Upload folder using huggingface_hub
Browse files- checkpoint-10020/config.json +76 -0
- checkpoint-10020/model.safetensors +3 -0
- checkpoint-10020/optimizer.pt +3 -0
- checkpoint-10020/preprocessor_config.json +22 -0
- checkpoint-10020/rng_state.pth +3 -0
- checkpoint-10020/scheduler.pt +3 -0
- checkpoint-10020/trainer_state.json +409 -0
- checkpoint-10020/training_args.bin +3 -0
- config.json +76 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- training_args.bin +3 -0
checkpoint-10020/config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "01",
|
| 13 |
+
"1": "02",
|
| 14 |
+
"2": "03",
|
| 15 |
+
"3": "04",
|
| 16 |
+
"4": "05",
|
| 17 |
+
"5": "06-07",
|
| 18 |
+
"6": "08-09",
|
| 19 |
+
"7": "08-9",
|
| 20 |
+
"8": "10-12",
|
| 21 |
+
"9": "13-15",
|
| 22 |
+
"10": "16-20",
|
| 23 |
+
"11": "21-25",
|
| 24 |
+
"12": "26-30",
|
| 25 |
+
"13": "31-35",
|
| 26 |
+
"14": "36-40",
|
| 27 |
+
"15": "41-45",
|
| 28 |
+
"16": "46-50",
|
| 29 |
+
"17": "51-55",
|
| 30 |
+
"18": "56-60",
|
| 31 |
+
"19": "61-65",
|
| 32 |
+
"20": "66-70",
|
| 33 |
+
"21": "71-80",
|
| 34 |
+
"22": "81-90",
|
| 35 |
+
"23": "90+"
|
| 36 |
+
},
|
| 37 |
+
"image_size": 224,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 3072,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"01": 0,
|
| 42 |
+
"02": 1,
|
| 43 |
+
"03": 2,
|
| 44 |
+
"04": 3,
|
| 45 |
+
"05": 4,
|
| 46 |
+
"06-07": 5,
|
| 47 |
+
"08-09": 6,
|
| 48 |
+
"08-9": 7,
|
| 49 |
+
"10-12": 8,
|
| 50 |
+
"13-15": 9,
|
| 51 |
+
"16-20": 10,
|
| 52 |
+
"21-25": 11,
|
| 53 |
+
"26-30": 12,
|
| 54 |
+
"31-35": 13,
|
| 55 |
+
"36-40": 14,
|
| 56 |
+
"41-45": 15,
|
| 57 |
+
"46-50": 16,
|
| 58 |
+
"51-55": 17,
|
| 59 |
+
"56-60": 18,
|
| 60 |
+
"61-65": 19,
|
| 61 |
+
"66-70": 20,
|
| 62 |
+
"71-80": 21,
|
| 63 |
+
"81-90": 22,
|
| 64 |
+
"90+": 23
|
| 65 |
+
},
|
| 66 |
+
"layer_norm_eps": 1e-12,
|
| 67 |
+
"model_type": "vit",
|
| 68 |
+
"num_attention_heads": 12,
|
| 69 |
+
"num_channels": 3,
|
| 70 |
+
"num_hidden_layers": 12,
|
| 71 |
+
"patch_size": 16,
|
| 72 |
+
"problem_type": "single_label_classification",
|
| 73 |
+
"qkv_bias": true,
|
| 74 |
+
"torch_dtype": "float32",
|
| 75 |
+
"transformers_version": "4.35.0"
|
| 76 |
+
}
|
checkpoint-10020/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a22def0831c81660cca9db86c3bae57d49fe05506dfb7beb2270c5fa8af17134
|
| 3 |
+
size 343291648
|
checkpoint-10020/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0b3a93ae9e09ed9eb7cc6058f798ce868ab29eb10fb8973d849dc206eb76698
|
| 3 |
+
size 686703749
|
checkpoint-10020/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-10020/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:410805409324550af0798c0afed9543ad0b881f9bf774cb384d5ee67814b7d81
|
| 3 |
+
size 14575
|
checkpoint-10020/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0255b0e5a00ff6081c15a6e17f322afdbc6a194dae395bcfe0e6a366fb97361
|
| 3 |
+
size 627
|
checkpoint-10020/trainer_state.json
ADDED
|
