Upload folder using huggingface_hub
Browse files- checkpoint-28722/config.json +32 -0
- checkpoint-28722/model.safetensors +3 -0
- checkpoint-28722/optimizer.pt +3 -0
- checkpoint-28722/preprocessor_config.json +22 -0
- checkpoint-28722/rng_state.pth +3 -0
- checkpoint-28722/scheduler.pt +3 -0
- checkpoint-28722/trainer_state.json +492 -0
- checkpoint-28722/training_args.bin +3 -0
- config.json +1 -1
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-28722/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dima806/man_woman_face_image_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": "man",
|
| 13 |
+
"1": "woman"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"man": 0,
|
| 20 |
+
"woman": 1
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qkv_bias": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.46.0"
|
| 32 |
+
}
|
checkpoint-28722/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76a0e858198cf9bc5c049b946990a31fbcfae443b96421d92b8311418245180c
|
| 3 |
+
size 343223968
|
checkpoint-28722/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fde8352e05b54c513e88c2311777159e76dc24bb7c9f263bba0c11611c6cea9
|
| 3 |
+
size 686568453
|
checkpoint-28722/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-28722/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e81283754b3e014a50aa833e04a38cc4850ced3758ae7e550611ef88fb4d0b88
|
| 3 |
+
size 14575
|
checkpoint-28722/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdc1feea2633691c8da122cd31d11454ec918aa70986cde883ab8e5441f011c9
|
| 3 |
+
size 627
|
checkpoint-28722/trainer_state.json
ADDED
|
@@ -0,0 +1,492 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.046924859285354614,
|
| 3 |
+
"best_model_checkpoint": "man_woman_face_image_detection/checkpoint-28722",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 28722,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.10444955086693128,
|
| 13 |
+
"grad_norm": 0.17686675488948822,
|
| 14 |
+
"learning_rate": 6.89013671875e-07,
|
| 15 |
+
"loss": 0.1192,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.20889910173386256,
|
| 20 |
+
"grad_norm": 7.6029133796691895,
|
| 21 |
+
"learning_rate": 6.76806640625e-07,
|
| 22 |
+
"loss": 0.1074,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3133486526007938,
|
| 27 |
+
"grad_norm": 0.25385862588882446,
|
| 28 |
+
"learning_rate": 6.645996093749999e-07,
|
| 29 |
+
"loss": 0.0978,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4177982034677251,
|
| 34 |
+
"grad_norm": 1.1110018491744995,
|
| 35 |
+
"learning_rate": 6.52392578125e-07,
|
| 36 |
+
"loss": 0.0842,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5222477543346563,
|
| 41 |
+
"grad_norm": 0.5810139179229736,
|
| 42 |
+
"learning_rate": 6.40185546875e-07,
|
| 43 |
+
"loss": 0.0862,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6266973052015876,
|
| 48 |
+
"grad_norm": 5.968545436859131,
|
| 49 |
+
"learning_rate": 6.279785156249999e-07,
|
| 50 |
+
"loss": 0.0834,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7311468560685189,
|
| 55 |
+
"grad_norm": 2.3612782955169678,
|
| 56 |
+
"learning_rate": 6.15771484375e-07,
|
| 57 |
+
"loss": 0.0788,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.8355964069354502,
|
| 62 |
+
"grad_norm": 2.7137603759765625,
|
| 63 |
+
"learning_rate": 6.03564453125e-07,
|
| 64 |
+
"loss": 0.0815,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.9400459578023814,
|
| 69 |
+
"grad_norm": 2.546800374984741,
|
| 70 |
+
"learning_rate": 5.91357421875e-07,
|
| 71 |
+
"loss": 0.0714,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.0,
