Upload folder using huggingface_hub
Browse files- config.json +52 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +27 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +348 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/dinov2-with-registers-small",
|
| 3 |
+
"apply_layernorm": true,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Dinov2WithRegistersForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"drop_path_rate": 0.0,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 384,
|
| 12 |
+
"image_size": 518,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"interpolate_antialias": true,
|
| 15 |
+
"interpolate_offset": 0.0,
|
| 16 |
+
"layer_norm_eps": 1e-06,
|
| 17 |
+
"layerscale_value": 1.0,
|
| 18 |
+
"mlp_ratio": 4,
|
| 19 |
+
"model_type": "dinov2_with_registers",
|
| 20 |
+
"num_attention_heads": 6,
|
| 21 |
+
"num_channels": 3,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"num_register_tokens": 4,
|
| 24 |
+
"out_features": [
|
| 25 |
+
"stage12"
|
| 26 |
+
],
|
| 27 |
+
"out_indices": [
|
| 28 |
+
12
|
| 29 |
+
],
|
| 30 |
+
"patch_size": 14,
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"qkv_bias": true,
|
| 33 |
+
"reshape_hidden_states": true,
|
| 34 |
+
"stage_names": [
|
| 35 |
+
"stem",
|
| 36 |
+
"stage1",
|
| 37 |
+
"stage2",
|
| 38 |
+
"stage3",
|
| 39 |
+
"stage4",
|
| 40 |
+
"stage5",
|
| 41 |
+
"stage6",
|
| 42 |
+
"stage7",
|
| 43 |
+
"stage8",
|
| 44 |
+
"stage9",
|
| 45 |
+
"stage10",
|
| 46 |
+
"stage11",
|
| 47 |
+
"stage12"
|
| 48 |
+
],
|
| 49 |
+
"torch_dtype": "float32",
|
| 50 |
+
"transformers_version": "4.48.1",
|
| 51 |
+
"use_swiglu_ffn": false
|
| 52 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2aea2da872884f2706b4a95e3b1fffa3c99d81477d55bf646bac347aa6fb2813
|
| 3 |
+
size 88267432
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04e73676eb0451543ead6221e4df6fddb96d704f5eb6454f18b5e8d9a7f40268
|
| 3 |
+
size 176666106
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.485,
|
| 13 |
+
0.456,
|
| 14 |
+
0.406
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "BitImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.229,
|
| 19 |
+
0.224,
|
| 20 |
+
0.225
|
| 21 |
+
],
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"shortest_edge": 256
|
| 26 |
+
}
|
| 27 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d85331cdb7873a32fdbe680a651df4734dde10919ae9c4a67dac6b84d6a21aa
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,348 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9651834647200833,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-3000",
|
| 4 |
+
"epoch": 0.9363295880149812,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3000,
|
| 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,
|
| 13 |
+
"eval_accuracy": 0.6045787545787545,
|
| 14 |
+
"eval_ap": 0.6438655017635215,
|
| 15 |
+
"eval_auc": 0.6252253659085975,
|
| 16 |
+
"eval_eer": 0.41503637833468066,
|
| 17 |
+
"eval_f1": 0.673324254804055,
|
| 18 |
+
"eval_loss": 0.6694703102111816,
|
| 19 |
+
"eval_precision": 0.6141319348606128,
|
| 20 |
+
"eval_recall": 0.7451440053583389,
|
| 21 |
+
"eval_runtime": 1161.2986,
|
| 22 |
+
"eval_samples_per_second": 70.524,
|
| 23 |
+
"eval_steps_per_second": 0.276,
|
| 24 |
+
"step": 0
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.031210986267166042,
|
| 28 |
+
"grad_norm": 1570057.0,
|
| 29 |
+
"learning_rate": 1e-05,
|
| 30 |
+
"loss": 0.3999,
|
| 31 |
+
"step": 100
