Commit
•
3b2a89b
1
Parent(s):
c1f461a
Training in progress, epoch 1
Browse files- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +11 -249
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a365e4891d90ec23233f68651248b0bb5da2d876f36817a4be0ad6f4f0c322
|
| 3 |
+
size 721661957
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377646433
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea916919791655f74aec3b70a6233614608427e834da06bc5f606ea72149c620
|
| 3 |
size 377646433
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41734c590d4ca9111afda14d4d6e0db4819c1b65e8ffee27fa29d4e1cde666e4
|
| 3 |
+
size 14639
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd86c1f3d5f1b7e58ab1b190ff0893321dea6cfb611bb6b4388ebc93c6931aa8
|
| 3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a50eceed5d5a14aef24a7445d77f16047b39c151ba5bdc2775618ddbda6486ac
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,271 +1,33 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
-
"learning_rate": 9.
|
| 13 |
-
"loss":
|
| 14 |
"step": 739
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
-
"eval_cer": 0
|
| 19 |
-
"eval_loss": 3.
|
| 20 |
-
"eval_new_wer": 0
|
| 21 |
"eval_old_wer": 1.0,
|
| 22 |
-
"eval_runtime": 7.
|
| 23 |
-
"eval_samples_per_second": 24.
|
| 24 |
-
"eval_steps_per_second": 3.
|
| 25 |
"step": 739
|
| 26 |
-
},
|
| 27 |
-
{
|
| 28 |
-
"epoch": 2.0,
|
| 29 |
-
"learning_rate": 9.132086221631374e-05,
|
| 30 |
-
"loss": 3.7546,
|
| 31 |
-
"step": 1478
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 2.0,
|
| 35 |
-
"eval_cer": 0.9636363636363636,
|
| 36 |
-
"eval_loss": 3.780017852783203,
|
| 37 |
-
"eval_new_wer": 0.9,
|
| 38 |
-
"eval_old_wer": 1.0,
|
| 39 |
-
"eval_runtime": 7.3406,
|
| 40 |
-
"eval_samples_per_second": 24.521,
|
| 41 |
-
"eval_steps_per_second": 3.133,
|
| 42 |
-
"step": 1478
|
| 43 |
-
},
|
| 44 |
-
{
|
| 45 |
-
"epoch": 3.0,
|
| 46 |
-
"learning_rate": 8.43034849491976e-05,
|
| 47 |
-
"loss": 3.4946,
|
| 48 |
-
"step": 2217
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 3.0,
|
| 52 |
-
"eval_cer": 0.9636363636363636,
|
| 53 |
-
"eval_loss": 3.61942720413208,
|
| 54 |
-
"eval_new_wer": 0.9,
|
| 55 |
-
"eval_old_wer": 1.0,
|
| 56 |
-
"eval_runtime": 7.4322,
|
| 57 |
-
"eval_samples_per_second": 24.219,
|
| 58 |
-
"eval_steps_per_second": 3.095,
|
| 59 |
-
"step": 2217
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 4.0,
|
| 63 |
-
"learning_rate": 7.728610768208148e-05,
|
| 64 |
-
"loss": 3.4427,
|
| 65 |
-
"step": 2956
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 4.0,
|
| 69 |
-
"eval_cer": 0.9636363636363636,
|
| 70 |
-
"eval_loss": 3.581315040588379,
|
| 71 |
-
"eval_new_wer": 0.9,
|
| 72 |
-
"eval_old_wer": 1.0,
|
| 73 |
-
"eval_runtime": 7.2928,
|
| 74 |
-
"eval_samples_per_second": 24.682,
|
| 75 |
-
"eval_steps_per_second": 3.154,
|
| 76 |
-
"step": 2956
|
| 77 |
-
},
|
| 78 |
-
{
|
| 79 |
-
"epoch": 5.0,
|
| 80 |
-
"learning_rate": 7.026873041496534e-05,
|
| 81 |
-
"loss": 3.4094,
|
| 82 |
-
"step": 3695
|
| 83 |
-
},
|
| 84 |
-
{
|
| 85 |
-
"epoch": 5.0,
|
| 86 |
-
"eval_cer": 0.9636363636363636,
|
| 87 |
-
"eval_loss": 3.5385422706604004,
|
| 88 |
-
"eval_new_wer": 0.9,
|
| 89 |
-
"eval_old_wer": 1.0,
|
| 90 |
-
"eval_runtime": 7.2804,
|
| 91 |
-
"eval_samples_per_second": 24.724,
|
| 92 |
-
"eval_steps_per_second": 3.159,
|
| 93 |
-
"step": 3695
