Upload folder using huggingface_hub
Browse files- checkpoint-8940/config.json +96 -0
- checkpoint-8940/optimizer.pt +3 -0
- checkpoint-8940/preprocessor_config.json +22 -0
- checkpoint-8940/pytorch_model.bin +3 -0
- checkpoint-8940/rng_state.pth +3 -0
- checkpoint-8940/scheduler.pt +3 -0
- checkpoint-8940/trainer_state.json +256 -0
- checkpoint-8940/training_args.bin +3 -0
- config.json +96 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
checkpoint-8940/config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "omelette",
|
| 13 |
+
"1": "apple_pie",
|
| 14 |
+
"2": "Sandwich",
|
| 15 |
+
"3": "kulfi",
|
| 16 |
+
"4": "chicken_curry",
|
| 17 |
+
"5": "Fries",
|
| 18 |
+
"6": "jalebi",
|
| 19 |
+
"7": "Taquito",
|
| 20 |
+
"8": "Crispy Chicken",
|
| 21 |
+
"9": "Baked Potato",
|
| 22 |
+
"10": "kaathi_rolls",
|
| 23 |
+
"11": "masala_dosa",
|
| 24 |
+
"12": "paani_puri",
|
| 25 |
+
"13": "fried_rice",
|
| 26 |
+
"14": "chole_bhature",
|
| 27 |
+
"15": "chai",
|
| 28 |
+
"16": "Taco",
|
| 29 |
+
"17": "samosa",
|
| 30 |
+
"18": "dhokla",
|
| 31 |
+
"19": "chapati",
|
| 32 |
+
"20": "sushi",
|
| 33 |
+
"21": "pakode",
|
| 34 |
+
"22": "butter_naan",
|
| 35 |
+
"23": "momos",
|
| 36 |
+
"24": "idli",
|
| 37 |
+
"25": "pav_bhaji",
|
| 38 |
+
"26": "cheesecake",
|
| 39 |
+
"27": "Donut",
|
| 40 |
+
"28": "burger",
|
| 41 |
+
"29": "pizza",
|
| 42 |
+
"30": "dal_makhani",
|
| 43 |
+
"31": "Hot Dog",
|
| 44 |
+
"32": "ice_cream",
|
| 45 |
+
"33": "kadai_paneer"
|
| 46 |
+
},
|
| 47 |
+
"image_size": 224,
|
| 48 |
+
"initializer_range": 0.02,
|
| 49 |
+
"intermediate_size": 3072,
|
| 50 |
+
"label2id": {
|
| 51 |
+
"Baked Potato": 9,
|
| 52 |
+
"Crispy Chicken": 8,
|
| 53 |
+
"Donut": 27,
|
| 54 |
+
"Fries": 5,
|
| 55 |
+
"Hot Dog": 31,
|
| 56 |
+
"Sandwich": 2,
|
| 57 |
+
"Taco": 16,
|
| 58 |
+
"Taquito": 7,
|
| 59 |
+
"apple_pie": 1,
|
| 60 |
+
"burger": 28,
|
| 61 |
+
"butter_naan": 22,
|
| 62 |
+
"chai": 15,
|
| 63 |
+
"chapati": 19,
|
| 64 |
+
"cheesecake": 26,
|
| 65 |
+
"chicken_curry": 4,
|
| 66 |
+
"chole_bhature": 14,
|
| 67 |
+
"dal_makhani": 30,
|
| 68 |
+
"dhokla": 18,
|
| 69 |
+
"fried_rice": 13,
|
| 70 |
+
"ice_cream": 32,
|
| 71 |
+
"idli": 24,
|
| 72 |
+
"jalebi": 6,
|
| 73 |
+
"kaathi_rolls": 10,
|
| 74 |
+
"kadai_paneer": 33,
|
| 75 |
+
"kulfi": 3,
|
| 76 |
+
"masala_dosa": 11,
|
| 77 |
+
"momos": 23,
|
| 78 |
+
"omelette": 0,
|
| 79 |
+
"paani_puri": 12,
|
| 80 |
+
"pakode": 21,
|
| 81 |
+
"pav_bhaji": 25,
|
| 82 |
+
"pizza": 29,
|
| 83 |
+
"samosa": 17,
|
| 84 |
+
"sushi": 20
|
| 85 |
+
},
|
| 86 |
+
"layer_norm_eps": 1e-12,
|
| 87 |
+
"model_type": "vit",
|
| 88 |
+
"num_attention_heads": 12,
|
| 89 |
+
"num_channels": 3,
|
| 90 |
+
"num_hidden_layers": 12,
|
| 91 |
+
"patch_size": 16,
|
| 92 |
+
"problem_type": "single_label_classification",
|
| 93 |
+
"qkv_bias": true,
|
