Upload folder using huggingface_hub
Browse files- checkpoint-13224/config.json +34 -0
- checkpoint-13224/model.safetensors +3 -0
- checkpoint-13224/optimizer.pt +3 -0
- checkpoint-13224/preprocessor_config.json +22 -0
- checkpoint-13224/rng_state.pth +3 -0
- checkpoint-13224/scheduler.pt +3 -0
- checkpoint-13224/trainer_state.json +438 -0
- checkpoint-13224/training_args.bin +3 -0
- config.json +2 -2
- model.safetensors +1 -1
- training_args.bin +2 -2
checkpoint-13224/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dima806/faces_age_detection",
|
| 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": "MIDDLE",
|
| 13 |
+
"1": "YOUNG",
|
| 14 |
+
"2": "OLD"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"MIDDLE": 0,
|
| 21 |
+
"OLD": 2,
|
| 22 |
+
"YOUNG": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"model_type": "vit",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_channels": 3,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qkv_bias": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.36.1"
|
| 34 |
+
}
|
checkpoint-13224/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d3a7c9d3c224dfc90448da0b1a9555f833fa9c1980b2cc388f42adc627da263
|
| 3 |
+
size 343227052
|
checkpoint-13224/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb5e7dddebdfec38301e806c98e0c463e396be595d6c4ddb73ce13929f19e3f4
|
| 3 |
+
size 686574597
|
checkpoint-13224/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-13224/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50ca26edcd69f19c8e4ab09901f196b325e0284845bf6127ec75b8ef2f7dede4
|
| 3 |
+
size 14575
|
checkpoint-13224/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9fccbf8a5a7dc04e2a6a3d1769106d34d29498af8e69d7de8090bbe37ff77f8
|
| 3 |
+
size 627
|
checkpoint-13224/trainer_state.json
ADDED
|
@@ -0,0 +1,438 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.27537301182746887,
|
| 3 |
+
"best_model_checkpoint": "faces_age_detection/checkpoint-13224",
|
| 4 |
+
"epoch": 29.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 13224,
|
| 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": 0.8806292412091302,
|
| 14 |
+
"eval_loss": 0.3289386034011841,
|
| 15 |
+
"eval_runtime": 29.1731,
|
| 16 |
+
"eval_samples_per_second": 111.13,
|
| 17 |
+
"eval_steps_per_second": 3.496,
|
| 18 |
+
"step": 456
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.1,
|
| 22 |
+
"learning_rate": 1.9339691856199557e-06,
|
| 23 |
+
"loss": 0.3578,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.879086983343615,
|
| 29 |
+
"eval_loss": 0.3256358802318573,
|
| 30 |
+
"eval_runtime": 29.8484,
|
| 31 |
+
"eval_samples_per_second": 108.615,
|
| 32 |
+
"eval_steps_per_second": 3.417,
|
| 33 |
+
"step": 912
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.19,
|
| 37 |
+
"learning_rate": 1.8606016140865737e-06,
|
| 38 |
+
"loss": 0.2998,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"eval_accuracy": 0.8834053053670574,
|
| 44 |
+
"eval_loss": 0.3201422393321991,
|
| 45 |
+
"eval_runtime": 29.3669,
|
| 46 |
+
"eval_samples_per_second": 110.396,
|
| 47 |
+
"eval_steps_per_second": 3.473,
|
| 48 |
+
"step": 1368
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.29,
|
| 52 |
+
"learning_rate": 1.7872340425531913e-06,
|
| 53 |
+
"loss": 0.2666,
|
| 54 |
+
