Commit
•
68125e7
1
Parent(s):
e1fe65f
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:ca2488c7c7e90101e4b14aa522a59ad2bf2118296861b9ea9158cca63add0769
|
| 3 |
+
size 721655813
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377643361
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77a87c8ec786e02155f6f7dec60ce648c9a2caaee133fb17f93a3d7e1be007a9
|
| 3 |
size 377643361
|
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:ea49d5f6f6fde3589f0e548b39f94eb336cef5282e7f7120921ec12941b1115e
|
| 3 |
+
size 14575
|
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:d86624103fa47ceeb667c5882baed38a7d9803787a13ec04e49ed10f8b91695a
|
| 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:fac6afd13d5ae29d5fa67e15b29421215e62ba138c49b108fef3d1c1618449c6
|
| 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": 622
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
-
"eval_cer": 0.
|
| 19 |
-
"eval_loss":
|
| 20 |
-
"eval_new_wer": 0.
|
| 21 |
"eval_old_wer": 1.0,
|
| 22 |
-
"eval_runtime":
|
| 23 |
-
"eval_samples_per_second":
|
| 24 |
-
"eval_steps_per_second": 3.
|
| 25 |
"step": 622
|
| 26 |
-
},
|
| 27 |
-
{
|
| 28 |
-
"epoch": 2.0,
|
| 29 |
-
"learning_rate": 9.130189530685921e-05,
|
| 30 |
-
"loss": 3.6309,
|
| 31 |
-
"step": 1244
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 2.0,
|
| 35 |
-
"eval_cer": 0.9636363636363636,
|
| 36 |
-
"eval_loss": 4.148990154266357,
|
| 37 |
-
"eval_new_wer": 0.9,
|
| 38 |
-
"eval_old_wer": 1.0,
|
| 39 |
-
"eval_runtime": 8.5756,
|
| 40 |
-
"eval_samples_per_second": 24.488,
|
| 41 |
-
"eval_steps_per_second": 3.148,
|
| 42 |
-
"step": 1244
|
| 43 |
-
},
|
| 44 |
-
{
|
| 45 |
-
"epoch": 3.0,
|
| 46 |
-
"learning_rate": 8.428474729241878e-05,
|
| 47 |
-
"loss": 3.3586,
|
| 48 |
-
"step": 1866
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 3.0,
|
| 52 |
-
"eval_cer": 0.9636363636363636,
|
| 53 |
-
"eval_loss": 4.03645133972168,
|
| 54 |
-
"eval_new_wer": 0.9,
|
| 55 |
-
"eval_old_wer": 1.0,
|
| 56 |
-
"eval_runtime": 8.62,
|
| 57 |
-
"eval_samples_per_second": 24.362,
|
| 58 |
-
"eval_steps_per_second": 3.132,
|
| 59 |
-
"step": 1866
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 4.0,
|
| 63 |
-
"learning_rate": 7.726759927797835e-05,
|
| 64 |
-
"loss": 3.319,
|
| 65 |
-
"step": 2488
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 4.0,
|
| 69 |
-
"eval_cer": 0.9636363636363636,
|
| 70 |
-
"eval_loss": 3.9594714641571045,
|
| 71 |
-
"eval_new_wer": 0.9,
|
| 72 |
-
"eval_old_wer": 1.0,
|
| 73 |
-
"eval_runtime": 8.8026,
|
| 74 |
-
"eval_samples_per_second": 23.857,
|
| 75 |
-
"eval_steps_per_second": 3.067,
|
| 76 |
-
"step": 2488
|
| 77 |
-
},
|
| 78 |
-
{
|
| 79 |
-
"epoch": 5.0,
|
| 80 |
-
"learning_rate": 7.02504512635379e-05,
|
| 81 |
-
"loss": 3.2905,
|
| 82 |
-
"step": 3110
|
| 83 |
-
},
|
| 84 |
-
{
|
| 85 |
-
"epoch": 5.0,
|
| 86 |
-
"eval_cer": 0.9636363636363636,
|
| 87 |
-
"eval_loss": 3.8774044513702393,
|
| 88 |
-
"eval_new_wer": 0.9,
|
| 89 |
-
"eval_old_wer": 1.0,
|
| 90 |
-
"eval_runtime": 8.6675,
|
| 91 |
-
"eval_samples_per_second": 24.228,
|
| 92 |
-
"eval_steps_per_second": 3.115,
|
| 93 |
-
"step": 3110
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 6.0,
|
| 97 |
-