| 94 |
+
"torch_dtype": "float32",
|
| 95 |
+
"transformers_version": "4.33.0"
|
| 96 |
+
}
|
checkpoint-8940/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9f406b3b5cfffa58bf41ce79a9283f147213763e43ccd9e4c0dbcb4ffeb3097
|
| 3 |
+
size 686765317
|
checkpoint-8940/preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
checkpoint-8940/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e1a5f6f000db5299e4dcc037d681964637940cbe22a32faf0681f3190844b17
|
| 3 |
+
size 343367149
|
checkpoint-8940/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d894fda4a82b74c46d9c2ed46fe0df0531757cbc32ed52fadb9df3946bde36a2
|
| 3 |
+
size 14575
|
checkpoint-8940/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dbed6d90c1d66e8d3a84cb5c5d9b6d1bb8c4cdd7353788d23d0303f057ef1dd
|
| 3 |
+
size 627
|
checkpoint-8940/trainer_state.json
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.28963080048561096,
|
| 3 |
+
"best_model_checkpoint": "food_type_image_detection/checkpoint-8940",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8940,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.84,
|
| 13 |
+
"learning_rate": 9.62089300758214e-06,
|
| 14 |
+
"loss": 2.844,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_accuracy": 0.7601762484263533,
|
| 20 |
+
"eval_loss": 2.02563738822937,
|
| 21 |
+
"eval_runtime": 74.4294,
|
| 22 |
+
"eval_samples_per_second": 64.034,
|
| 23 |
+
"eval_steps_per_second": 8.008,
|
| 24 |
+
"step": 596
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.68,
|
| 28 |
+
"learning_rate": 9.19966301600674e-06,
|
| 29 |
+
"loss": 1.7896,
|
| 30 |
+
"step": 1000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.8583718002517835,
|
| 35 |
+
"eval_loss": 1.3447567224502563,
|
| 36 |
+
"eval_runtime": 74.2376,
|
| 37 |
+
"eval_samples_per_second": 64.199,
|
| 38 |
+
"eval_steps_per_second": 8.028,
|
| 39 |
+
"step": 1192
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.52,
|
| 43 |
+
"learning_rate": 8.77843302443134e-06,
|
| 44 |
+
"loss": 1.2585,
|
| 45 |
+
"step": 1500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.0,
|
| 49 |
+
"eval_accuracy": 0.8927822073017205,
|
| 50 |
+
"eval_loss": 0.9783705472946167,
|
| 51 |
+
"eval_runtime": 77.5013,
|
| 52 |
+
"eval_samples_per_second": 61.496,
|
| 53 |
+
"eval_steps_per_second": 7.69,
|
| 54 |
+
"step": 1788
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.36,
|
| 58 |
+
"learning_rate": 8.357203032855939e-06,
|
| 59 |
+
"loss": 0.9277,
|
| 60 |
+
"step": 2000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.0,
|
| 64 |
+
"eval_accuracy": 0.9175409148132606,
|
| 65 |
+
"eval_loss": 0.748791515827179,
|
| 66 |
+
"eval_runtime": 73.4549,
|
| 67 |
+
"eval_samples_per_second": 64.883,
|
| 68 |
+
"eval_steps_per_second": 8.114,
|
| 69 |
+
"step": 2384
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.19,
|