|
| 76 |
+
"eval_accuracy": 0.984920292977165,
|
| 77 |
+
"eval_loss": 0.051657598465681076,
|
| 78 |
+
"eval_model_preparation_time": 0.0052,
|
| 79 |
+
"eval_runtime": 1021.407,
|
| 80 |
+
"eval_samples_per_second": 99.984,
|
| 81 |
+
"eval_steps_per_second": 12.498,
|
| 82 |
+
"step": 4787
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.0444955086693126,
|
| 86 |
+
"grad_norm": 2.2125747203826904,
|
| 87 |
+
"learning_rate": 5.791503906249999e-07,
|
| 88 |
+
"loss": 0.0807,
|
| 89 |
+
"step": 5000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.148945059536244,
|
| 93 |
+
"grad_norm": 0.20245374739170074,
|
| 94 |
+
"learning_rate": 5.66943359375e-07,
|
| 95 |
+
"loss": 0.0743,
|
| 96 |
+
"step": 5500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.2533946104031752,
|
| 100 |
+
"grad_norm": 0.28860384225845337,
|
| 101 |
+
"learning_rate": 5.54736328125e-07,
|
| 102 |
+
"loss": 0.0719,
|
| 103 |
+
"step": 6000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.3578441612701067,
|
| 107 |
+
"grad_norm": 0.21754620969295502,
|
| 108 |
+
"learning_rate": 5.425292968749999e-07,
|
| 109 |
+
"loss": 0.0691,
|
| 110 |
+
"step": 6500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.4622937121370378,
|
| 114 |
+
"grad_norm": 3.9786083698272705,
|
| 115 |
+
"learning_rate": 5.30322265625e-07,
|
| 116 |
+
"loss": 0.0721,
|
| 117 |
+
"step": 7000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.566743263003969,
|
| 121 |
+
"grad_norm": 0.5568149089813232,
|
| 122 |
+
"learning_rate": 5.18115234375e-07,
|
| 123 |
+
"loss": 0.0728,
|
| 124 |
+
"step": 7500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.6711928138709005,
|
| 128 |
+
"grad_norm": 7.5547027587890625,
|
| 129 |
+
"learning_rate": 5.059082031249999e-07,
|
| 130 |
+
"loss": 0.0709,
|
| 131 |
+
"step": 8000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.7756423647378317,
|
| 135 |
+
"grad_norm": 3.4100685119628906,
|
| 136 |
+
"learning_rate": 4.937011718749999e-07,
|
| 137 |
+
"loss": 0.0689,
|
| 138 |
+
"step": 8500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.8800919156047629,
|
| 142 |
+
"grad_norm": 0.25586971640586853,
|
| 143 |
+
"learning_rate": 4.81494140625e-07,
|
| 144 |
+
"loss": 0.0686,
|
| 145 |
+
"step": 9000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.9845414664716943,
|
| 149 |
+
"grad_norm": 0.20959605276584625,
|
| 150 |
+
"learning_rate": 4.69287109375e-07,
|
| 151 |
+
"loss": 0.0632,
|
| 152 |
+
"step": 9500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.0,
|
| 156 |
+
"eval_accuracy": 0.9853021816615095,
|
| 157 |
+
"eval_loss": 0.04927506670355797,
|
| 158 |
+
"eval_model_preparation_time": 0.0052,
|
| 159 |
+
"eval_runtime": 1036.5941,
|
| 160 |
+
"eval_samples_per_second": 98.519,
|
| 161 |
+
"eval_steps_per_second": 12.315,
|
| 162 |
+
"step": 9574
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.0889910173386252,
|
| 166 |
+
"grad_norm": 10.270435333251953,
|
| 167 |
+
"learning_rate": 4.5708007812499997e-07,
|
| 168 |
+
"loss": 0.0663,
|
| 169 |
+
"step": 10000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.1934405682055567,
|
| 173 |
+
"grad_norm": 4.9907331466674805,
|
| 174 |
+
"learning_rate": 4.44873046875e-07,
|
| 175 |
+
"loss": 0.0674,
|
| 176 |
+
"step": 10500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.297890119072488,
|
| 180 |
+
"grad_norm": 0.05801746994256973,
|
| 181 |
+
"learning_rate": 4.32666015625e-07,
|
| 182 |
+
"loss": 0.0619,
|
| 183 |
+
"step": 11000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.402339669939419,
