Commit
•
b6b1319
1
Parent(s):
d6d841c
End of training
Browse files- README.md +2 -0
- all_results.json +15 -0
- eval_results.json +9 -0
- runs/Sep03_06-18-05_c461da42ad14/events.out.tfevents.1725348640.c461da42ad14.1376.1 +3 -0
- train_results.json +9 -0
- trainer_state.json +298 -0
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/wav2vec2-large-xlsr-53
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- wer
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/wav2vec2-large-xlsr-53
|
| 4 |
tags:
|
| 5 |
+
- automatic-speech-recognition
|
| 6 |
+
- ./data-configs/btb-cv-other.json
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- wer
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.2075471698113207,
|
| 3 |
+
"eval_loss": 0.49337518215179443,
|
| 4 |
+
"eval_runtime": 195.3217,
|
| 5 |
+
"eval_samples": 7022,
|
| 6 |
+
"eval_samples_per_second": 35.951,
|
| 7 |
+
"eval_steps_per_second": 0.563,
|
| 8 |
+
"eval_wer": 0.37760267874938547,
|
| 9 |
+
"total_flos": 9.085819982279884e+18,
|
| 10 |
+
"train_loss": 0.9942695980072022,
|
| 11 |
+
"train_runtime": 6320.527,
|
| 12 |
+
"train_samples": 52993,
|
| 13 |
+
"train_samples_per_second": 10.126,
|
| 14 |
+
"train_steps_per_second": 1.266
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.2075471698113207,
|
| 3 |
+
"eval_loss": 0.49337518215179443,
|
| 4 |
+
"eval_runtime": 195.3217,
|
| 5 |
+
"eval_samples": 7022,
|
| 6 |
+
"eval_samples_per_second": 35.951,
|
| 7 |
+
"eval_steps_per_second": 0.563,
|
| 8 |
+
"eval_wer": 0.37760267874938547
|
| 9 |
+
}
|
runs/Sep03_06-18-05_c461da42ad14/events.out.tfevents.1725348640.c461da42ad14.1376.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d37482fa8291b6cb45cffbe5ba560fe6aba8323be68fe5e740f8c3e2ce4f99d3
|
| 3 |
+
size 406
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.2075471698113207,
|
| 3 |
+
"total_flos": 9.085819982279884e+18,
|
| 4 |
+
"train_loss": 0.9942695980072022,
|
| 5 |
+
"train_runtime": 6320.527,
|
| 6 |
+
"train_samples": 52993,
|
| 7 |
+
"train_samples_per_second": 10.126,
|
| 8 |
+
"train_steps_per_second": 1.266
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.2075471698113207,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07547169811320754,
|
| 13 |
+
"grad_norm": 9.590713500976562,
|
| 14 |
+
"learning_rate": 0.00018449999999999999,
|
| 15 |
+
"loss": 5.1054,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07547169811320754,
|
| 20 |
+
"eval_loss": 2.816082239151001,
|
| 21 |
+
"eval_runtime": 195.1014,
|
| 22 |
+
"eval_samples_per_second": 35.992,
|
| 23 |
+
"eval_steps_per_second": 0.564,
|
| 24 |
+
"eval_wer": 1.0,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.1509433962264151,
|
| 29 |
+
"grad_norm": 6.886263847351074,
|
| 30 |
+
"learning_rate": 0.00029204166666666663,
|
| 31 |
+
"loss": 1.4196,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.1509433962264151,
|
| 36 |
+
"eval_loss": 1.168688178062439,
|
| 37 |
+
"eval_runtime": 193.3054,
|
| 38 |
+
"eval_samples_per_second": 36.326,
|
| 39 |
+
"eval_steps_per_second": 0.569,
|
| 40 |
+
"eval_wer": 0.7941110033351493,
|
| 41 |
+
"step": 1000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.22641509433962265,
|
| 45 |
+
"grad_norm": 3.8018798828125,
|
| 46 |
+
"learning_rate": 0.00027124999999999995,
|
| 47 |
+
"loss": 1.0028,
|
| 48 |
+
"step": 1500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.22641509433962265,
|
| 52 |
+
"eval_loss": 0.9889835119247437,
|
| 53 |
+
"eval_runtime": 194.0625,
|
| 54 |
+
"eval_samples_per_second": 36.184,
|
| 55 |
+
"eval_steps_per_second": 0.567,
|
| 56 |
+
"eval_wer": 0.6952523950623846,
|
| 57 |
+
"step": 1500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.3018867924528302,
|
| 61 |
+
"grad_norm": 9.146143913269043,
|
| 62 |
+
"learning_rate": 0.00025041666666666664,
|
| 63 |
+