| 73 |
+
"learning_rate": 7.93597304128054e-06,
|
| 74 |
+
"loss": 0.7029,
|
| 75 |
+
"step": 2500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.0,
|
| 79 |
+
"eval_accuracy": 0.9267729752412925,
|
| 80 |
+
"eval_loss": 0.5919772386550903,
|
| 81 |
+
"eval_runtime": 75.09,
|
| 82 |
+
"eval_samples_per_second": 63.471,
|
| 83 |
+
"eval_steps_per_second": 7.937,
|
| 84 |
+
"step": 2980
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.03,
|
| 88 |
+
"learning_rate": 7.51474304970514e-06,
|
| 89 |
+
"loss": 0.5413,
|
| 90 |
+
"step": 3000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 5.87,
|
| 94 |
+
"learning_rate": 7.09351305812974e-06,
|
| 95 |
+
"loss": 0.4146,
|
| 96 |
+
"step": 3500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.9313890054553084,
|
| 101 |
+
"eval_loss": 0.4901541471481323,
|
| 102 |
+
"eval_runtime": 78.8726,
|
| 103 |
+
"eval_samples_per_second": 60.427,
|
| 104 |
+
"eval_steps_per_second": 7.556,
|
| 105 |
+
"step": 3576
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.71,
|
| 109 |
+
"learning_rate": 6.672283066554339e-06,
|
| 110 |
+
"loss": 0.3251,
|
| 111 |
+
"step": 4000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 7.0,
|
| 115 |
+
"eval_accuracy": 0.9318086445656735,
|
| 116 |
+
"eval_loss": 0.4218488931655884,
|
| 117 |
+
"eval_runtime": 73.7814,
|
| 118 |
+
"eval_samples_per_second": 64.596,
|
| 119 |
+
"eval_steps_per_second": 8.078,
|
| 120 |
+
"step": 4172
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 7.55,
|
| 124 |
+
"learning_rate": 6.251053074978939e-06,
|
| 125 |
+
"loss": 0.2602,
|
| 126 |
+
"step": 4500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.9362148552245069,
|
| 131 |
+
"eval_loss": 0.3739270269870758,
|
| 132 |
+
"eval_runtime": 75.0777,
|
| 133 |
+
"eval_samples_per_second": 63.481,
|
| 134 |
+
"eval_steps_per_second": 7.938,
|
| 135 |
+
"step": 4768
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.39,
|
| 139 |
+
"learning_rate": 5.829823083403539e-06,
|
| 140 |
+
"loss": 0.2034,
|
| 141 |
+
"step": 5000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 9.0,
|
| 145 |
+
"eval_accuracy": 0.9336970205623164,
|
| 146 |
+
"eval_loss": 0.3482232093811035,
|
| 147 |
+
"eval_runtime": 74.9107,
|
| 148 |
+
"eval_samples_per_second": 63.622,
|
| 149 |
+
"eval_steps_per_second": 7.956,
|
| 150 |
+
"step": 5364
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 9.23,
|
| 154 |
+
"learning_rate": 5.408593091828138e-06,
|
| 155 |
+
"loss": 0.1691,
|
| 156 |
+
"step": 5500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 10.0,
|
| 160 |
+
"eval_accuracy": 0.9376835921107848,
|
| 161 |
+
"eval_loss": 0.3193051517009735,
|
| 162 |
+
"eval_runtime": 73.7221,
|
| 163 |
+
"eval_samples_per_second": 64.648,
|
| 164 |
+
"eval_steps_per_second": 8.084,
|
| 165 |
+
"step": 5960