@@ -0,0 +1,409 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.6296087503433228,
|
| 3 |
+
"best_model_checkpoint": "facial_age_image_detection/checkpoint-10020",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 10020,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.24297489696515548,
|
| 14 |
+
"eval_loss": 2.9744021892547607,
|
| 15 |
+
"eval_runtime": 52.2658,
|
| 16 |
+
"eval_samples_per_second": 102.132,
|
| 17 |
+
"eval_steps_per_second": 3.195,
|
| 18 |
+
"step": 334
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.5,
|
| 22 |
+
"learning_rate": 2.864593781344032e-06,
|
| 23 |
+
"loss": 2.9888,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.29674035219183215,
|
| 29 |
+
"eval_loss": 2.684274673461914,
|
| 30 |
+
"eval_runtime": 53.0339,
|
| 31 |
+
"eval_samples_per_second": 100.653,
|
| 32 |
+
"eval_steps_per_second": 3.149,
|
| 33 |
+
"step": 668
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.99,
|
| 37 |
+
"learning_rate": 2.714142427281846e-06,
|
| 38 |
+
"loss": 2.5675,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"eval_accuracy": 0.31997002622705134,
|
| 44 |
+
"eval_loss": 2.4912328720092773,
|
| 45 |
+
"eval_runtime": 52.2504,
|
| 46 |
+
"eval_samples_per_second": 102.162,
|
| 47 |
+
"eval_steps_per_second": 3.196,
|
| 48 |
+
"step": 1002
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.3405769951292619,
|
| 53 |
+
"eval_loss": 2.3644516468048096,
|
| 54 |
+
"eval_runtime": 52.2527,
|
| 55 |
+
"eval_samples_per_second": 102.157,
|
| 56 |
+
"eval_steps_per_second": 3.196,
|
| 57 |
+
"step": 1336
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.49,
|
| 61 |
+
"learning_rate": 2.5636910732196588e-06,
|
| 62 |
+
"loss": 2.3316,
|
| 63 |
+
"step": 1500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 5.0,
|
| 67 |
+
"eval_accuracy": 0.3621206444361184,
|
| 68 |
+
"eval_loss": 2.266845226287842,
|
| 69 |
+
"eval_runtime": 52.3012,
|
| 70 |
+
"eval_samples_per_second": 102.063,
|
| 71 |
+
"eval_steps_per_second": 3.193,
|
| 72 |
+
"step": 1670
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.99,
|
| 76 |
+
"learning_rate": 2.4132397191574725e-06,
|
| 77 |
+
"loss": 2.185,
|
| 78 |
+
"step": 2000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.0,
|
| 82 |
+
"eval_accuracy": 0.3831022855001873,
|
| 83 |
+
"eval_loss": 2.1891231536865234,
|
| 84 |
+
"eval_runtime": 53.1986,
|
| 85 |
+
"eval_samples_per_second": 100.341,
|
| 86 |
+
"eval_steps_per_second": 3.139,
|
| 87 |
+
"step": 2004
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 7.0,
|
| 91 |
+
"eval_accuracy": 0.3939677781940802,
|
| 92 |
+
"eval_loss": 2.124483346939087,
|
| 93 |
+
"eval_runtime": 54.0657,
|
| 94 |
+
"eval_samples_per_second": 98.732,
|
| 95 |
+
"eval_steps_per_second": 3.089,
|
| 96 |
+
"step": 2338
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 7.49,
|
| 100 |
+
"learning_rate": 2.262788365095286e-06,
|
| 101 |
+
"loss": 2.0759,
|
| 102 |
+
"step": 2500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 8.0,
|
| 106 |