"step": 1500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.0,
|
| 58 |
+
"eval_accuracy": 0.8867982726711906,
|
| 59 |
+
"eval_loss": 0.31441426277160645,
|
| 60 |
+
"eval_runtime": 29.5521,
|
| 61 |
+
"eval_samples_per_second": 109.705,
|
| 62 |
+
"eval_steps_per_second": 3.452,
|
| 63 |
+
"step": 1824
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.39,
|
| 67 |
+
"learning_rate": 1.7138664710198092e-06,
|
| 68 |
+
"loss": 0.2445,
|
| 69 |
+
"step": 2000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.0,
|
| 73 |
+
"eval_accuracy": 0.8840222085132634,
|
| 74 |
+
"eval_loss": 0.31040704250335693,
|
| 75 |
+
"eval_runtime": 29.3243,
|
| 76 |
+
"eval_samples_per_second": 110.557,
|
| 77 |
+
"eval_steps_per_second": 3.478,
|
| 78 |
+
"step": 2280
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.48,
|
| 82 |
+
"learning_rate": 1.6404988994864268e-06,
|
| 83 |
+
"loss": 0.2307,
|
| 84 |
+
"step": 2500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.0,
|
| 88 |
+
"eval_accuracy": 0.8756940160394818,
|
| 89 |
+
"eval_loss": 0.31916671991348267,
|
| 90 |
+
"eval_runtime": 29.1138,
|
| 91 |
+
"eval_samples_per_second": 111.356,
|
| 92 |
+
"eval_steps_per_second": 3.503,
|
| 93 |
+
"step": 2736
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 6.58,
|
| 97 |
+
"learning_rate": 1.5671313279530447e-06,
|
| 98 |
+
"loss": 0.2218,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.0,
|
| 103 |
+
"eval_accuracy": 0.8821714990746453,
|
| 104 |
+
"eval_loss": 0.30659398436546326,
|
| 105 |
+
"eval_runtime": 29.0887,
|
| 106 |
+
"eval_samples_per_second": 111.452,
|
| 107 |
+
"eval_steps_per_second": 3.507,
|
| 108 |
+
"step": 3192
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 7.68,
|
| 112 |
+
"learning_rate": 1.4937637564196623e-06,
|
| 113 |
+
"loss": 0.2007,
|
| 114 |
+
"step": 3500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 8.0,
|
| 118 |
+
"eval_accuracy": 0.8793954349167181,
|
| 119 |
+
"eval_loss": 0.3129652738571167,
|
| 120 |
+
"eval_runtime": 28.3857,
|
| 121 |
+
"eval_samples_per_second": 114.212,
|
| 122 |
+
"eval_steps_per_second": 3.593,
|
| 123 |
+
"step": 3648
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 8.77,
|
| 127 |
+
"learning_rate": 1.4203961848862801e-06,
|
| 128 |
+
"loss": 0.192,
|
| 129 |
+
"step": 4000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 9.0,
|
| 133 |
+
"eval_accuracy": 0.8809376927822332,
|
| 134 |
+
"eval_loss": 0.31223684549331665,
|
| 135 |
+
"eval_runtime": 28.6423,
|
| 136 |
+
"eval_samples_per_second": 113.189,
|
| 137 |
+
"eval_steps_per_second": 3.561,
|
| 138 |
+
"step": 4104
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 9.87,
|
| 142 |
+
"learning_rate": 1.3470286133528978e-06,
|
| 143 |
+
"loss": 0.1832,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 10.0,
|
| 148 |
+
"eval_accuracy": 0.8883405305367057,
|
| 149 |
+
"eval_loss": 0.29440754652023315,
|
| 150 |
+
"eval_runtime": 29.0492,
|
| 151 |
+
"eval_samples_per_second": 111.604,
|
| 152 |
+
"eval_steps_per_second": 3.511,
|
| 153 |
+
"step": 4560
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 10.96,
|
| 157 |
+
"learning_rate": 1.2736610418195158e-06,
|
| 158 |
+
"loss": 0.1743,
|
| 159 |
+
"step": 5000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 11.0,
|
| 163 |
+
