End of training
Browse files
README.md
CHANGED
|
@@ -3,6 +3,7 @@ library_name: peft
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: openai/whisper-small
|
| 5 |
tags:
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- audiofolder
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: openai/whisper-small
|
| 5 |
tags:
|
| 6 |
+
- whisper-event
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- audiofolder
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.01,
|
| 3 |
+
"eval_loss": 1.5216612815856934,
|
| 4 |
+
"eval_runtime": 360.9127,
|
| 5 |
+
"eval_samples_per_second": 9.002,
|
| 6 |
+
"eval_steps_per_second": 1.128,
|
| 7 |
+
"total_flos": 9.3113310633984e+18,
|
| 8 |
+
"train_loss": 0.11658428072929382,
|
| 9 |
+
"train_runtime": 5497.3683,
|
| 10 |
+
"train_samples_per_second": 5.821,
|
| 11 |
+
"train_steps_per_second": 0.182
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.01,
|
| 3 |
+
"eval_loss": 1.5216612815856934,
|
| 4 |
+
"eval_runtime": 360.9127,
|
| 5 |
+
"eval_samples_per_second": 9.002,
|
| 6 |
+
"eval_steps_per_second": 1.128
|
| 7 |
+
}
|
runs/Mar27_12-26-58_siva-notebook-vm-gpu/events.out.tfevents.1743084296.siva-notebook-vm-gpu.33906.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:097d3dd4473004caf831e58606d74c5bf54c06113367625c0d8d417e7dd21cbd
|
| 3 |
+
size 359
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.01,
|
| 3 |
+
"total_flos": 9.3113310633984e+18,
|
| 4 |
+
"train_loss": 0.11658428072929382,
|
| 5 |
+
"train_runtime": 5497.3683,
|
| 6 |
+
"train_samples_per_second": 5.821,
|
| 7 |
+
"train_steps_per_second": 0.182
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,338 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.01,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.025,
|
| 13 |
+
"grad_norm": 0.5332708954811096,
|
| 14 |
+
"learning_rate": 0.0005,
|
| 15 |
+
"loss": 1.3185,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 0.36998245120048523,
|
| 21 |
+
"learning_rate": 0.001,
|
| 22 |
+
"loss": 0.3227,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.075,
|
| 27 |
+
"grad_norm": 0.31179681420326233,
|
| 28 |
+
"learning_rate": 0.0009736842105263158,
|
| 29 |
+
"loss": 0.2727,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.001,
|
| 34 |
+
"grad_norm": 0.24960194528102875,
|
| 35 |
+
"learning_rate": 0.0009473684210526315,
|
| 36 |
+
"loss": 0.2695,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.026,
|
| 41 |
+
"grad_norm": 0.277804434299469,
|
| 42 |
+
"learning_rate": 0.0009210526315789473,
|
| 43 |
+
"loss": 0.2295,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.051,
|
| 48 |
+
"grad_norm": 0.3241264224052429,
|
| 49 |
+
"learning_rate": 0.0008947368421052632,
|
| 50 |
+
"loss": 0.222,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.076,
|
| 55 |
+
"grad_norm": 0.2752802073955536,
|
| 56 |
+
"learning_rate": 0.000868421052631579,
|
| 57 |
+
"loss": 0.2296,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.002,
|
| 62 |
+
"grad_norm": 0.2725565433502197,
|
| 63 |
+
"learning_rate": 0.0008421052631578947,
|
| 64 |
+
"loss": 0.2251,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.027,
|
| 69 |
+
"grad_norm": 0.32025495171546936,
|
| 70 |
+
"learning_rate": 0.0008157894736842105,
|
| 71 |
+
"loss": 0.1499,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.052,
|
| 76 |
+
"grad_norm": 0.33148202300071716,
|
| 77 |
+
"learning_rate": 0.0007894736842105263,
|
| 78 |
+
"loss": 0.1523,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.077,
|
| 83 |
+
"grad_norm": 0.36358487606048584,
|
| 84 |
+
"learning_rate": 0.0007631578947368421,
|
| 85 |
+
"loss": 0.1582,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 3.003,