+
"eval_accuracy": 0.40764331210191085,
|
| 107 |
+
"eval_loss": 2.0697174072265625,
|
| 108 |
+
"eval_runtime": 52.3282,
|
| 109 |
+
"eval_samples_per_second": 102.01,
|
| 110 |
+
"eval_steps_per_second": 3.191,
|
| 111 |
+
"step": 2672
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 8.98,
|
| 115 |
+
"learning_rate": 2.1123370110330997e-06,
|
| 116 |
+
"loss": 1.9878,
|
| 117 |
+
"step": 3000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 9.0,
|
| 121 |
+
"eval_accuracy": 0.4194454852004496,
|
| 122 |
+
"eval_loss": 2.019850015640259,
|
| 123 |
+
"eval_runtime": 52.333,
|
| 124 |
+
"eval_samples_per_second": 102.001,
|
| 125 |
+
"eval_steps_per_second": 3.191,
|
| 126 |
+
"step": 3006
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 10.0,
|
| 130 |
+
"eval_accuracy": 0.43368302735106784,
|
| 131 |
+
"eval_loss": 1.9797377586364746,
|
| 132 |
+
"eval_runtime": 52.4208,
|
| 133 |
+
"eval_samples_per_second": 101.83,
|
| 134 |
+
"eval_steps_per_second": 3.186,
|
| 135 |
+
"step": 3340
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.48,
|
| 139 |
+
"learning_rate": 1.9618856569709126e-06,
|
| 140 |
+
"loss": 1.9168,
|
| 141 |
+
"step": 3500
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 11.0,
|
| 145 |
+
"eval_accuracy": 0.43349569127013865,
|
| 146 |
+
"eval_loss": 1.9416717290878296,
|
| 147 |
+
"eval_runtime": 52.2275,
|
| 148 |
+
"eval_samples_per_second": 102.207,
|
| 149 |
+
"eval_steps_per_second": 3.198,
|
| 150 |
+
"step": 3674
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 11.98,
|
| 154 |
+
"learning_rate": 1.8114343029087262e-06,
|
| 155 |
+
"loss": 1.8504,
|
| 156 |
+
"step": 4000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 12.0,
|
| 160 |
+
"eval_accuracy": 0.45185462720119896,
|
| 161 |
+
"eval_loss": 1.9020978212356567,
|
| 162 |
+
"eval_runtime": 52.0691,
|
| 163 |
+
"eval_samples_per_second": 102.518,
|
| 164 |
+
"eval_steps_per_second": 3.207,
|
| 165 |
+
"step": 4008
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 13.0,
|
| 169 |
+
"eval_accuracy": 0.45766204571000374,
|
| 170 |
+
"eval_loss": 1.868658185005188,
|
| 171 |
+
"eval_runtime": 52.1907,
|
| 172 |
+
"eval_samples_per_second": 102.279,
|
| 173 |
+
"eval_steps_per_second": 3.2,
|
| 174 |
+
"step": 4342
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 13.47,
|
| 178 |
+
"learning_rate": 1.6609829488465398e-06,
|
| 179 |
+
"loss": 1.7952,
|
| 180 |
+
"step": 4500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 14.0,
|
| 184 |
+
"eval_accuracy": 0.4644061446234545,
|
| 185 |
+
"eval_loss": 1.8404171466827393,
|
| 186 |
+
"eval_runtime": 52.0362,
|
| 187 |
+
"eval_samples_per_second": 102.582,
|
| 188 |
+
"eval_steps_per_second": 3.209,
|
| 189 |
+
"step": 4676
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 14.97,
|
| 193 |
+
"learning_rate": 1.510531594784353e-06,
|
| 194 |
+
"loss": 1.7469,
|
| 195 |
+
"step": 5000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 15.0,
|
| 199 |
+
