Upload folder using huggingface_hub
Browse files- config.json +33 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +13 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +296 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ASTForAudioClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"frequency_stride": 10,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "fake",
|
| 13 |
+
"1": "real"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"fake": 0,
|
| 19 |
+
"real": 1
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_length": 1024,
|
| 23 |
+
"model_type": "audio-spectrogram-transformer",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"num_mel_bins": 128,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"problem_type": "multi_label_classification",
|
| 29 |
+
"qkv_bias": true,
|
| 30 |
+
"time_stride": 10,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.47.0"
|
| 33 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26819c8f41ac20921682a9e340498d8faa508b7a06feabf5efe2471ee8dffd2f
|
| 3 |
+
size 344790040
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6262712b1f7815657936ebc671cd3ec930454e219cab4df9cf8e6887c7d0f096
|
| 3 |
+
size 689692538
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "ASTFeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"max_length": 1024,
|
| 6 |
+
"mean": -4.2677393,
|
| 7 |
+
"num_mel_bins": 128,
|
| 8 |
+
"padding_side": "right",
|
| 9 |
+
"padding_value": 0.0,
|
| 10 |
+
"return_attention_mask": false,
|
| 11 |
+
"sampling_rate": 16000,
|
| 12 |
+
"std": 4.5689974
|
| 13 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5edb34d031c0c2b447f3eaadb401a4c1e7e7e6d8c096e28b7092e01a8bd48c92
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffad90ba2d44400541fefd6b35ec89711836fc8e20c4def302be896c6abce095
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,296 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9672544080604534,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-32",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"eval_steps": 16,
|
| 6 |
+
"global_step": 32,
|
| 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": 0.5631369073992025,
|
| 14 |
+
"eval_f1": 0.2187004754358162,
|
| 15 |
+
"eval_loss": 0.6949890851974487,
|
| 16 |
+
"eval_precision": 0.4859154929577465,
|
| 17 |
+
"eval_recall": 0.1411042944785276,
|
| 18 |
+
"eval_roc_auc": 0.5134763067388728,
|
| 19 |
+
"eval_runtime": 223.301,
|
| 20 |
+
"eval_samples_per_second": 10.107,
|
| 21 |
+
"eval_steps_per_second": 0.161,
|
| 22 |
+
"step": 0
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.25,
|
| 26 |
+
"grad_norm": 403305.03125,
|
| 27 |
+
"learning_rate": 5e-06,
|
| 28 |
+
"loss": 0.7064,
|
| 29 |
+
"step": 1
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.5,
|
| 33 |
+
"grad_norm": 356396.5625,
|
| 34 |
+
"learning_rate": 1e-05,
|
| 35 |
+
"loss": 0.6935,
|
| 36 |
+
"step": 2
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.75,
|
| 40 |
+
"grad_norm": 307834.09375,
|
| 41 |
+
"learning_rate": 1.5e-05,
|
| 42 |
+
"loss": 0.6726,
|
| 43 |
+
"step": 3
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 1.0,
|
| 47 |
+
"grad_norm": 243574.875,
|
| 48 |
+
"learning_rate": 2e-05,
|
| 49 |
+
"loss": 0.5962,
|
| 50 |
+
"step": 4
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.25,
|
| 54 |
+
"grad_norm": 221193.53125,
|
| 55 |
+
"learning_rate": 2.5e-05,
|
| 56 |
+
"loss": 0.5996,
|
| 57 |
+
"step": 5
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.5,
|
| 61 |
+
"grad_norm": 186638.8125,