"loss": 0.8942,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.3018867924528302,
|
| 68 |
+
"eval_loss": 0.8935320973396301,
|
| 69 |
+
"eval_runtime": 191.4777,
|
| 70 |
+
"eval_samples_per_second": 36.673,
|
| 71 |
+
"eval_steps_per_second": 0.574,
|
| 72 |
+
"eval_wer": 0.6194873702812953,
|
| 73 |
+
"step": 2000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.37735849056603776,
|
| 77 |
+
"grad_norm": 5.679136276245117,
|
| 78 |
+
"learning_rate": 0.0002295833333333333,
|
| 79 |
+
"loss": 0.8285,
|
| 80 |
+
"step": 2500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.37735849056603776,
|
| 84 |
+
"eval_loss": 0.8221403360366821,
|
| 85 |
+
"eval_runtime": 191.0145,
|
| 86 |
+
"eval_samples_per_second": 36.762,
|
| 87 |
+
"eval_steps_per_second": 0.576,
|
| 88 |
+
"eval_wer": 0.6075419551150029,
|
| 89 |
+
"step": 2500
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.4528301886792453,
|
| 93 |
+
"grad_norm": 7.3102006912231445,
|
| 94 |
+
"learning_rate": 0.00020879166666666664,
|
| 95 |
+
"loss": 0.763,
|
| 96 |
+
"step": 3000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.4528301886792453,
|
| 100 |
+
"eval_loss": 0.7164860963821411,
|
| 101 |
+
"eval_runtime": 191.5603,
|
| 102 |
+
"eval_samples_per_second": 36.657,
|
| 103 |
+
"eval_steps_per_second": 0.574,
|
| 104 |
+
"eval_wer": 0.5306873596513374,
|
| 105 |
+
"step": 3000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.5283018867924528,
|
| 109 |
+
"grad_norm": 4.605156898498535,
|
| 110 |
+
"learning_rate": 0.00018795833333333333,
|
| 111 |
+
"loss": 0.7203,
|
| 112 |
+
"step": 3500
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.5283018867924528,
|
| 116 |
+
"eval_loss": 0.6891956925392151,
|
| 117 |
+
"eval_runtime": 191.0308,
|
| 118 |
+
"eval_samples_per_second": 36.758,
|
| 119 |
+
"eval_steps_per_second": 0.576,
|
| 120 |
+
"eval_wer": 0.5053747724524642,
|
| 121 |
+
"step": 3500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6037735849056604,
|
| 125 |
+
"grad_norm": 4.3389763832092285,
|
| 126 |
+
"learning_rate": 0.000167125,
|
| 127 |
+
"loss": 0.7051,
|
| 128 |
+
"step": 4000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6037735849056604,
|
| 132 |
+
"eval_loss": 0.6848454475402832,
|
| 133 |
+
"eval_runtime": 192.1753,
|
| 134 |
+
"eval_samples_per_second": 36.54,
|
| 135 |
+
"eval_steps_per_second": 0.572,
|
| 136 |
+
"eval_wer": 0.5069825535816315,
|
| 137 |
+
"step": 4000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.6792452830188679,
|
| 141 |
+
"grad_norm": 5.629897117614746,
|
| 142 |
+
"learning_rate": 0.00014629166666666667,
|
| 143 |
+
"loss": 0.6568,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.6792452830188679,
|
| 148 |
+
"eval_loss": 0.6341728568077087,
|
| 149 |
+
"eval_runtime": 190.6714,
|
| 150 |
+
"eval_samples_per_second": 36.828,
|
| 151 |
+
"eval_steps_per_second": 0.577,
|
| 152 |
+
"eval_wer": 0.4925789606558684,
|
| 153 |
+
"step": 4500
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.7547169811320755,
|
| 157 |
+
"grad_norm": 5.2013421058654785,
|
| 158 |
+
"learning_rate": 0.0001255,
|
| 159 |
+
"loss": 0.6315,
|
| 160 |
+
"step": 5000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.7547169811320755,
|
| 164 |
+
"eval_loss": 0.59560626745224,
|
| 165 |
+
"eval_runtime": 192.113,
|
| 166 |
+
"eval_samples_per_second": 36.551,
|
| 167 |
+
"eval_steps_per_second": 0.573,
|
| 168 |
+
"eval_wer": 0.4493947567732763,
|
| 169 |
+
"step": 5000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.8301886792452831,
|
| 173 |
+
"grad_norm": 6.034324645996094,
|
| 174 |
+
"learning_rate": 0.00010466666666666667,
|
| 175 |
+
"loss": 0.6171,
|
| 176 |
+
"step": 5500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.8301886792452831,
|
| 180 |
+
"eval_loss": 0.5532522201538086,
|
| 181 |
+
"eval_runtime": 191.0439,
|
| 182 |
+