"eval_accuracy": 0.4668415136755339,
|
| 200 |
+
"eval_loss": 1.814427137374878,
|
| 201 |
+
"eval_runtime": 52.0939,
|
| 202 |
+
"eval_samples_per_second": 102.469,
|
| 203 |
+
"eval_steps_per_second": 3.206,
|
| 204 |
+
"step": 5010
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 16.0,
|
| 208 |
+
"eval_accuracy": 0.46796553016110903,
|
| 209 |
+
"eval_loss": 1.7911080121994019,
|
| 210 |
+
"eval_runtime": 53.1692,
|
| 211 |
+
"eval_samples_per_second": 100.396,
|
| 212 |
+
"eval_steps_per_second": 3.141,
|
| 213 |
+
"step": 5344
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 16.47,
|
| 217 |
+
"learning_rate": 1.3600802407221665e-06,
|
| 218 |
+
"loss": 1.7033,
|
| 219 |
+
"step": 5500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 17.0,
|
| 223 |
+
"eval_accuracy": 0.4795803671787186,
|
| 224 |
+
"eval_loss": 1.7677799463272095,
|
| 225 |
+
"eval_runtime": 51.8901,
|
| 226 |
+
"eval_samples_per_second": 102.871,
|
| 227 |
+
"eval_steps_per_second": 3.218,
|
| 228 |
+
"step": 5678
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 17.96,
|
| 232 |
+
"learning_rate": 1.20962888665998e-06,
|
| 233 |
+
"loss": 1.6621,
|
| 234 |
+
"step": 6000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 18.0,
|
| 238 |
+
"eval_accuracy": 0.4855751217684526,
|
| 239 |
+
"eval_loss": 1.748055338859558,
|
| 240 |
+
"eval_runtime": 52.1275,
|
| 241 |
+
"eval_samples_per_second": 102.403,
|
| 242 |
+
"eval_steps_per_second": 3.204,
|
| 243 |
+
"step": 6012
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 19.0,
|
| 247 |
+
"eval_accuracy": 0.48651180217309853,
|
| 248 |
+
"eval_loss": 1.7302188873291016,
|
| 249 |
+
"eval_runtime": 52.0882,
|
| 250 |
+
"eval_samples_per_second": 102.48,
|
| 251 |
+
"eval_steps_per_second": 3.206,
|
| 252 |
+
"step": 6346
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 19.46,
|
| 256 |
+
"learning_rate": 1.0591775325977935e-06,
|
| 257 |
+
"loss": 1.6249,
|
| 258 |
+
"step": 6500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 20.0,
|
| 262 |
+
"eval_accuracy": 0.4866991382540277,
|
| 263 |
+
"eval_loss": 1.7110319137573242,
|
| 264 |
+
"eval_runtime": 52.1234,
|
| 265 |
+
"eval_samples_per_second": 102.411,
|
| 266 |
+
"eval_steps_per_second": 3.204,
|
| 267 |
+
"step": 6680
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 20.96,
|
| 271 |
+
"learning_rate": 9.087261785356068e-07,
|
| 272 |
+
"loss": 1.6,
|
| 273 |
+
"step": 7000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 21.0,
|
| 277 |
+
"eval_accuracy": 0.49587860621955787,
|
| 278 |
+
"eval_loss": 1.6950350999832153,
|
| 279 |
+
"eval_runtime": 52.517,
|
| 280 |
+
"eval_samples_per_second": 101.643,
|
| 281 |
+
"eval_steps_per_second": 3.18,
|
| 282 |
+
"step": 7014
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 22.0,
|
| 286 |
+
"eval_accuracy": 0.4971899587860622,
|
| 287 |
+
"eval_loss": 1.683102011680603,
|
| 288 |
+
"eval_runtime": 52.8184,
|
| 289 |
+
"eval_samples_per_second": 101.063,
|
| 290 |
+
"eval_steps_per_second": 3.162,
