer_state.json

@@ -0,0 +1,111 @@
+{
+  "best_metric": 0.22051118314266205,
+  "best_model_checkpoint": "wild_cats_image_detection/checkpoint-470",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 470,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9919354838709677,
+      "eval_loss": 0.22656135261058807,
+      "eval_runtime": 8.7802,
+      "eval_samples_per_second": 112.982,
+      "eval_steps_per_second": 14.123,
+      "step": 47
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9919354838709677,
+      "eval_loss": 0.22572563588619232,
+      "eval_runtime": 8.8451,
+      "eval_samples_per_second": 112.153,
+      "eval_steps_per_second": 14.019,
+      "step": 94
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9929435483870968,
+      "eval_loss": 0.22531047463417053,
+      "eval_runtime": 8.5884,
+      "eval_samples_per_second": 115.504,
+      "eval_steps_per_second": 14.438,
+      "step": 141
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9929435483870968,
+      "eval_loss": 0.2230643332004547,
+      "eval_runtime": 8.575,
+      "eval_samples_per_second": 115.685,
+      "eval_steps_per_second": 14.461,
+      "step": 188
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9929435483870968,
+      "eval_loss": 0.2232486605644226,
+      "eval_runtime": 8.7024,
+      "eval_samples_per_second": 113.992,
+      "eval_steps_per_second": 14.249,
+      "step": 235
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9929435483870968,
+      "eval_loss": 0.22252562642097473,
+      "eval_runtime": 8.6614,
+      "eval_samples_per_second": 114.532,
+      "eval_steps_per_second": 14.316,
+      "step": 282
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9929435483870968,
+      "eval_loss": 0.2216445803642273,
+      "eval_runtime": 8.6921,
+      "eval_samples_per_second": 114.126,
+      "eval_steps_per_second": 14.266,
+      "step": 329
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9929435483870968,
+      "eval_loss": 0.22078880667686462,
+      "eval_runtime": 8.581,
+      "eval_samples_per_second": 115.604,
+      "eval_steps_per_second": 14.451,
+      "step": 376
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9929435483870968,
+      "eval_loss": 0.22061674296855927,
+      "eval_runtime": 8.7731,
+      "eval_samples_per_second": 113.073,
+      "eval_steps_per_second": 14.134,
+      "step": 423
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9929435483870968,
+      "eval_loss": 0.22051118314266205,
+      "eval_runtime": 8.5923,
+      "eval_samples_per_second": 115.452,
+      "eval_steps_per_second": 14.431,
+      "step": 470
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 470,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.1531634830534246e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-470/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e922cbdcb187085f484963ce7a426c6c51817ed27659caa1746342555bfbc1b
+size 4411

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "_name_or_path": "dima806/wild_cats_image_detection",
   "architectures": [
     "ViTForImageClassification"
   ],
@@ -44,5 +44,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.0"
+  "transformers_version": "4.39.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a444d7be5ab8a25e9ae5504e61e9abb3396ec6ab271aad76c37460cac31634b
+size 343248584

preprocessor_config.json

@@ -1,4 +1,18 @@
 {
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:379350d6cc5241e75a1873b11ab4ea5ccf97133b46ded85692b65ad97c537da6
-size 4027
+oid sha256:2e922cbdcb187085f484963ce7a426c6c51817ed27659caa1746342555bfbc1b
+size 4411