"eval_accuracy": 0.8815545959284392,
|
| 164 |
+
"eval_loss": 0.3053087294101715,
|
| 165 |
+
"eval_runtime": 29.3331,
|
| 166 |
+
"eval_samples_per_second": 110.523,
|
| 167 |
+
"eval_steps_per_second": 3.477,
|
| 168 |
+
"step": 5016
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 12.0,
|
| 172 |
+
"eval_accuracy": 0.8858729179518815,
|
| 173 |
+
"eval_loss": 0.2922166883945465,
|
| 174 |
+
"eval_runtime": 29.148,
|
| 175 |
+
"eval_samples_per_second": 111.225,
|
| 176 |
+
"eval_steps_per_second": 3.499,
|
| 177 |
+
"step": 5472
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 12.06,
|
| 181 |
+
"learning_rate": 1.2002934702861334e-06,
|
| 182 |
+
"loss": 0.1668,
|
| 183 |
+
"step": 5500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 13.0,
|
| 187 |
+
"eval_accuracy": 0.8815545959284392,
|
| 188 |
+
"eval_loss": 0.3020872473716736,
|
| 189 |
+
"eval_runtime": 29.262,
|
| 190 |
+
"eval_samples_per_second": 110.792,
|
| 191 |
+
"eval_steps_per_second": 3.486,
|
| 192 |
+
"step": 5928
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 13.16,
|
| 196 |
+
"learning_rate": 1.1269258987527513e-06,
|
| 197 |
+
"loss": 0.1608,
|
| 198 |
+
"step": 6000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 14.0,
|
| 202 |
+
"eval_accuracy": 0.8830968537939543,
|
| 203 |
+
"eval_loss": 0.3037404716014862,
|
| 204 |
+
"eval_runtime": 29.0749,
|
| 205 |
+
"eval_samples_per_second": 111.505,
|
| 206 |
+
"eval_steps_per_second": 3.508,
|
| 207 |
+
"step": 6384
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 14.25,
|
| 211 |
+
"learning_rate": 1.053558327219369e-06,
|
| 212 |
+
"loss": 0.1563,
|
| 213 |
+
"step": 6500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 15.0,
|
| 217 |
+
"eval_accuracy": 0.8843306600863664,
|
| 218 |
+
"eval_loss": 0.29694926738739014,
|
| 219 |
+
"eval_runtime": 29.4263,
|
| 220 |
+
"eval_samples_per_second": 110.173,
|
| 221 |
+
"eval_steps_per_second": 3.466,
|
| 222 |
+
"step": 6840
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 15.35,
|
| 226 |
+
"learning_rate": 9.801907556859868e-07,
|
| 227 |
+
"loss": 0.1467,
|
| 228 |
+
"step": 7000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 16.0,
|
| 232 |
+
"eval_accuracy": 0.8877236273904997,
|
| 233 |
+
"eval_loss": 0.29596608877182007,
|
| 234 |
+
"eval_runtime": 29.2838,
|
| 235 |
+
"eval_samples_per_second": 110.71,
|
| 236 |
+
"eval_steps_per_second": 3.483,
|
| 237 |
+
"step": 7296
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 16.45,
|
| 241 |
+
"learning_rate": 9.068231841526045e-07,
|
| 242 |
+
"loss": 0.139,
|
| 243 |
+
"step": 7500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 17.0,
|
| 247 |
+
"eval_accuracy": 0.8864898210980876,
|
| 248 |
+
"eval_loss": 0.2912845313549042,
|
| 249 |
+
"eval_runtime": 29.0512,
|
| 250 |
+
"eval_samples_per_second": 111.596,
|
| 251 |
+
"eval_steps_per_second": 3.511,
|
| 252 |
+
"step": 7752
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 17.54,
|
| 256 |
+
"learning_rate": 8.334556126192222e-07,
|
| 257 |
+
"loss": 0.1363,
|
| 258 |
+
"step": 8000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 18.0,
|
| 262 |
+
"eval_accuracy": 0.891425046267736,
|
| 263 |
+
"eval_loss": 0.2851228415966034,
|
| 264 |
+
"eval_runtime": 29.8791,
|
| 265 |
+
"eval_samples_per_second": 108.504,