|
| 187 |
+
"grad_norm": 0.07323583215475082,
|
| 188 |
+
"learning_rate": 4.20458984375e-07,
|
| 189 |
+
"loss": 0.0631,
|
| 190 |
+
"step": 11500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.5067892208063505,
|
| 194 |
+
"grad_norm": 1.5988435745239258,
|
| 195 |
+
"learning_rate": 4.0825195312499994e-07,
|
| 196 |
+
"loss": 0.0643,
|
| 197 |
+
"step": 12000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.611238771673282,
|
| 201 |
+
"grad_norm": 0.5066471695899963,
|
| 202 |
+
"learning_rate": 3.96044921875e-07,
|
| 203 |
+
"loss": 0.0713,
|
| 204 |
+
"step": 12500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.7156883225402133,
|
| 208 |
+
"grad_norm": 1.4767159223556519,
|
| 209 |
+
"learning_rate": 3.83837890625e-07,
|
| 210 |
+
"loss": 0.0727,
|
| 211 |
+
"step": 13000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.8201378734071443,
|
| 215 |
+
"grad_norm": 6.386782169342041,
|
| 216 |
+
"learning_rate": 3.7163085937499995e-07,
|
| 217 |
+
"loss": 0.0575,
|
| 218 |
+
"step": 13500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.9245874242740757,
|
| 222 |
+
"grad_norm": 1.1449916362762451,
|
| 223 |
+
"learning_rate": 3.5942382812500003e-07,
|
| 224 |
+
"loss": 0.0626,
|
| 225 |
+
"step": 14000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.0,
|
| 229 |
+
"eval_accuracy": 0.9854490619247189,
|
| 230 |
+
"eval_loss": 0.048059992492198944,
|
| 231 |
+
"eval_model_preparation_time": 0.0052,
|
| 232 |
+
"eval_runtime": 1093.4649,
|
| 233 |
+
"eval_samples_per_second": 93.395,
|
| 234 |
+
"eval_steps_per_second": 11.675,
|
| 235 |
+
"step": 14361
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 3.0290369751410067,
|
| 239 |
+
"grad_norm": 8.965994834899902,
|
| 240 |
+
"learning_rate": 3.47216796875e-07,
|
| 241 |
+
"loss": 0.061,
|
| 242 |
+
"step": 14500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.133486526007938,
|
| 246 |
+
"grad_norm": 0.24369557201862335,
|
| 247 |
+
"learning_rate": 3.3500976562499996e-07,
|
| 248 |
+
"loss": 0.0585,
|
| 249 |
+
"step": 15000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.2379360768748695,
|
| 253 |
+
"grad_norm": 2.182089328765869,
|
| 254 |
+
"learning_rate": 3.22802734375e-07,
|
| 255 |
+
"loss": 0.0603,
|
| 256 |
+
"step": 15500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 3.342385627741801,
|
| 260 |
+
"grad_norm": 8.162790298461914,
|
| 261 |
+
"learning_rate": 3.1059570312499995e-07,
|
| 262 |
+
"loss": 0.0608,
|
| 263 |
+
"step": 16000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.446835178608732,
|
| 267 |
+
"grad_norm": 3.445383071899414,
|
| 268 |
+
"learning_rate": 2.98388671875e-07,
|
| 269 |
+
"loss": 0.0662,
|
| 270 |
+
"step": 16500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.5512847294756633,
|
| 274 |
+
"grad_norm": 0.21630489826202393,
|
| 275 |
+
"learning_rate": 2.86181640625e-07,
|
| 276 |
+
"loss": 0.0619,
|
| 277 |
+
"step": 17000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 3.6557342803425943,
|
| 281 |
+
"grad_norm": 8.268571853637695,
|
| 282 |
+
"learning_rate": 2.7397460937499996e-07,
|
| 283 |
+
"loss": 0.0601,
|
| 284 |
+
"step": 17500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.7601838312095257,
|
| 288 |
+
"grad_norm": 1.3148396015167236,
|
| 289 |
+
"learning_rate": 2.61767578125e-07,
|
| 290 |
+
"loss": 0.0655,
|
| 291 |
+
"step": 18000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 3.864633382076457,
|
| 295 |
+
"grad_norm": 1.5834839344024658,
|
| 296 |
+
"learning_rate": 2.4956054687499995e-07,
|
| 297 |
+
"loss": 0.0589,
|
| 298 |