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.062421972534332085,
|
| 35 |
+
"grad_norm": 1873799.375,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 0.183,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09363295880149813,
|
| 42 |
+
"grad_norm": 937146.625,
|
| 43 |
+
"learning_rate": 3e-05,
|
| 44 |
+
"loss": 0.1499,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.12484394506866417,
|
| 49 |
+
"grad_norm": 1296423.5,
|
| 50 |
+
"learning_rate": 4e-05,
|
| 51 |
+
"loss": 0.1939,
|
| 52 |
+
"step": 400
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1560549313358302,
|
| 56 |
+
"grad_norm": 698965.0,
|
| 57 |
+
"learning_rate": 5e-05,
|
| 58 |
+
"loss": 0.1542,
|
| 59 |
+
"step": 500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.1560549313358302,
|
| 63 |
+
"eval_accuracy": 0.7873870573870574,
|
| 64 |
+
"eval_ap": 0.9824733762472688,
|
| 65 |
+
"eval_auc": 0.9823328646050201,
|
| 66 |
+
"eval_eer": 0.06329830234438157,
|
| 67 |
+
"eval_f1": 0.7611024983193624,
|
| 68 |
+
"eval_loss": 0.586156964302063,
|
| 69 |
+
"eval_precision": 0.9871525677070359,
|
| 70 |
+
"eval_recall": 0.6192900200937709,
|
| 71 |
+
"eval_runtime": 896.8541,
|
| 72 |
+
"eval_samples_per_second": 91.319,
|
| 73 |
+
"eval_steps_per_second": 0.357,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.18726591760299627,
|
| 78 |
+
"grad_norm": 854220.375,
|
| 79 |
+
"learning_rate": 4.81508875739645e-05,
|
| 80 |
+
"loss": 0.1201,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.2184769038701623,
|
| 85 |
+
"grad_norm": 1128798.0,
|
| 86 |
+
"learning_rate": 4.6301775147928994e-05,
|
| 87 |
+
"loss": 0.1162,
|
| 88 |
+
"step": 700
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.24968789013732834,
|
| 92 |
+
"grad_norm": 622432.0,
|
| 93 |
+
"learning_rate": 4.44526627218935e-05,
|
| 94 |
+
"loss": 0.1071,
|
| 95 |
+
"step": 800
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.2808988764044944,
|
| 99 |
+
"grad_norm": 790906.0625,
|
| 100 |
+
"learning_rate": 4.260355029585799e-05,
|
| 101 |
+
"loss": 0.0874,
|
| 102 |
+
"step": 900
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.3121098626716604,
|
| 106 |
+
"grad_norm": 1022445.375,
|
| 107 |
+
"learning_rate": 4.075443786982249e-05,
|
| 108 |
+
"loss": 0.0748,
|
| 109 |
+
"step": 1000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.3121098626716604,
|
| 113 |
+
"eval_accuracy": 0.9135164835164835,
|
| 114 |
+
"eval_ap": 0.9891846925529121,
|
| 115 |
+
"eval_auc": 0.9885782446290119,
|
| 116 |
+
"eval_eer": 0.05095661546752897,
|
| 117 |
+
"eval_f1": 0.9160672599509415,
|
| 118 |
+
"eval_loss": 0.23737847805023193,
|
| 119 |
+
"eval_precision": 0.9761105078411071,
|
| 120 |
+
"eval_recall": 0.8629828086626479,
|
| 121 |
+
"eval_runtime": 899.3174,
|
| 122 |
+
"eval_samples_per_second": 91.069,
|
| 123 |
+
"eval_steps_per_second": 0.356,
|
| 124 |
+
"step": 1000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.3433208489388265,
|
| 128 |
+
"grad_norm": 857955.5625,
|
| 129 |
+
"learning_rate": 3.8905325443786985e-05,
|
| 130 |
+
"loss": 0.0764,
|
| 131 |
+
"step": 1100
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.37453183520599254,
|
| 135 |
+
"grad_norm": 874027.0,
|
| 136 |
+
"learning_rate": 3.705621301775148e-05,
|
| 137 |
+
"loss": 0.0709,
|
| 138 |
+
"step": 1200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.40574282147315854,
|
| 142 |
+
"grad_norm": 582799.875,
|
| 143 |
+
"learning_rate": 3.520710059171598e-05,