|
| 266 |
+
"eval_steps_per_second": 3.414,
|
| 267 |
+
"step": 8208
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 18.64,
|
| 271 |
+
"learning_rate": 7.6008804108584e-07,
|
| 272 |
+
"loss": 0.1283,
|
| 273 |
+
"step": 8500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 19.0,
|
| 277 |
+
"eval_accuracy": 0.892350400987045,
|
| 278 |
+
"eval_loss": 0.28452929854393005,
|
| 279 |
+
"eval_runtime": 29.4229,
|
| 280 |
+
"eval_samples_per_second": 110.186,
|
| 281 |
+
"eval_steps_per_second": 3.467,
|
| 282 |
+
"step": 8664
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 19.74,
|
| 286 |
+
"learning_rate": 6.867204695524578e-07,
|
| 287 |
+
"loss": 0.1302,
|
| 288 |
+
"step": 9000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 20.0,
|
| 292 |
+
"eval_accuracy": 0.8901912399753239,
|
| 293 |
+
"eval_loss": 0.28534042835235596,
|
| 294 |
+
"eval_runtime": 29.1008,
|
| 295 |
+
"eval_samples_per_second": 111.406,
|
| 296 |
+
"eval_steps_per_second": 3.505,
|
| 297 |
+
"step": 9120
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 20.83,
|
| 301 |
+
"learning_rate": 6.133528980190756e-07,
|
| 302 |
+
"loss": 0.1269,
|
| 303 |
+
"step": 9500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 21.0,
|
| 307 |
+
"eval_accuracy": 0.892041949413942,
|
| 308 |
+
"eval_loss": 0.28531745076179504,
|
| 309 |
+
"eval_runtime": 28.8168,
|
| 310 |
+
"eval_samples_per_second": 112.504,
|
| 311 |
+
"eval_steps_per_second": 3.54,
|
| 312 |
+
"step": 9576
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 21.93,
|
| 316 |
+
"learning_rate": 5.399853264856933e-07,
|
| 317 |
+
"loss": 0.1211,
|
| 318 |
+
"step": 10000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 22.0,
|
| 322 |
+
"eval_accuracy": 0.892041949413942,
|
| 323 |
+
"eval_loss": 0.2809159457683563,
|
| 324 |
+
"eval_runtime": 28.7701,
|
| 325 |
+
"eval_samples_per_second": 112.686,
|
| 326 |
+
"eval_steps_per_second": 3.545,
|
| 327 |
+
"step": 10032
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 23.0,
|
| 331 |
+
"eval_accuracy": 0.8892658852560148,
|
| 332 |
+
"eval_loss": 0.28494611382484436,
|
| 333 |
+
"eval_runtime": 28.5362,
|
| 334 |
+
"eval_samples_per_second": 113.61,
|
| 335 |
+
"eval_steps_per_second": 3.574,
|
| 336 |
+
"step": 10488
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 23.03,
|
| 340 |
+
"learning_rate": 4.6661775495231103e-07,
|
| 341 |
+
"loss": 0.1199,
|
| 342 |
+
"step": 10500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 24.0,
|
| 346 |
+
"eval_accuracy": 0.8942011104256632,
|
| 347 |
+
"eval_loss": 0.2793309986591339,
|
| 348 |
+
"eval_runtime": 28.7961,
|
| 349 |
+
"eval_samples_per_second": 112.585,
|
| 350 |
+
"eval_steps_per_second": 3.542,
|
| 351 |
+
"step": 10944
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 24.12,
|
| 355 |
+
"learning_rate": 3.932501834189288e-07,
|
| 356 |
+
"loss": 0.1197,
|
| 357 |
+
"step": 11000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 25.0,
|
| 361 |
+
"eval_accuracy": 0.8948180135718692,
|
| 362 |
+
"eval_loss": 0.2778417766094208,
|
| 363 |
+
"eval_runtime": 27.4503,
|
| 364 |
+
"eval_samples_per_second": 118.105,
|
| 365 |
+
"eval_steps_per_second": 3.716,
|
| 366 |
+
"step": 11400
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 25.22,
|
| 370 |
+