|
| 62 |
+
"learning_rate": 3e-05,
|
| 63 |
+
"loss": 0.4442,
|
| 64 |
+
"step": 6
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.75,
|
| 68 |
+
"grad_norm": 304570.8125,
|
| 69 |
+
"learning_rate": 3.5e-05,
|
| 70 |
+
"loss": 0.3794,
|
| 71 |
+
"step": 7
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.0,
|
| 75 |
+
"grad_norm": 229105.703125,
|
| 76 |
+
"learning_rate": 4e-05,
|
| 77 |
+
"loss": 0.274,
|
| 78 |
+
"step": 8
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.25,
|
| 82 |
+
"grad_norm": 759166.6875,
|
| 83 |
+
"learning_rate": 4.5e-05,
|
| 84 |
+
"loss": 0.5201,
|
| 85 |
+
"step": 9
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 2.5,
|
| 89 |
+
"grad_norm": 334408.0625,
|
| 90 |
+
"learning_rate": 5e-05,
|
| 91 |
+
"loss": 0.2268,
|
| 92 |
+
"step": 10
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.75,
|
| 96 |
+
"grad_norm": 228056.125,
|
| 97 |
+
"learning_rate": 4.772727272727273e-05,
|
| 98 |
+
"loss": 0.1741,
|
| 99 |
+
"step": 11
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.0,
|
| 103 |
+
"grad_norm": 323873.25,
|
| 104 |
+
"learning_rate": 4.545454545454546e-05,
|
| 105 |
+
"loss": 0.1596,
|
| 106 |
+
"step": 12
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.25,
|
| 110 |
+
"grad_norm": 224164.234375,
|
| 111 |
+
"learning_rate": 4.318181818181819e-05,
|
| 112 |
+
"loss": 0.1151,
|
| 113 |
+
"step": 13
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.5,
|
| 117 |
+
"grad_norm": 350307.4375,
|
| 118 |
+
"learning_rate": 4.0909090909090915e-05,
|
| 119 |
+
"loss": 0.1046,
|
| 120 |
+
"step": 14
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.75,
|
| 124 |
+
"grad_norm": 254783.046875,
|
| 125 |
+
"learning_rate": 3.8636363636363636e-05,
|
| 126 |
+
"loss": 0.0898,
|
| 127 |
+
"step": 15
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 4.0,
|
| 131 |
+
"grad_norm": 568981.0625,
|
| 132 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 133 |
+
"loss": 0.1363,
|
| 134 |
+
"step": 16
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.0,
|
| 138 |
+
"eval_accuracy": 0.9548072662826761,
|
| 139 |
+
"eval_f1": 0.9492537313432835,
|
| 140 |
+
"eval_loss": 0.12049589306116104,
|
| 141 |
+
"eval_precision": 0.9244186046511628,
|
| 142 |
+
"eval_recall": 0.9754601226993865,
|
| 143 |
+
"eval_roc_auc": 0.9572374890275666,
|
| 144 |
+
"eval_runtime": 201.6296,
|
| 145 |
+
"eval_samples_per_second": 11.194,
|
| 146 |
+
"eval_steps_per_second": 0.179,
|
| 147 |
+
"step": 16
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.25,
|
| 151 |
+
"grad_norm": 243960.203125,
|
| 152 |
+
"learning_rate": 3.409090909090909e-05,
|
| 153 |
+
"loss": 0.0667,
|
| 154 |
+
"step": 17
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 4.5,
|
| 158 |
+
"grad_norm": 142561.25,
|
| 159 |
+
"learning_rate": 3.181818181818182e-05,
|
| 160 |
+
"loss": 0.1296,
|
| 161 |
+
"step": 18
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 4.75,
|
| 165 |
+
"grad_norm": 372947.1875,
|
| 166 |
+
"learning_rate": 2.954545454545455e-05,
|
| 167 |
+
"loss": 0.079,
|
| 168 |
+
"step": 19
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.0,
|
| 172 |
+
"grad_norm": 263663.1875,
|
| 173 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 174 |
+
"loss": 0.0413,
|
| 175 |
+
"step": 20
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 5.25,
|
| 179 |
+
"grad_norm": 252958.59375,
|
| 180 |
+
"learning_rate": 2.5e-05,
|
| 181 |
+
"loss": 0.0576,
|
| 182 |
+
"step": 21
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 5.5,