|
| 291 |
+
"step": 7348
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 22.46,
|
| 295 |
+
"learning_rate": 7.582748244734203e-07,
|
| 296 |
+
"loss": 1.5698,
|
| 297 |
+
"step": 7500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 23.0,
|
| 301 |
+
"eval_accuracy": 0.5018733608092919,
|
| 302 |
+
"eval_loss": 1.6692556142807007,
|
| 303 |
+
"eval_runtime": 52.387,
|
| 304 |
+
"eval_samples_per_second": 101.895,
|
| 305 |
+
"eval_steps_per_second": 3.188,
|
| 306 |
+
"step": 7682
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 23.95,
|
| 310 |
+
"learning_rate": 6.078234704112337e-07,
|
| 311 |
+
"loss": 1.5493,
|
| 312 |
+
"step": 8000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 24.0,
|
| 316 |
+
"eval_accuracy": 0.49625327838141625,
|
| 317 |
+
"eval_loss": 1.659037709236145,
|
| 318 |
+
"eval_runtime": 52.3852,
|
| 319 |
+
"eval_samples_per_second": 101.899,
|
| 320 |
+
"eval_steps_per_second": 3.188,
|
| 321 |
+
"step": 8016
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 25.0,
|
| 325 |
+
"eval_accuracy": 0.5084301236418134,
|
| 326 |
+
"eval_loss": 1.650451421737671,
|
| 327 |
+
"eval_runtime": 51.9831,
|
| 328 |
+
"eval_samples_per_second": 102.687,
|
| 329 |
+
"eval_steps_per_second": 3.213,
|
| 330 |
+
"step": 8350
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 25.45,
|
| 334 |
+
"learning_rate": 4.5737211634904716e-07,
|
| 335 |
+
"loss": 1.5313,
|
| 336 |
+
"step": 8500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 26.0,
|
| 340 |
+
"eval_accuracy": 0.5050580741850881,
|
| 341 |
+
"eval_loss": 1.6430058479309082,
|
| 342 |
+
"eval_runtime": 52.0136,
|
| 343 |
+
"eval_samples_per_second": 102.627,
|
| 344 |
+
"eval_steps_per_second": 3.211,
|
| 345 |
+
"step": 8684
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 26.95,
|
| 349 |
+
"learning_rate": 3.069207622868606e-07,
|
| 350 |
+
"loss": 1.5177,
|
| 351 |
+
"step": 9000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 27.0,
|
| 355 |
+
"eval_accuracy": 0.5063694267515924,
|
| 356 |
+
"eval_loss": 1.6367906332015991,
|
| 357 |
+
"eval_runtime": 52.2435,
|
| 358 |
+
"eval_samples_per_second": 102.175,
|
| 359 |
+
"eval_steps_per_second": 3.197,
|
| 360 |
+
"step": 9018
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 28.0,
|
| 364 |
+
"eval_accuracy": 0.5076807793180966,
|
| 365 |
+
"eval_loss": 1.633717656135559,
|
| 366 |
+
"eval_runtime": 52.2304,
|
| 367 |
+
"eval_samples_per_second": 102.201,
|
| 368 |
+
"eval_steps_per_second": 3.197,
|
| 369 |
+
"step": 9352
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 28.44,
|
| 373 |
+
"learning_rate": 1.5646940822467403e-07,
|
| 374 |
+
"loss": 1.5101,
|
| 375 |
+
"step": 9500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 29.0,
|
| 379 |
+
"eval_accuracy": 0.5069314349943799,
|
| 380 |
+
"eval_loss": 1.6314198970794678,
|
| 381 |
+
"eval_runtime": 52.5904,
|
| 382 |
+
"eval_samples_per_second": 101.501,
|
| 383 |
+
"eval_steps_per_second": 3.175,
|