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 10.07,
|
| 169 |
+
"learning_rate": 4.987363100252738e-06,
|
| 170 |
+
"loss": 0.1355,
|
| 171 |
+
"step": 6000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 10.91,
|
| 175 |
+
"learning_rate": 4.566133108677338e-06,
|
| 176 |
+
"loss": 0.1122,
|
| 177 |
+
"step": 6500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 11.0,
|
| 181 |
+
"eval_accuracy": 0.9376835921107848,
|
| 182 |
+
"eval_loss": 0.3138887286186218,
|
| 183 |
+
"eval_runtime": 73.4016,
|
| 184 |
+
"eval_samples_per_second": 64.93,
|
| 185 |
+
"eval_steps_per_second": 8.12,
|
| 186 |
+
"step": 6556
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 11.74,
|
| 190 |
+
"learning_rate": 4.144903117101938e-06,
|
| 191 |
+
"loss": 0.0917,
|
| 192 |
+
"step": 7000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 12.0,
|
| 196 |
+
"eval_accuracy": 0.9372639530004196,
|
| 197 |
+
"eval_loss": 0.3041510581970215,
|
| 198 |
+
"eval_runtime": 73.7867,
|
| 199 |
+
"eval_samples_per_second": 64.592,
|
| 200 |
+
"eval_steps_per_second": 8.077,
|
| 201 |
+
"step": 7152
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 12.58,
|
| 205 |
+
"learning_rate": 3.723673125526538e-06,
|
| 206 |
+
"loss": 0.081,
|
| 207 |
+
"step": 7500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 13.0,
|
| 211 |
+
"eval_accuracy": 0.9368443138900545,
|
| 212 |
+
"eval_loss": 0.2987290918827057,
|
| 213 |
+
"eval_runtime": 73.3422,
|
| 214 |
+
"eval_samples_per_second": 64.983,
|
| 215 |
+
"eval_steps_per_second": 8.126,
|
| 216 |
+
"step": 7748
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 13.42,
|
| 220 |
+
"learning_rate": 3.3024431339511375e-06,
|
| 221 |
+
"loss": 0.0712,
|
| 222 |
+
"step": 8000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 14.0,
|
| 226 |
+
"eval_accuracy": 0.936634494334872,
|
| 227 |
+
"eval_loss": 0.2976749837398529,
|
| 228 |
+
"eval_runtime": 74.536,
|
| 229 |
+
"eval_samples_per_second": 63.942,
|
| 230 |
+
"eval_steps_per_second": 7.996,
|
| 231 |
+
"step": 8344
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 14.26,
|
| 235 |
+
"learning_rate": 2.881213142375737e-06,
|
| 236 |
+
"loss": 0.0571,
|
| 237 |
+
"step": 8500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 15.0,
|
| 241 |
+
"eval_accuracy": 0.9385228703315149,
|
| 242 |
+
"eval_loss": 0.28963080048561096,
|
| 243 |
+
"eval_runtime": 75.6121,
|
| 244 |
+
"eval_samples_per_second": 63.032,
|
| 245 |
+
"eval_steps_per_second": 7.882,
|
| 246 |
+
"step": 8940
|
| 247 |
+
}
|
| 248 |
+
],
|
| 249 |
+
"logging_steps": 500,
|
| 250 |
+
"max_steps": 11920,
|
| 251 |
+
"num_train_epochs": 20,
|
| 252 |
+
"save_steps": 500,
|
| 253 |
+
"total_flos": 2.2162476716746813e+19,
|
| 254 |
+
"trial_name": null,
|
| 255 |
+
"trial_params": null
|
| 256 |
+
}
|