"learning_rate": 6.323330324909747e-05,
|
| 98 |
-
"loss": 3.2693,
|
| 99 |
-
"step": 3732
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 6.0,
|
| 103 |
-
"eval_cer": 0.9636363636363636,
|
| 104 |
-
"eval_loss": 3.8836023807525635,
|
| 105 |
-
"eval_new_wer": 0.9,
|
| 106 |
-
"eval_old_wer": 1.0,
|
| 107 |
-
"eval_runtime": 8.4359,
|
| 108 |
-
"eval_samples_per_second": 24.894,
|
| 109 |
-
"eval_steps_per_second": 3.201,
|
| 110 |
-
"step": 3732
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 7.0,
|
| 114 |
-
"learning_rate": 5.621615523465704e-05,
|
| 115 |
-
"loss": 3.2546,
|
| 116 |
-
"step": 4354
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 7.0,
|
| 120 |
-
"eval_cer": 0.9636363636363636,
|
| 121 |
-
"eval_loss": 3.8469648361206055,
|
| 122 |
-
"eval_new_wer": 0.9,
|
| 123 |
-
"eval_old_wer": 1.0,
|
| 124 |
-
"eval_runtime": 8.5607,
|
| 125 |
-
"eval_samples_per_second": 24.531,
|
| 126 |
-
"eval_steps_per_second": 3.154,
|
| 127 |
-
"step": 4354
|
| 128 |
-
},
|
| 129 |
-
{
|
| 130 |
-
"epoch": 8.0,
|
| 131 |
-
"learning_rate": 4.9199007220216606e-05,
|
| 132 |
-
"loss": 3.2424,
|
| 133 |
-
"step": 4976
|
| 134 |
-
},
|
| 135 |
-
{
|
| 136 |
-
"epoch": 8.0,
|
| 137 |
-
"eval_cer": 0.9636363636363636,
|
| 138 |
-
"eval_loss": 3.798175811767578,
|
| 139 |
-
"eval_new_wer": 0.9,
|
| 140 |
-
"eval_old_wer": 1.0,
|
| 141 |
-
"eval_runtime": 8.5308,
|
| 142 |
-
"eval_samples_per_second": 24.617,
|
| 143 |
-
"eval_steps_per_second": 3.165,
|
| 144 |
-
"step": 4976
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"epoch": 9.0,
|
| 148 |
-
"learning_rate": 4.2181859205776176e-05,
|
| 149 |
-
"loss": 3.2306,
|
| 150 |
-
"step": 5598
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 9.0,
|
| 154 |
-
"eval_cer": 0.9636363636363636,
|
| 155 |
-
"eval_loss": 3.7588889598846436,
|
| 156 |
-
"eval_new_wer": 0.9,
|
| 157 |
-
"eval_old_wer": 1.0,
|
| 158 |
-
"eval_runtime": 8.6596,
|
| 159 |
-
"eval_samples_per_second": 24.25,
|
| 160 |
-
"eval_steps_per_second": 3.118,
|
| 161 |
-
"step": 5598
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"epoch": 10.0,
|
| 165 |
-
"learning_rate": 3.516471119133574e-05,
|
| 166 |
-
"loss": 3.2218,
|
| 167 |
-
"step": 6220
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 10.0,
|
| 171 |
-
"eval_cer": 0.9636363636363636,
|
| 172 |
-
"eval_loss": 3.738402843475342,
|
| 173 |
-
"eval_new_wer": 0.9,
|
| 174 |
-
"eval_old_wer": 1.0,
|
| 175 |
-
"eval_runtime": 8.5202,
|
| 176 |
-
"eval_samples_per_second": 24.647,
|
| 177 |
-
"eval_steps_per_second": 3.169,
|
| 178 |
-
"step": 6220
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 11.0,
|
| 182 |
-
"learning_rate": 2.814756317689531e-05,
|
| 183 |
-
"loss": 3.2149,
|
| 184 |
-
"step": 6842
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 11.0,
|
| 188 |
-
"eval_cer": 0.9636363636363636,
|
| 189 |
-
"eval_loss": 3.7330896854400635,
|
| 190 |
-
"eval_new_wer": 0.9,
|
| 191 |
-
"eval_old_wer": 1.0,
|
| 192 |
-
"eval_runtime": 8.6236,
|
| 193 |
-
"eval_samples_per_second": 24.352,
|
| 194 |
-
"eval_steps_per_second": 3.131,
|
| 195 |
-
"step": 6842
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 12.0,
|
| 199 |
-
"learning_rate": 2.1130415162454876e-05,
|
| 200 |
-
"loss": 3.2088,