| 384 |
+
"step": 9686
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 29.94,
|
| 388 |
+
"learning_rate": 6.018054162487462e-09,
|
| 389 |
+
"loss": 1.5,
|
| 390 |
+
"step": 10000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 30.0,
|
| 394 |
+
"eval_accuracy": 0.5050580741850881,
|
| 395 |
+
"eval_loss": 1.6296087503433228,
|
| 396 |
+
"eval_runtime": 52.2229,
|
| 397 |
+
"eval_samples_per_second": 102.216,
|
| 398 |
+
"eval_steps_per_second": 3.198,
|
| 399 |
+
"step": 10020
|
| 400 |
+
}
|
| 401 |
+
],
|
| 402 |
+
"logging_steps": 500,
|
| 403 |
+
"max_steps": 10020,
|
| 404 |
+
"num_train_epochs": 30,
|
| 405 |
+
"save_steps": 500,
|
| 406 |
+
"total_flos": 4.964340605762765e+19,
|
| 407 |
+
"trial_name": null,
|
| 408 |
+
"trial_params": null
|
| 409 |
+
}
|
checkpoint-10020/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7c9a1b990012db059eeb2765cb4f742d0ae6ffaa2dbd995adacf469ba98c917
|
| 3 |
+
size 4091
|
config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "01",
|
| 13 |
+
"1": "02",
|
| 14 |
+
"2": "03",
|
| 15 |
+
"3": "04",
|
| 16 |
+
"4": "05",
|
| 17 |
+
"5": "06-07",
|
| 18 |
+
"6": "08-09",
|
| 19 |
+
"7": "08-9",
|
| 20 |
+
"8": "10-12",
|
| 21 |
+
"9": "13-15",
|
| 22 |
+
"10": "16-20",
|
| 23 |
+
"11": "21-25",
|
| 24 |
+
"12": "26-30",
|
| 25 |
+
"13": "31-35",
|
| 26 |
+
"14": "36-40",
|
| 27 |
+
"15": "41-45",
|
| 28 |
+
"16": "46-50",
|
| 29 |
+
"17": "51-55",
|
| 30 |
+
"18": "56-60",
|
| 31 |
+
"19": "61-65",
|
| 32 |
+
"20": "66-70",
|
| 33 |
+
"21": "71-80",
|
| 34 |
+
"22": "81-90",
|
| 35 |
+
"23": "90+"
|
| 36 |
+
},
|
| 37 |
+
"image_size": 224,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 3072,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"01": 0,
|
| 42 |
+
"02": 1,
|
| 43 |
+
"03": 2,
|
| 44 |
+
"04": 3,
|
| 45 |
+
"05": 4,
|
| 46 |
+
"06-07": 5,
|
| 47 |
+
"08-09": 6,
|
| 48 |
+
"08-9": 7,
|
| 49 |
+
"10-12": 8,
|
| 50 |
+
"13-15": 9,
|
| 51 |
+
"16-20": 10,
|
| 52 |
+
"21-25": 11,
|
| 53 |
+
"26-30": 12,
|
| 54 |
+
"31-35": 13,
|
| 55 |
+
"36-40": 14,
|
| 56 |
+
"41-45": 15,
|
| 57 |
+
"46-50": 16,
|
| 58 |
+
"51-55": 17,
|
| 59 |
+
"56-60": 18,
|
| 60 |
+
"61-65": 19,
|
| 61 |
+
"66-70": 20,
|
| 62 |
+
"71-80": 21,
|
| 63 |
+
"81-90": 22,
|
| 64 |
+
"90+": 23
|
| 65 |
+
},
|
| 66 |
+
"layer_norm_eps": 1e-12,
|
| 67 |
+
"model_type": "vit",
|
| 68 |
+
"num_attention_heads": 12,
|
| 69 |
+
"num_channels": 3,
|
| 70 |
+
"num_hidden_layers": 12,
|
| 71 |
+
"patch_size": 16,
|
| 72 |
+
"problem_type": "single_label_classification",
|
| 73 |
+
"qkv_bias": true,
|
| 74 |
+
"torch_dtype": "float32",
|
| 75 |
+
"transformers_version": "4.35.0"
|
| 76 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a22def0831c81660cca9db86c3bae57d49fe05506dfb7beb2270c5fa8af17134
|
| 3 |
+
size 343291648
|
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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7c9a1b990012db059eeb2765cb4f742d0ae6ffaa2dbd995adacf469ba98c917
|
| 3 |
+
size 4091
|