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 6.0,
|
| 97 |
-
"learning_rate": 6.325135314784922e-05,
|
| 98 |
-
"loss": 3.384,
|
| 99 |
-
"step": 4434
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 6.0,
|
| 103 |
-
"eval_cer": 0.9636363636363636,
|
| 104 |
-
"eval_loss": 3.447321891784668,
|
| 105 |
-
"eval_new_wer": 0.9,
|
| 106 |
-
"eval_old_wer": 1.0,
|
| 107 |
-
"eval_runtime": 7.2913,
|
| 108 |
-
"eval_samples_per_second": 24.687,
|
| 109 |
-
"eval_steps_per_second": 3.154,
|
| 110 |
-
"step": 4434
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 7.0,
|
| 114 |
-
"learning_rate": 5.6233975880733084e-05,
|
| 115 |
-
"loss": 3.3675,
|
| 116 |
-
"step": 5173
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 7.0,
|
| 120 |
-
"eval_cer": 0.9636363636363636,
|
| 121 |
-
"eval_loss": 3.407554864883423,
|
| 122 |
-
"eval_new_wer": 0.9,
|
| 123 |
-
"eval_old_wer": 1.0,
|
| 124 |
-
"eval_runtime": 7.8277,
|
| 125 |
-
"eval_samples_per_second": 22.995,
|
| 126 |
-
"eval_steps_per_second": 2.938,
|
| 127 |
-
"step": 5173
|
| 128 |
-
},
|
| 129 |
-
{
|
| 130 |
-
"epoch": 8.0,
|
| 131 |
-
"learning_rate": 4.9216598613616946e-05,
|
| 132 |
-
"loss": 3.3539,
|
| 133 |
-
"step": 5912
|
| 134 |
-
},
|
| 135 |
-
{
|
| 136 |
-
"epoch": 8.0,
|
| 137 |
-
"eval_cer": 0.9636363636363636,
|
| 138 |
-
"eval_loss": 3.375277042388916,
|
| 139 |
-
"eval_new_wer": 0.9,
|
| 140 |
-
"eval_old_wer": 1.0,
|
| 141 |
-
"eval_runtime": 7.2374,
|
| 142 |
-
"eval_samples_per_second": 24.871,
|
| 143 |
-
"eval_steps_per_second": 3.178,
|
| 144 |
-
"step": 5912
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"epoch": 9.0,
|
| 148 |
-
"learning_rate": 4.2199221346500814e-05,
|
| 149 |
-
"loss": 3.3382,
|
| 150 |
-
"step": 6651
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 9.0,
|
| 154 |
-
"eval_cer": 0.9636363636363636,
|
| 155 |
-
"eval_loss": 3.335272789001465,
|
| 156 |
-
"eval_new_wer": 0.9,
|
| 157 |
-
"eval_old_wer": 1.0,
|
| 158 |
-
"eval_runtime": 7.2156,
|
| 159 |
-
"eval_samples_per_second": 24.946,
|
| 160 |
-
"eval_steps_per_second": 3.188,
|
| 161 |
-
"step": 6651
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"epoch": 10.0,
|
| 165 |
-
"learning_rate": 3.5181844079384676e-05,
|
| 166 |
-
"loss": 3.3304,
|
| 167 |
-
"step": 7390
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 10.0,
|
| 171 |
-
"eval_cer": 0.9636363636363636,
|
| 172 |
-
"eval_loss": 3.328141212463379,
|
| 173 |
-
"eval_new_wer": 0.9,
|
| 174 |
-
"eval_old_wer": 1.0,
|
| 175 |
-
"eval_runtime": 7.5963,
|
| 176 |
-
"eval_samples_per_second": 23.696,
|
| 177 |
-
"eval_steps_per_second": 3.028,
|
| 178 |
-
"step": 7390
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 11.0,
|
| 182 |
-
"learning_rate": 2.816446681226854e-05,
|
| 183 |
-
"loss": 3.3184,
|
| 184 |
-
"step": 8129
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 11.0,
|
| 188 |
-
"eval_cer": 0.9636363636363636,
|
| 189 |
-
"eval_loss": 3.3093180656433105,
|
| 190 |
-
"eval_new_wer": 0.9,
|
| 191 |
-
"eval_old_wer": 1.0,
|
| 192 |
-
"eval_runtime": 7.2653,
|
| 193 |
-
"eval_samples_per_second": 24.775,
|
| 194 |
-
"eval_steps_per_second": 3.166,
|
| 195 |
-
"step": 8129
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 12.0,
|
| 199 |
-
"learning_rate": 2.1147089545152407e-05,
|
| 200 |
-
"loss": 3.3116,
|
| 201 |
-
"step": 8868
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 12.0,
|
| 205 |
-