|
| 144 |
+
"loss": 0.0636,
|
| 145 |
+
"step": 1300
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.4369538077403246,
|
| 149 |
+
"grad_norm": 521187.625,
|
| 150 |
+
"learning_rate": 3.335798816568047e-05,
|
| 151 |
+
"loss": 0.0533,
|
| 152 |
+
"step": 1400
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.4681647940074906,
|
| 156 |
+
"grad_norm": 522330.4375,
|
| 157 |
+
"learning_rate": 3.150887573964497e-05,
|
| 158 |
+
"loss": 0.0465,
|
| 159 |
+
"step": 1500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.4681647940074906,
|
| 163 |
+
"eval_accuracy": 0.9357875457875457,
|
| 164 |
+
"eval_ap": 0.9924125253776173,
|
| 165 |
+
"eval_auc": 0.9918219498411971,
|
| 166 |
+
"eval_eer": 0.042576125033683646,
|
| 167 |
+
"eval_f1": 0.9388722931898225,
|
| 168 |
+
"eval_loss": 0.18004347383975983,
|
| 169 |
+
"eval_precision": 0.9792449627815629,
|
| 170 |
+
"eval_recall": 0.9016968073230632,
|
| 171 |
+
"eval_runtime": 904.8241,
|
| 172 |
+
"eval_samples_per_second": 90.515,
|
| 173 |
+
"eval_steps_per_second": 0.354,
|
| 174 |
+
"step": 1500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.4993757802746567,
|
| 178 |
+
"grad_norm": 1439895.375,
|
| 179 |
+
"learning_rate": 2.965976331360947e-05,
|
| 180 |
+
"loss": 0.0479,
|
| 181 |
+
"step": 1600
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.5305867665418227,
|
| 185 |
+
"grad_norm": 522678.71875,
|
| 186 |
+
"learning_rate": 2.7810650887573965e-05,
|
| 187 |
+
"loss": 0.0429,
|
| 188 |
+
"step": 1700
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.5617977528089888,
|
| 192 |
+
"grad_norm": 1075267.0,
|
| 193 |
+
"learning_rate": 2.5961538461538464e-05,
|
| 194 |
+
"loss": 0.0419,
|
| 195 |
+
"step": 1800
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.5930087390761548,
|
| 199 |
+
"grad_norm": 621287.5625,
|
| 200 |
+
"learning_rate": 2.411242603550296e-05,
|
| 201 |
+
"loss": 0.0449,
|
| 202 |
+
"step": 1900
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.6242197253433208,
|
| 206 |
+
"grad_norm": 431768.9375,
|
| 207 |
+
"learning_rate": 2.2263313609467456e-05,
|
| 208 |
+
"loss": 0.0373,
|
| 209 |
+
"step": 2000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.6242197253433208,
|
| 213 |
+
"eval_accuracy": 0.9467277167277167,
|
| 214 |
+
"eval_ap": 0.9953183185775565,
|
| 215 |
+
"eval_auc": 0.9948050755617595,
|
| 216 |
+
"eval_eer": 0.03290218270008084,
|
| 217 |
+
"eval_f1": 0.9495787636800684,
|
| 218 |
+
"eval_loss": 0.16710303723812103,
|
| 219 |
+
"eval_precision": 0.9842600800172492,
|
| 220 |
+
"eval_recall": 0.9172583165885242,
|
| 221 |
+
"eval_runtime": 883.8932,
|
| 222 |
+
"eval_samples_per_second": 92.658,
|
| 223 |
+
"eval_steps_per_second": 0.362,
|
| 224 |
+
"step": 2000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.6554307116104869,
|
| 228 |
+
"grad_norm": 300561.40625,
|
| 229 |
+
"learning_rate": 2.0414201183431952e-05,
|
| 230 |
+
"loss": 0.0367,
|
| 231 |
+
"step": 2100
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.686641697877653,
|
| 235 |
+
"grad_norm": 759234.625,
|
| 236 |
+
"learning_rate": 1.856508875739645e-05,
|
| 237 |
+
"loss": 0.0385,
|
| 238 |
+
"step": 2200
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.717852684144819,
|
| 242 |
+
"grad_norm": 110611.8984375,
|
| 243 |
+
"learning_rate": 1.6715976331360947e-05,
|
| 244 |
+
"loss": 0.029,
|
| 245 |
+
"step": 2300
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.7490636704119851,
|
