Upload folder using huggingface_hub

checkpoint-2814/config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "dima806/hand_gestures_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": "call",
+    "1": "dislike",
+    "2": "fist",
+    "3": "four",
+    "4": "like",
+    "5": "mute",
+    "6": "ok",
+    "7": "one",
+    "8": "palm",
+    "9": "peace",
+    "10": "peace_inverted",
+    "11": "rock",
+    "12": "stop",
+    "13": "stop_inverted",
+    "14": "three",
+    "15": "three2",
+    "16": "two_up",
+    "17": "two_up_inverted"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "call": 0,
+    "dislike": 1,
+    "fist": 2,
+    "four": 3,
+    "like": 4,
+    "mute": 5,
+    "ok": 6,
+    "one": 7,
+    "palm": 8,
+    "peace": 9,
+    "peace_inverted": 10,
+    "rock": 11,
+    "stop": 12,
+    "stop_inverted": 13,
+    "three": 14,
+    "three2": 15,
+    "two_up": 16,
+    "two_up_inverted": 17
+  },
+  "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"
+}

checkpoint-2814/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b40b5f490b48c6ae469666379b82d1795c96d0ee09ce025c8120d77532cf2bb4
+size 343273192

checkpoint-2814/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae35315b4cbc39b527332b99cd6bc617ef5bf018da235d100df85838901eb97
+size 686666885

checkpoint-2814/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
+  }
+}

checkpoint-2814/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911717e6c079ece6a92564164b43a0f7d6db4376cf820e7d270da472c85a1217
+size 14575

checkpoint-2814/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d0e96e8a6e2180542ad74c5394ad428b2d806caadea61917c4b717137690ed
+size 627

checkpoint-2814/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 2.4189274311065674,
+  "best_model_checkpoint": "hand_gestures_image_detection/checkpoint-2814",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2814,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.371924746743849e-07,
+      "loss": 2.8229,
+      "step": 500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.562952243125904e-07,
+      "loss": 2.704,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4466,
+      "eval_loss": 2.5748167037963867,
+      "eval_runtime": 119.6576,
+      "eval_samples_per_second": 83.572,
+      "eval_steps_per_second": 2.616,
+      "step": 1407
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.7539797395079595e-07,
+      "loss": 2.5758,
+      "step": 1500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.9450072358900143e-07,
+      "loss": 2.4697,
+      "step": 2000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.1360347322720694e-07,
+      "loss": 2.4039,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5548,
+      "eval_loss": 2.4189274311065674,
+      "eval_runtime": 118.9495,
+      "eval_samples_per_second": 84.069,
+      "eval_steps_per_second": 2.631,
+      "step": 2814
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2814,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.395055839485952e+19,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2814/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a812e0c9b9b4ac9878b584a99c5fc65fd84a85a7d5087efc49cd658a927dfbde
+size 4219

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "_name_or_path": "dima806/hand_gestures_image_detection",
   "architectures": [
     "ViTForImageClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a7edc119b2706bbc7a2b58cf531a03bf32549a6c5cc37ac74af369cd64409b
+oid sha256:b40b5f490b48c6ae469666379b82d1795c96d0ee09ce025c8120d77532cf2bb4
 size 343273192

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8676d1b969b494fd587db8fc37b017cc09641351dbc01a703277533d7b5316f6
+oid sha256:a812e0c9b9b4ac9878b584a99c5fc65fd84a85a7d5087efc49cd658a927dfbde
 size 4219