"eval_samples_per_second": 36.756,
|
| 183 |
+
"eval_steps_per_second": 0.576,
|
| 184 |
+
"eval_wer": 0.4304601443016782,
|
| 185 |
+
"step": 5500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.9056603773584906,
|
| 189 |
+
"grad_norm": 11.971189498901367,
|
| 190 |
+
"learning_rate": 8.383333333333333e-05,
|
| 191 |
+
"loss": 0.5717,
|
| 192 |
+
"step": 6000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.9056603773584906,
|
| 196 |
+
"eval_loss": 0.5359871983528137,
|
| 197 |
+
"eval_runtime": 188.0002,
|
| 198 |
+
"eval_samples_per_second": 37.351,
|
| 199 |
+
"eval_steps_per_second": 0.585,
|
| 200 |
+
"eval_wer": 0.42121208094712925,
|
| 201 |
+
"step": 6000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.9811320754716981,
|
| 205 |
+
"grad_norm": 13.140325546264648,
|
| 206 |
+
"learning_rate": 6.304166666666666e-05,
|
| 207 |
+
"loss": 0.5699,
|
| 208 |
+
"step": 6500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.9811320754716981,
|
| 212 |
+
"eval_loss": 0.518449068069458,
|
| 213 |
+
"eval_runtime": 186.6376,
|
| 214 |
+
"eval_samples_per_second": 37.624,
|
| 215 |
+
"eval_steps_per_second": 0.589,
|
| 216 |
+
"eval_wer": 0.4039516868414409,
|
| 217 |
+
"step": 6500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.0566037735849056,
|
| 221 |
+
"grad_norm": 1.923995018005371,
|
| 222 |
+
"learning_rate": 4.2208333333333334e-05,
|
| 223 |
+
"loss": 0.4905,
|
| 224 |
+
"step": 7000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.0566037735849056,
|
| 228 |
+
"eval_loss": 0.5081383585929871,
|
| 229 |
+
"eval_runtime": 187.1769,
|
| 230 |
+
"eval_samples_per_second": 37.515,
|
| 231 |
+
"eval_steps_per_second": 0.588,
|
| 232 |
+
"eval_wer": 0.39667016569446845,
|
| 233 |
+
"step": 7000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.1320754716981132,
|
| 237 |
+
"grad_norm": 4.82823371887207,
|
| 238 |
+
"learning_rate": 2.1374999999999998e-05,
|
| 239 |
+
"loss": 0.4706,
|
| 240 |
+
"step": 7500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.1320754716981132,
|
| 244 |
+
"eval_loss": 0.49912941455841064,
|
| 245 |
+
"eval_runtime": 187.5036,
|
| 246 |
+
"eval_samples_per_second": 37.45,
|
| 247 |
+
"eval_steps_per_second": 0.587,
|
| 248 |
+
"eval_wer": 0.3825323217156752,
|
| 249 |
+
"step": 7500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.2075471698113207,
|
| 253 |
+
"grad_norm": 2.875157594680786,
|
| 254 |
+
"learning_rate": 6.249999999999999e-07,
|
| 255 |
+
"loss": 0.4614,
|
| 256 |
+
"step": 8000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.2075471698113207,
|
| 260 |
+
"eval_loss": 0.49337518215179443,
|
| 261 |
+
"eval_runtime": 189.5607,
|
| 262 |
+
"eval_samples_per_second": 37.044,
|
| 263 |
+
"eval_steps_per_second": 0.58,
|
| 264 |
+
"eval_wer": 0.37760267874938547,
|
| 265 |
+
"step": 8000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.2075471698113207,
|
| 269 |
+
"step": 8000,
|
| 270 |
+
"total_flos": 9.085819982279884e+18,
|
| 271 |
+
"train_loss": 0.9942695980072022,
|
| 272 |
+
"train_runtime": 6320.527,
|
| 273 |
+
"train_samples_per_second": 10.126,
|
| 274 |
+
"train_steps_per_second": 1.266
|
| 275 |
+
}
|
| 276 |
+
],
|
| 277 |
+
"logging_steps": 500,
|
| 278 |
+
"max_steps": 8000,
|
| 279 |
+
"num_input_tokens_seen": 0,
|
| 280 |
+
"num_train_epochs": 2,
|
| 281 |
+
"save_steps": 500,
|
| 282 |
+
"stateful_callbacks": {
|
| 283 |
+
"TrainerControl": {
|
| 284 |
+
"args": {
|
| 285 |
+
"should_epoch_stop": false,
|
| 286 |
+
"should_evaluate": false,
|
| 287 |
+
"should_log": false,
|
| 288 |
+
"should_save": true,
|
| 289 |
+
"should_training_stop": true
|
| 290 |
+
},
|
| 291 |
+
"attributes": {}
|
| 292 |
+
}
|
| 293 |
+
},
|
| 294 |
+
"total_flos": 9.085819982279884e+18,
|
| 295 |
+
"train_batch_size": 8,
|
| 296 |
+
"trial_name": null,
|
| 297 |
+
"trial_params": null
|
| 298 |
+
}
|