| 249 |
+
"grad_norm": 890414.25,
|
| 250 |
+
"learning_rate": 1.4866863905325445e-05,
|
| 251 |
+
"loss": 0.0243,
|
| 252 |
+
"step": 2400
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.7802746566791511,
|
| 256 |
+
"grad_norm": 110954.5390625,
|
| 257 |
+
"learning_rate": 1.3017751479289941e-05,
|
| 258 |
+
"loss": 0.028,
|
| 259 |
+
"step": 2500
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.7802746566791511,
|
| 263 |
+
"eval_accuracy": 0.9541514041514042,
|
| 264 |
+
"eval_ap": 0.9963480520212278,
|
| 265 |
+
"eval_auc": 0.9958883442351322,
|
| 266 |
+
"eval_eer": 0.02915656157369981,
|
| 267 |
+
"eval_f1": 0.9567799633982114,
|
| 268 |
+
"eval_loss": 0.1855895221233368,
|
| 269 |
+
"eval_precision": 0.9874557506355278,
|
| 270 |
+
"eval_recall": 0.9279526680062514,
|
| 271 |
+
"eval_runtime": 916.7443,
|
| 272 |
+
"eval_samples_per_second": 89.338,
|
| 273 |
+
"eval_steps_per_second": 0.349,
|
| 274 |
+
"step": 2500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.8114856429463171,
|
| 278 |
+
"grad_norm": 969664.1875,
|
| 279 |
+
"learning_rate": 1.1168639053254439e-05,
|
| 280 |
+
"loss": 0.0268,
|
| 281 |
+
"step": 2600
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.8426966292134831,
|
| 285 |
+
"grad_norm": 21713.740234375,
|
| 286 |
+
"learning_rate": 9.319526627218936e-06,
|
| 287 |
+
"loss": 0.0259,
|
| 288 |
+
"step": 2700
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.8739076154806492,
|
| 292 |
+
"grad_norm": 625.3981323242188,
|
| 293 |
+
"learning_rate": 7.470414201183433e-06,
|
| 294 |
+
"loss": 0.0272,
|
| 295 |
+
"step": 2800
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.9051186017478152,
|
| 299 |
+
"grad_norm": 51626.33203125,
|
| 300 |
+
"learning_rate": 5.621301775147929e-06,
|
| 301 |
+
"loss": 0.0255,
|
| 302 |
+
"step": 2900
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.9363295880149812,
|
| 306 |
+
"grad_norm": 330527.75,
|
| 307 |
+
"learning_rate": 3.772189349112426e-06,
|
| 308 |
+
"loss": 0.0196,
|
| 309 |
+
"step": 3000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.9363295880149812,
|
| 313 |
+
"eval_accuracy": 0.9628449328449329,
|
| 314 |
+
"eval_ap": 0.9971936987222482,
|
| 315 |
+
"eval_auc": 0.996572647864952,
|
| 316 |
+
"eval_eer": 0.02357855025599569,
|
| 317 |
+
"eval_f1": 0.9651834647200833,
|
| 318 |
+
"eval_loss": 0.2491898238658905,
|
| 319 |
+
"eval_precision": 0.9898617727816761,
|
| 320 |
+
"eval_recall": 0.9417057378879214,
|
| 321 |
+
"eval_runtime": 887.8512,
|
| 322 |
+
"eval_samples_per_second": 92.245,
|
| 323 |
+
"eval_steps_per_second": 0.36,
|
| 324 |
+
"step": 3000
|
| 325 |
+
}
|
| 326 |
+
],
|
| 327 |
+
"logging_steps": 100,
|
| 328 |
+
"max_steps": 3204,
|
| 329 |
+
"num_input_tokens_seen": 0,
|
| 330 |
+
"num_train_epochs": 1,
|
| 331 |
+
"save_steps": 500,
|
| 332 |
+
"stateful_callbacks": {
|
| 333 |
+
"TrainerControl": {
|
| 334 |
+
"args": {
|
| 335 |
+
"should_epoch_stop": false,
|
| 336 |
+
"should_evaluate": false,
|
| 337 |
+
"should_log": false,
|
| 338 |
+
"should_save": true,
|
| 339 |
+
"should_training_stop": false
|
| 340 |
+
},
|
| 341 |
+
"attributes": {}
|
| 342 |
+
}
|
| 343 |
+
},
|
| 344 |
+
"total_flos": 7.6506508689408e+18,
|
| 345 |
+
"train_batch_size": 128,
|
| 346 |
+
"trial_name": null,
|
| 347 |
+
"trial_params": null
|
| 348 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d78dd7607d12c6e838c300398defc50de9b401f222da99855bf99f882970333
|
| 3 |
+
size 5304
|