|
| 90 |
+
"grad_norm": 0.23482877016067505,
|
| 91 |
+
"learning_rate": 0.0007368421052631579,
|
| 92 |
+
"loss": 0.1592,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.028,
|
| 97 |
+
"grad_norm": 0.2773413062095642,
|
| 98 |
+
"learning_rate": 0.0007105263157894737,
|
| 99 |
+
"loss": 0.0931,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 3.053,
|
| 104 |
+
"grad_norm": 0.43919506669044495,
|
| 105 |
+
"learning_rate": 0.0006842105263157895,
|
| 106 |
+
"loss": 0.0944,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.078,
|
| 111 |
+
"grad_norm": 0.2814411222934723,
|
| 112 |
+
"learning_rate": 0.0006578947368421054,
|
| 113 |
+
"loss": 0.1019,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.004,
|
| 118 |
+
"grad_norm": 0.2654748260974884,
|
| 119 |
+
"learning_rate": 0.0006315789473684211,
|
| 120 |
+
"loss": 0.0984,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.029,
|
| 125 |
+
"grad_norm": 0.2132512629032135,
|
| 126 |
+
"learning_rate": 0.0006052631578947369,
|
| 127 |
+
"loss": 0.0506,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.054,
|
| 132 |
+
"grad_norm": 0.2793805003166199,
|
| 133 |
+
"learning_rate": 0.0005789473684210527,
|
| 134 |
+
"loss": 0.0549,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.079,
|
| 139 |
+
"grad_norm": 0.2352992296218872,
|
| 140 |
+
"learning_rate": 0.0005526315789473685,
|
| 141 |
+
"loss": 0.0638,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 5.005,
|
| 146 |
+
"grad_norm": 0.2415677160024643,
|
| 147 |
+
"learning_rate": 0.0005263157894736842,
|
| 148 |
+
"loss": 0.0581,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.005,
|
| 153 |
+
"eval_loss": 1.3403475284576416,
|
| 154 |
+
"eval_runtime": 415.9648,
|
| 155 |
+
"eval_samples_per_second": 7.811,
|
| 156 |
+
"eval_steps_per_second": 0.978,
|
| 157 |
+
"step": 500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 5.03,
|
| 161 |
+
"grad_norm": 0.22632592916488647,
|
| 162 |
+
"learning_rate": 0.0005,
|
| 163 |
+
"loss": 0.0332,
|
| 164 |
+
"step": 525
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 5.055,
|
| 168 |
+
"grad_norm": 0.2028239220380783,
|
| 169 |
+
"learning_rate": 0.00047368421052631577,
|
| 170 |
+
"loss": 0.0331,
|
| 171 |
+
"step": 550
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 5.08,
|
| 175 |
+
"grad_norm": 0.3129159212112427,
|
| 176 |
+
"learning_rate": 0.0004473684210526316,
|
| 177 |
+
"loss": 0.0368,
|
| 178 |
+
"step": 575
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 6.006,
|
| 182 |
+
"grad_norm": 0.18915531039237976,
|
| 183 |
+
"learning_rate": 0.00042105263157894734,
|
| 184 |
+
"loss": 0.0343,
|
| 185 |
+
"step": 600
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 6.031,
|
| 189 |
+
"grad_norm": 0.16215360164642334,
|
| 190 |
+
"learning_rate": 0.00039473684210526315,
|
| 191 |
+
"loss": 0.0217,
|
| 192 |
+
"step": 625
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 6.056,
|
| 196 |
+
"grad_norm": 0.3027922213077545,
|
| 197 |
+
"learning_rate": 0.00036842105263157896,
|
| 198 |
+
"loss": 0.0216,
|
| 199 |
+
"step": 650
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 6.081,
|
| 203 |
+
"grad_norm": 0.20284023880958557,
|
| 204 |
+
"learning_rate": 0.00034210526315789477,
|
| 205 |
+
"loss": 0.0217,
|
| 206 |
+
"step": 675
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 7.007,
|
| 210 |
+
"grad_norm": 0.10826993733644485,
|
| 211 |
+
"learning_rate": 0.00031578947368421053,
|
| 212 |
+
"loss": 0.0182,
|
| 213 |
+
"step": 700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 7.032,
|
| 217 |
+
"grad_norm": 0.08263543248176575,
|
| 218 |
+