"learning_rate": 3.1988261188554655e-07,
|
| 371 |
+
"loss": 0.1163,
|
| 372 |
+
"step": 11500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 26.0,
|
| 376 |
+
"eval_accuracy": 0.8960518198642813,
|
| 377 |
+
"eval_loss": 0.27623382210731506,
|
| 378 |
+
"eval_runtime": 27.6199,
|
| 379 |
+
"eval_samples_per_second": 117.379,
|
| 380 |
+
"eval_steps_per_second": 3.693,
|
| 381 |
+
"step": 11856
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 26.32,
|
| 385 |
+
"learning_rate": 2.4651504035216434e-07,
|
| 386 |
+
"loss": 0.1152,
|
| 387 |
+
"step": 12000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 27.0,
|
| 391 |
+
"eval_accuracy": 0.8963602714373843,
|
| 392 |
+
"eval_loss": 0.2759145498275757,
|
| 393 |
+
"eval_runtime": 29.0519,
|
| 394 |
+
"eval_samples_per_second": 111.594,
|
| 395 |
+
"eval_steps_per_second": 3.511,
|
| 396 |
+
"step": 12312
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 27.41,
|
| 400 |
+
"learning_rate": 1.7314746881878208e-07,
|
| 401 |
+
"loss": 0.1105,
|
| 402 |
+
"step": 12500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 28.0,
|
| 406 |
+
"eval_accuracy": 0.8969771745835904,
|
| 407 |
+
"eval_loss": 0.27611085772514343,
|
| 408 |
+
"eval_runtime": 27.509,
|
| 409 |
+
"eval_samples_per_second": 117.852,
|
| 410 |
+
"eval_steps_per_second": 3.708,
|
| 411 |
+
"step": 12768
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 28.51,
|
| 415 |
+
"learning_rate": 9.977989728539984e-08,
|
| 416 |
+
"loss": 0.11,
|
| 417 |
+
"step": 13000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 29.0,
|
| 421 |
+
"eval_accuracy": 0.8969771745835904,
|
| 422 |
+
"eval_loss": 0.27537301182746887,
|
| 423 |
+
"eval_runtime": 28.0691,
|
| 424 |
+
"eval_samples_per_second": 115.501,
|
| 425 |
+
"eval_steps_per_second": 3.634,
|
| 426 |
+
"step": 13224
|
| 427 |
+
}
|
| 428 |
+
],
|
| 429 |
+
"logging_steps": 500,
|
| 430 |
+
"max_steps": 13680,
|
| 431 |
+
"num_input_tokens_seen": 0,
|
| 432 |
+
"num_train_epochs": 30,
|
| 433 |
+
"save_steps": 500,
|
| 434 |
+
"total_flos": 6.555338630367276e+19,
|
| 435 |
+
"train_batch_size": 64,
|
| 436 |
+
"trial_name": null,
|
| 437 |
+
"trial_params": null
|
| 438 |
+
}
|
checkpoint-13224/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bd72a040a5273c5a59914a678aa821a7674b174f7cddfede528074dbb317864
|
| 3 |
+
size 4219
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"ViTForImageClassification"
|
| 5 |
],
|
|
@@ -30,5 +30,5 @@
|
|
| 30 |
"problem_type": "single_label_classification",
|
| 31 |
"qkv_bias": true,
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
-
"transformers_version": "4.
|
| 34 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "dima806/faces_age_detection",
|
| 3 |
"architectures": [
|
| 4 |
"ViTForImageClassification"
|
| 5 |
],
|
|
|
|
| 30 |
"problem_type": "single_label_classification",
|
| 31 |
"qkv_bias": true,
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.36.1"
|
| 34 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343227052
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d3a7c9d3c224dfc90448da0b1a9555f833fa9c1980b2cc388f42adc627da263
|
| 3 |
size 343227052
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bd72a040a5273c5a59914a678aa821a7674b174f7cddfede528074dbb317864
|
| 3 |
+
size 4219
|