Upload folder using huggingface_hub

checkpoint-14968/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-14968/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80fcb76db341927822b0bc980e96521dfdb0d991a76bc6c76280a0ece62f2bdf
+size 343273192

checkpoint-14968/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba28a0e5ad69840fa80903429162787d4205e86943e7137ddc9d43388d0ca67
+size 686666885

checkpoint-14968/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-14968/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c64e2e16791803f10345fd0e39eba83b6c2d075520aaa657ccb8c816ff5bbe6
+size 14575

checkpoint-14968/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e51dc3b2b95d746df38d77c07a0e0eeba4bf5a57c6b5c18403adce16e6cad8
+size 627

checkpoint-14968/trainer_state.json

@@ -0,0 +1,213 @@
+{
+  "best_metric": 1.3194196224212646,
+  "best_model_checkpoint": "hand_gestures_image_detection/checkpoint-14968",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 14968,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.84917549269339e-07,
+      "loss": 2.3317,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.6815927067971575e-07,
+      "loss": 2.2323,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.5140099209009247e-07,
+      "loss": 2.1419,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.3464271350046923e-07,
+      "loss": 2.0548,
+      "step": 2000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.1788443491084595e-07,
+      "loss": 1.9753,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.0112615632122266e-07,
+      "loss": 1.908,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.843678777315994e-07,
+      "loss": 1.8392,
+      "step": 3500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 3.6760959914197614e-07,
+      "loss": 1.7853,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.5085132055235285e-07,
+      "loss": 1.7308,
+      "step": 4500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.3409304196272956e-07,
+      "loss": 1.6786,
+      "step": 5000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.173347633731063e-07,
+      "loss": 1.6325,
+      "step": 5500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.0057648478348304e-07,
+      "loss": 1.5887,
+      "step": 6000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.8381820619385976e-07,
+      "loss": 1.5505,
+      "step": 6500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.6705992760423647e-07,
+      "loss": 1.512,
+      "step": 7000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8551563439567047,
+      "eval_loss": 1.5290167331695557,
+      "eval_runtime": 671.8117,
+      "eval_samples_per_second": 79.213,
+      "eval_steps_per_second": 2.475,
+      "step": 7484
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.503016490146132e-07,
+      "loss": 1.4861,
+      "step": 7500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.3354337042498992e-07,
+      "loss": 1.4527,
+      "step": 8000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.1678509183536666e-07,
+      "loss": 1.4237,
+      "step": 8500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.0002681324574337e-07,
+      "loss": 1.3982,
+      "step": 9000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.8326853465612011e-07,
+      "loss": 1.3758,
+      "step": 9500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.6651025606649685e-07,
+      "loss": 1.3574,
+      "step": 10000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.4975197747687357e-07,
+      "loss": 1.3389,
+      "step": 10500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.3299369888725028e-07,
+      "loss": 1.3232,
+      "step": 11000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.1623542029762702e-07,
+      "loss": 1.3078,
+      "step": 11500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.947714170800376e-08,
+      "loss": 1.2976,
+      "step": 12000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.271886311838047e-08,
+      "loss": 1.2858,
+      "step": 12500
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 6.59605845287572e-08,
+      "loss": 1.2758,
+      "step": 13000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.920230593913393e-08,
+      "loss": 1.2754,
+      "step": 13500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.244402734951066e-08,
+      "loss": 1.2647,
+      "step": 14000
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.5685748759887383e-08,
+      "loss": 1.2642,
+      "step": 14500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.883963469633193,
+      "eval_loss": 1.3194196224212646,
+      "eval_runtime": 673.3538,
+      "eval_samples_per_second": 79.031,
+      "eval_steps_per_second": 2.47,
+      "step": 14968
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14968,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 7.423805150444932e+19,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-14968/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30518e4f8bc3bcbf0ebddc024498f9f147b637f7e39a8091142f93dbe19de848
+size 4219

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b40b5f490b48c6ae469666379b82d1795c96d0ee09ce025c8120d77532cf2bb4
+oid sha256:80fcb76db341927822b0bc980e96521dfdb0d991a76bc6c76280a0ece62f2bdf
 size 343273192

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a812e0c9b9b4ac9878b584a99c5fc65fd84a85a7d5087efc49cd658a927dfbde
+oid sha256:30518e4f8bc3bcbf0ebddc024498f9f147b637f7e39a8091142f93dbe19de848
 size 4219