"learning_rate": 0.00028947368421052634,
|
| 219 |
+
"loss": 0.0129,
|
| 220 |
+
"step": 725
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 7.057,
|
| 224 |
+
"grad_norm": 0.09080210328102112,
|
| 225 |
+
"learning_rate": 0.0002631578947368421,
|
| 226 |
+
"loss": 0.0122,
|
| 227 |
+
"step": 750
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 7.082,
|
| 231 |
+
"grad_norm": 0.12056039273738861,
|
| 232 |
+
"learning_rate": 0.00023684210526315788,
|
| 233 |
+
"loss": 0.0135,
|
| 234 |
+
"step": 775
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 8.008,
|
| 238 |
+
"grad_norm": 0.042966585606336594,
|
| 239 |
+
"learning_rate": 0.00021052631578947367,
|
| 240 |
+
"loss": 0.0117,
|
| 241 |
+
"step": 800
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.033,
|
| 245 |
+
"grad_norm": 0.09803847968578339,
|
| 246 |
+
"learning_rate": 0.00018421052631578948,
|
| 247 |
+
"loss": 0.0097,
|
| 248 |
+
"step": 825
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.058,
|
| 252 |
+
"grad_norm": 0.05925946682691574,
|
| 253 |
+
"learning_rate": 0.00015789473684210527,
|
| 254 |
+
"loss": 0.0098,
|
| 255 |
+
"step": 850
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.083,
|
| 259 |
+
"grad_norm": 0.06515707820653915,
|
| 260 |
+
"learning_rate": 0.00013157894736842105,
|
| 261 |
+
"loss": 0.0091,
|
| 262 |
+
"step": 875
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 9.009,
|
| 266 |
+
"grad_norm": 0.051406506448984146,
|
| 267 |
+
"learning_rate": 0.00010526315789473683,
|
| 268 |
+
"loss": 0.0086,
|
| 269 |
+
"step": 900
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 9.034,
|
| 273 |
+
"grad_norm": 0.03954557701945305,
|
| 274 |
+
"learning_rate": 7.894736842105263e-05,
|
| 275 |
+
"loss": 0.0078,
|
| 276 |
+
"step": 925
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 9.059,
|
| 280 |
+
"grad_norm": 0.05422484129667282,
|
| 281 |
+
"learning_rate": 5.263157894736842e-05,
|
| 282 |
+
"loss": 0.0076,
|
| 283 |
+
"step": 950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 9.084,
|
| 287 |
+
"grad_norm": 0.04248082637786865,
|
| 288 |
+
"learning_rate": 2.631578947368421e-05,
|
| 289 |
+
"loss": 0.0081,
|
| 290 |
+
"step": 975
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 10.01,
|
| 294 |
+
"grad_norm": 0.04863487556576729,
|
| 295 |
+
"learning_rate": 0.0,
|
| 296 |
+
"loss": 0.0075,
|
| 297 |
+
"step": 1000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 10.01,
|
| 301 |
+
"eval_loss": 1.5216612815856934,
|
| 302 |
+
"eval_runtime": 357.9658,
|
| 303 |
+
"eval_samples_per_second": 9.076,
|
| 304 |
+
"eval_steps_per_second": 1.137,
|
| 305 |
+
"step": 1000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 10.01,
|
| 309 |
+
"step": 1000,
|
| 310 |
+
"total_flos": 9.3113310633984e+18,
|
| 311 |
+
"train_loss": 0.11658428072929382,
|
| 312 |
+
"train_runtime": 5497.3683,
|
| 313 |
+
"train_samples_per_second": 5.821,
|
| 314 |
+
"train_steps_per_second": 0.182
|
| 315 |
+
}
|
| 316 |
+
],
|
| 317 |
+
"logging_steps": 25,
|
| 318 |
+
"max_steps": 1000,
|
| 319 |
+
"num_input_tokens_seen": 0,
|
| 320 |
+
"num_train_epochs": 9223372036854775807,
|
| 321 |
+
"save_steps": 1000,
|
| 322 |
+
"stateful_callbacks": {
|
| 323 |
+
"TrainerControl": {
|
| 324 |
+
"args": {
|
| 325 |
+
"should_epoch_stop": false,
|
| 326 |
+
"should_evaluate": false,
|
| 327 |
+
"should_log": false,
|
| 328 |
+
"should_save": true,
|
| 329 |
+
"should_training_stop": true
|
| 330 |
+
},
|
| 331 |
+
"attributes": {}
|
| 332 |
+
}
|
| 333 |
+
},
|
| 334 |
+
"total_flos": 9.3113310633984e+18,
|
| 335 |
+
"train_batch_size": 32,
|
| 336 |
+
"trial_name": null,
|
| 337 |
+
"trial_params": null
|
| 338 |
+
}
|