+
"step": 18500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 3.9690829329433885,
|
| 302 |
+
"grad_norm": 6.2100510597229,
|
| 303 |
+
"learning_rate": 2.37353515625e-07,
|
| 304 |
+
"loss": 0.0578,
|
| 305 |
+
"step": 19000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.0,
|
| 309 |
+
"eval_accuracy": 0.9855959421879285,
|
| 310 |
+
"eval_loss": 0.04732793942093849,
|
| 311 |
+
"eval_model_preparation_time": 0.0052,
|
| 312 |
+
"eval_runtime": 1129.7256,
|
| 313 |
+
"eval_samples_per_second": 90.397,
|
| 314 |
+
"eval_steps_per_second": 11.3,
|
| 315 |
+
"step": 19148
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 4.07353248381032,
|
| 319 |
+
"grad_norm": 0.3075694441795349,
|
| 320 |
+
"learning_rate": 2.2514648437499997e-07,
|
| 321 |
+
"loss": 0.0588,
|
| 322 |
+
"step": 19500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.1779820346772505,
|
| 326 |
+
"grad_norm": 5.955320358276367,
|
| 327 |
+
"learning_rate": 2.12939453125e-07,
|
| 328 |
+
"loss": 0.0631,
|
| 329 |
+
"step": 20000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 4.282431585544182,
|
| 333 |
+
"grad_norm": 0.7760459780693054,
|
| 334 |
+
"learning_rate": 2.00732421875e-07,
|
| 335 |
+
"loss": 0.0601,
|
| 336 |
+
"step": 20500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 4.386881136411113,
|
| 340 |
+
"grad_norm": 6.535593032836914,
|
| 341 |
+
"learning_rate": 1.8852539062499998e-07,
|
| 342 |
+
"loss": 0.0598,
|
| 343 |
+
"step": 21000
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 4.491330687278045,
|
| 347 |
+
"grad_norm": 1.7667866945266724,
|
| 348 |
+
"learning_rate": 1.76318359375e-07,
|
| 349 |
+
"loss": 0.0562,
|
| 350 |
+
"step": 21500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.595780238144976,
|
| 354 |
+
"grad_norm": 1.9524359703063965,
|
| 355 |
+
"learning_rate": 1.64111328125e-07,
|
| 356 |
+
"loss": 0.0615,
|
| 357 |
+
"step": 22000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 4.700229789011908,
|
| 361 |
+
"grad_norm": 0.6181924939155579,
|
| 362 |
+
"learning_rate": 1.5190429687499999e-07,
|
| 363 |
+
"loss": 0.0602,
|
| 364 |
+
"step": 22500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 4.804679339878838,
|
| 368 |
+
"grad_norm": 4.446329593658447,
|
| 369 |
+
"learning_rate": 1.39697265625e-07,
|
| 370 |
+
"loss": 0.0604,
|
| 371 |
+
"step": 23000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 4.9091288907457695,
|
| 375 |
+
"grad_norm": 12.356111526489258,
|
| 376 |
+
"learning_rate": 1.27490234375e-07,
|
| 377 |
+
"loss": 0.06,
|
| 378 |
+
"step": 23500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 5.0,
|
| 382 |
+
"eval_accuracy": 0.9857330304335905,
|
| 383 |
+
"eval_loss": 0.0469873771071434,
|
| 384 |
+
"eval_model_preparation_time": 0.0052,
|
| 385 |
+
"eval_runtime": 1092.9703,
|
| 386 |
+
"eval_samples_per_second": 93.437,
|
| 387 |
+
"eval_steps_per_second": 11.68,
|
| 388 |
+
"step": 23935
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 5.013578441612701,
|
| 392 |
+
"grad_norm": 0.1434878706932068,
|
| 393 |
+
"learning_rate": 1.15283203125e-07,
|
| 394 |
+
"loss": 0.0525,
|
| 395 |
+
"step": 24000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 5.118027992479632,
|
| 399 |
+
"grad_norm": 0.09600865095853806,
|
| 400 |
+
"learning_rate": 1.0307617187499999e-07,
|
| 401 |
+
"loss": 0.0555,
|
| 402 |
+
"step": 24500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 5.222477543346564,
|
| 406 |
+
"grad_norm": 1.8430639505386353,
|
| 407 |
+
"learning_rate": 9.086914062499999e-08,
|
| 408 |
+
"loss": 0.066,
|