|
| 186 |
+
"grad_norm": 236010.8125,
|
| 187 |
+
"learning_rate": 2.272727272727273e-05,
|
| 188 |
+
"loss": 0.0356,
|
| 189 |
+
"step": 22
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 5.75,
|
| 193 |
+
"grad_norm": 437607.6875,
|
| 194 |
+
"learning_rate": 2.0454545454545457e-05,
|
| 195 |
+
"loss": 0.0561,
|
| 196 |
+
"step": 23
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 6.0,
|
| 200 |
+
"grad_norm": 125936.2890625,
|
| 201 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 202 |
+
"loss": 0.0316,
|
| 203 |
+
"step": 24
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 6.25,
|
| 207 |
+
"grad_norm": 24917.3125,
|
| 208 |
+
"learning_rate": 1.590909090909091e-05,
|
| 209 |
+
"loss": 0.0077,
|
| 210 |
+
"step": 25
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 6.5,
|
| 214 |
+
"grad_norm": 38501.140625,
|
| 215 |
+
"learning_rate": 1.3636363636363637e-05,
|
| 216 |
+
"loss": 0.0096,
|
| 217 |
+
"step": 26
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 6.75,
|
| 221 |
+
"grad_norm": 470888.34375,
|
| 222 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 223 |
+
"loss": 0.1262,
|
| 224 |
+
"step": 27
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 7.0,
|
| 228 |
+
"grad_norm": 119350.9921875,
|
| 229 |
+
"learning_rate": 9.090909090909091e-06,
|
| 230 |
+
"loss": 0.0164,
|
| 231 |
+
"step": 28
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 7.25,
|
| 235 |
+
"grad_norm": 85813.4609375,
|
| 236 |
+
"learning_rate": 6.818181818181818e-06,
|
| 237 |
+
"loss": 0.0128,
|
| 238 |
+
"step": 29
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 7.5,
|
| 242 |
+
"grad_norm": 7517.9716796875,
|
| 243 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 244 |
+
"loss": 0.0043,
|
| 245 |
+
"step": 30
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 7.75,
|
| 249 |
+
"grad_norm": 18834.26953125,
|
| 250 |
+
"learning_rate": 2.2727272727272728e-06,
|
| 251 |
+
"loss": 0.0057,
|
| 252 |
+
"step": 31
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 8.0,
|
| 256 |
+
"grad_norm": 10225.0634765625,
|
| 257 |
+
"learning_rate": 0.0,
|
| 258 |
+
"loss": 0.0055,
|
| 259 |
+
"step": 32
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 8.0,
|
| 263 |
+
"eval_accuracy": 0.9712007089056269,
|
| 264 |
+
"eval_f1": 0.9672544080604534,
|
| 265 |
+
"eval_loss": 0.07409351319074631,
|
| 266 |
+
"eval_precision": 0.9533267130089375,
|
| 267 |
+
"eval_recall": 0.9815950920245399,
|
| 268 |
+
"eval_roc_auc": 0.9724238165361168,
|
| 269 |
+
"eval_runtime": 212.9489,
|
| 270 |
+
"eval_samples_per_second": 10.599,
|
| 271 |
+
"eval_steps_per_second": 0.169,
|
| 272 |
+
"step": 32
|
| 273 |
+
}
|
| 274 |
+
],
|
| 275 |
+
"logging_steps": 1,
|
| 276 |
+
"max_steps": 32,
|
| 277 |
+
"num_input_tokens_seen": 0,
|
| 278 |
+
"num_train_epochs": 8,
|
| 279 |
+
"save_steps": 16,
|
| 280 |
+
"stateful_callbacks": {
|
| 281 |
+
"TrainerControl": {
|
| 282 |
+
"args": {
|
| 283 |
+
"should_epoch_stop": false,
|
| 284 |
+
"should_evaluate": false,
|
| 285 |
+
"should_log": false,
|
| 286 |
+
"should_save": true,
|
| 287 |
+
"should_training_stop": true
|
| 288 |
+
},
|
| 289 |
+
"attributes": {}
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"total_flos": 6.507152629825536e+16,
|
| 293 |
+
"train_batch_size": 32,
|
| 294 |
+
"trial_name": null,
|
| 295 |
+
"trial_params": null
|
| 296 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2aa820ca26d546e59ee8632bab139dae987a3758b5b964894f5da5ff6f02aab1
|
| 3 |
+
size 5304
|