|
| 201 |
-
"step": 7464
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 12.0,
|
| 205 |
-
"eval_cer": 0.9636363636363636,
|
| 206 |
-
"eval_loss": 3.721147298812866,
|
| 207 |
-
"eval_new_wer": 0.9,
|
| 208 |
-
"eval_old_wer": 1.0,
|
| 209 |
-
"eval_runtime": 8.7097,
|
| 210 |
-
"eval_samples_per_second": 24.111,
|
| 211 |
-
"eval_steps_per_second": 3.1,
|
| 212 |
-
"step": 7464
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 13.0,
|
| 216 |
-
"learning_rate": 1.4113267148014443e-05,
|
| 217 |
-
"loss": 3.2056,
|
| 218 |
-
"step": 8086
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 13.0,
|
| 222 |
-
"eval_cer": 0.9636363636363636,
|
| 223 |
-
"eval_loss": 3.7029576301574707,
|
| 224 |
-
"eval_new_wer": 0.9,
|
| 225 |
-
"eval_old_wer": 1.0,
|
| 226 |
-
"eval_runtime": 8.5372,
|
| 227 |
-
"eval_samples_per_second": 24.598,
|
| 228 |
-
"eval_steps_per_second": 3.163,
|
| 229 |
-
"step": 8086
|
| 230 |
-
},
|
| 231 |
-
{
|
| 232 |
-
"epoch": 14.0,
|
| 233 |
-
"learning_rate": 7.0961191335740075e-06,
|
| 234 |
-
"loss": 3.2031,
|
| 235 |
-
"step": 8708
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 14.0,
|
| 239 |
-
"eval_cer": 0.9636363636363636,
|
| 240 |
-
"eval_loss": 3.6995913982391357,
|
| 241 |
-
"eval_new_wer": 0.9,
|
| 242 |
-
"eval_old_wer": 1.0,
|
| 243 |
-
"eval_runtime": 8.6411,
|
| 244 |
-
"eval_samples_per_second": 24.302,
|
| 245 |
-
"eval_steps_per_second": 3.125,
|
| 246 |
-
"step": 8708
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 15.0,
|
| 250 |
-
"learning_rate": 7.8971119133574e-08,
|
| 251 |
-
"loss": 3.1984,
|
| 252 |
-
"step": 9330
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"epoch": 15.0,
|
| 256 |
-
"eval_cer": 0.9636363636363636,
|
| 257 |
-
"eval_loss": 3.7015275955200195,
|
| 258 |
-
"eval_new_wer": 0.9,
|
| 259 |
-
"eval_old_wer": 1.0,
|
| 260 |
-
"eval_runtime": 8.7621,
|
| 261 |
-
"eval_samples_per_second": 23.967,
|
| 262 |
-
"eval_steps_per_second": 3.081,
|
| 263 |
-
"step": 9330
|
| 264 |
}
|
| 265 |
],
|
| 266 |
"max_steps": 9330,
|
| 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": 622,
|
| 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": 9.83303249097473e-05,
|
| 13 |
+
"loss": 16.7556,
|
| 14 |
"step": 622
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
+
"eval_cer": 0.9341991341991343,
|
| 19 |
+
"eval_loss": 3.3474249839782715,
|
| 20 |
+
"eval_new_wer": 0.9380952380952381,
|
| 21 |
"eval_old_wer": 1.0,
|
| 22 |
+
"eval_runtime": 7.7874,
|
| 23 |
+
"eval_samples_per_second": 26.967,
|
| 24 |
+
"eval_steps_per_second": 3.467,
|
| 25 |
"step": 622
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
],
|
| 28 |
"max_steps": 9330,
|
| 29 |
"num_train_epochs": 15,
|
| 30 |
+
"total_flos": 4.58996805867552e+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 sha256:0000b096c0b617d6be374ea1bea5add3f1148e5ae411824afcaf501618c33f42
|
| 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 377643361
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77a87c8ec786e02155f6f7dec60ce648c9a2caaee133fb17f93a3d7e1be007a9
|
| 3 |
size 377643361
|
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 sha256:0000b096c0b617d6be374ea1bea5add3f1148e5ae411824afcaf501618c33f42
|
| 3 |
size 3387
|