| 409 |
+
"step": 25000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 5.326927094213495,
|
| 413 |
+
"grad_norm": 3.1898910999298096,
|
| 414 |
+
"learning_rate": 7.866210937499999e-08,
|
| 415 |
+
"loss": 0.0569,
|
| 416 |
+
"step": 25500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 5.431376645080427,
|
| 420 |
+
"grad_norm": 4.9123854637146,
|
| 421 |
+
"learning_rate": 6.645507812499999e-08,
|
| 422 |
+
"loss": 0.0618,
|
| 423 |
+
"step": 26000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 5.535826195947357,
|
| 427 |
+
"grad_norm": 2.0142762660980225,
|
| 428 |
+
"learning_rate": 5.4248046875e-08,
|
| 429 |
+
"loss": 0.0592,
|
| 430 |
+
"step": 26500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 5.640275746814289,
|
| 434 |
+
"grad_norm": 0.04716000333428383,
|
| 435 |
+
"learning_rate": 4.2041015624999996e-08,
|
| 436 |
+
"loss": 0.0558,
|
| 437 |
+
"step": 27000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 5.74472529768122,
|
| 441 |
+
"grad_norm": 0.09332660585641861,
|
| 442 |
+
"learning_rate": 2.9833984375000004e-08,
|
| 443 |
+
"loss": 0.0583,
|
| 444 |
+
"step": 27500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 5.849174848548151,
|
| 448 |
+
"grad_norm": 0.10846803337335587,
|
| 449 |
+
"learning_rate": 1.7626953124999998e-08,
|
| 450 |
+
"loss": 0.06,
|
| 451 |
+
"step": 28000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 5.953624399415083,
|
| 455 |
+
"grad_norm": 1.7731516361236572,
|
| 456 |
+
"learning_rate": 5.419921875e-09,
|
| 457 |
+
"loss": 0.055,
|
| 458 |
+
"step": 28500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 6.0,
|
| 462 |
+
"eval_accuracy": 0.985811366573969,
|
| 463 |
+
"eval_loss": 0.046924859285354614,
|
| 464 |
+
"eval_model_preparation_time": 0.0052,
|
| 465 |
+
"eval_runtime": 964.6086,
|
| 466 |
+
"eval_samples_per_second": 105.871,
|
| 467 |
+
"eval_steps_per_second": 13.234,
|
| 468 |
+
"step": 28722
|
| 469 |
+
}
|
| 470 |
+
],
|
| 471 |
+
"logging_steps": 500,
|
| 472 |
+
"max_steps": 28722,
|
| 473 |
+
"num_input_tokens_seen": 0,
|
| 474 |
+
"num_train_epochs": 6,
|
| 475 |
+
"save_steps": 500,
|
| 476 |
+
"stateful_callbacks": {
|
| 477 |
+
"TrainerControl": {
|
| 478 |
+
"args": {
|
| 479 |
+
"should_epoch_stop": false,
|
| 480 |
+
"should_evaluate": false,
|
| 481 |
+
"should_log": false,
|
| 482 |
+
"should_save": true,
|
| 483 |
+
"should_training_stop": true
|
| 484 |
+
},
|
| 485 |
+
"attributes": {}
|
| 486 |
+
}
|
| 487 |
+
},
|
| 488 |
+
"total_flos": 7.1223197622729966e+19,
|
| 489 |
+
"train_batch_size": 32,
|
| 490 |
+
"trial_name": null,
|
| 491 |
+
"trial_params": null
|
| 492 |
+
}
|
checkpoint-28722/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c28c1f257c537cb703935fd86e87d6b3ad069482a37aed881f667e21331c3d9d
|
| 3 |
+
size 4731
|
config.json
CHANGED
|
@@ -28,5 +28,5 @@
|
|
| 28 |
"problem_type": "single_label_classification",
|
| 29 |
"qkv_bias": true,
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
-
"transformers_version": "4.
|
| 32 |
}
|
|
|
|
| 28 |
"problem_type": "single_label_classification",
|
| 29 |
"qkv_bias": true,
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.46.0"
|
| 32 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343223968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76a0e858198cf9bc5c049b946990a31fbcfae443b96421d92b8311418245180c
|
| 3 |
size 343223968
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4731
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c28c1f257c537cb703935fd86e87d6b3ad069482a37aed881f667e21331c3d9d
|
| 3 |
size 4731
|