checkpoint-8940/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b6c916ae398b6e8eab8b778c81b098c97605d951c975dc8104cd3ba9efb0abc
|
| 3 |
+
size 4027
|
config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "omelette",
|
| 13 |
+
"1": "apple_pie",
|
| 14 |
+
"2": "Sandwich",
|
| 15 |
+
"3": "kulfi",
|
| 16 |
+
"4": "chicken_curry",
|
| 17 |
+
"5": "Fries",
|
| 18 |
+
"6": "jalebi",
|
| 19 |
+
"7": "Taquito",
|
| 20 |
+
"8": "Crispy Chicken",
|
| 21 |
+
"9": "Baked Potato",
|
| 22 |
+
"10": "kaathi_rolls",
|
| 23 |
+
"11": "masala_dosa",
|
| 24 |
+
"12": "paani_puri",
|
| 25 |
+
"13": "fried_rice",
|
| 26 |
+
"14": "chole_bhature",
|
| 27 |
+
"15": "chai",
|
| 28 |
+
"16": "Taco",
|
| 29 |
+
"17": "samosa",
|
| 30 |
+
"18": "dhokla",
|
| 31 |
+
"19": "chapati",
|
| 32 |
+
"20": "sushi",
|
| 33 |
+
"21": "pakode",
|
| 34 |
+
"22": "butter_naan",
|
| 35 |
+
"23": "momos",
|
| 36 |
+
"24": "idli",
|
| 37 |
+
"25": "pav_bhaji",
|
| 38 |
+
"26": "cheesecake",
|
| 39 |
+
"27": "Donut",
|
| 40 |
+
"28": "burger",
|
| 41 |
+
"29": "pizza",
|
| 42 |
+
"30": "dal_makhani",
|
| 43 |
+
"31": "Hot Dog",
|
| 44 |
+
"32": "ice_cream",
|
| 45 |
+
"33": "kadai_paneer"
|
| 46 |
+
},
|
| 47 |
+
"image_size": 224,
|
| 48 |
+
"initializer_range": 0.02,
|
| 49 |
+
"intermediate_size": 3072,
|
| 50 |
+
"label2id": {
|
| 51 |
+
"Baked Potato": 9,
|
| 52 |
+
"Crispy Chicken": 8,
|
| 53 |
+
"Donut": 27,
|
| 54 |
+
"Fries": 5,
|
| 55 |
+
"Hot Dog": 31,
|
| 56 |
+
"Sandwich": 2,
|
| 57 |
+
"Taco": 16,
|
| 58 |
+
"Taquito": 7,
|
| 59 |
+
"apple_pie": 1,
|
| 60 |
+
"burger": 28,
|
| 61 |
+
"butter_naan": 22,
|
| 62 |
+
"chai": 15,
|
| 63 |
+
"chapati": 19,
|
| 64 |
+
"cheesecake": 26,
|
| 65 |
+
"chicken_curry": 4,
|
| 66 |
+
"chole_bhature": 14,
|
| 67 |
+
"dal_makhani": 30,
|
| 68 |
+
"dhokla": 18,
|
| 69 |
+
"fried_rice": 13,
|
| 70 |
+
"ice_cream": 32,
|
| 71 |
+
"idli": 24,
|
| 72 |
+
"jalebi": 6,
|
| 73 |
+
"kaathi_rolls": 10,
|
| 74 |
+
"kadai_paneer": 33,
|
| 75 |
+
"kulfi": 3,
|
| 76 |
+
"masala_dosa": 11,
|
| 77 |
+
"momos": 23,
|
| 78 |
+
"omelette": 0,
|
| 79 |
+
"paani_puri": 12,
|
| 80 |
+
"pakode": 21,
|
| 81 |
+
"pav_bhaji": 25,
|
| 82 |
+
"pizza": 29,
|
| 83 |
+
"samosa": 17,
|
| 84 |
+
"sushi": 20
|
| 85 |
+
},
|
| 86 |
+
"layer_norm_eps": 1e-12,
|
| 87 |
+
"model_type": "vit",
|
| 88 |
+
"num_attention_heads": 12,
|
| 89 |
+
"num_channels": 3,
|
| 90 |
+
"num_hidden_layers": 12,
|
| 91 |
+
"patch_size": 16,
|
| 92 |
+
"problem_type": "single_label_classification",
|
| 93 |
+
"qkv_bias": true,
|
| 94 |
+
"torch_dtype": "float32",
|
| 95 |
+
"transformers_version": "4.33.0"
|
| 96 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e1a5f6f000db5299e4dcc037d681964637940cbe22a32faf0681f3190844b17
|
| 3 |
+
size 343367149
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b6c916ae398b6e8eab8b778c81b098c97605d951c975dc8104cd3ba9efb0abc
|
| 3 |
+
size 4027
|