"eval_cer": 0.9636363636363636,
|
| 206 |
-
"eval_loss": 3.3055644035339355,
|
| 207 |
-
"eval_new_wer": 0.9,
|
| 208 |
-
"eval_old_wer": 1.0,
|
| 209 |
-
"eval_runtime": 7.2417,
|
| 210 |
-
"eval_samples_per_second": 24.856,
|
| 211 |
-
"eval_steps_per_second": 3.176,
|
| 212 |
-
"step": 8868
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 13.0,
|
| 216 |
-
"learning_rate": 1.4129712278036275e-05,
|
| 217 |
-
"loss": 3.3032,
|
| 218 |
-
"step": 9607
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 13.0,
|
| 222 |
-
"eval_cer": 0.9636363636363636,
|
| 223 |
-
"eval_loss": 3.3021399974823,
|
| 224 |
-
"eval_new_wer": 0.9,
|
| 225 |
-
"eval_old_wer": 1.0,
|
| 226 |
-
"eval_runtime": 7.3911,
|
| 227 |
-
"eval_samples_per_second": 24.354,
|
| 228 |
-
"eval_steps_per_second": 3.112,
|
| 229 |
-
"step": 9607
|
| 230 |
-
},
|
| 231 |
-
{
|
| 232 |
-
"epoch": 14.0,
|
| 233 |
-
"learning_rate": 7.112335010920141e-06,
|
| 234 |
-
"loss": 3.3038,
|
| 235 |
-
"step": 10346
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 14.0,
|
| 239 |
-
"eval_cer": 0.9636363636363636,
|
| 240 |
-
"eval_loss": 3.3013970851898193,
|
| 241 |
-
"eval_new_wer": 0.9,
|
| 242 |
-
"eval_old_wer": 1.0,
|
| 243 |
-
"eval_runtime": 7.3511,
|
| 244 |
-
"eval_samples_per_second": 24.486,
|
| 245 |
-
"eval_steps_per_second": 3.129,
|
| 246 |
-
"step": 10346
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 15.0,
|
| 250 |
-
"learning_rate": 9.495774380400722e-08,
|
| 251 |
-
"loss": 3.2971,
|
| 252 |
-
"step": 11085
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"epoch": 15.0,
|
| 256 |
-
"eval_cer": 0.9636363636363636,
|
| 257 |
-
"eval_loss": 3.2989487648010254,
|
| 258 |
-
"eval_new_wer": 0.9,
|
| 259 |
-
"eval_old_wer": 1.0,
|
| 260 |
-
"eval_runtime": 7.2244,
|
| 261 |
-
"eval_samples_per_second": 24.915,
|
| 262 |
-
"eval_steps_per_second": 3.184,
|
| 263 |
-
"step": 11085
|
| 264 |
}
|
| 265 |
],
|
| 266 |
"max_steps": 11085,
|
| 267 |
"num_train_epochs": 15,
|
| 268 |
-
"total_flos":
|
| 269 |
"trial_name": null,
|
| 270 |
"trial_params": null
|
| 271 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 739,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 9.831924793466908e-05,
|
| 13 |
+
"loss": 18.2448,
|
| 14 |
"step": 739
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
+
"eval_cer": 1.0,
|
| 19 |
+
"eval_loss": 3.3216891288757324,
|
| 20 |
+
"eval_new_wer": 1.0,
|
| 21 |
"eval_old_wer": 1.0,
|
| 22 |
+
"eval_runtime": 7.2541,
|
| 23 |
+
"eval_samples_per_second": 24.814,
|
| 24 |
+
"eval_steps_per_second": 3.171,
|
| 25 |
"step": 739
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
],
|
| 28 |
"max_steps": 11085,
|
| 29 |
"num_train_epochs": 15,
|
| 30 |
+
"total_flos": 5.7487243575776256e+17,
|
| 31 |
"trial_name": null,
|
| 32 |
"trial_params": null
|
| 33 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3387
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c03ddeae8e5b6c8b1c706e99c450b1a83dc9b242862b2db4c5fb889a74640900
|
| 3 |
size 3387
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377646433
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea916919791655f74aec3b70a6233614608427e834da06bc5f606ea72149c620
|
| 3 |
size 377646433
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3387
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c03ddeae8e5b6c8b1c706e99c450b1a83dc9b242862b2db4c5fb889a74640900
|
| 3 |
size 3387
|