Commit
•
d1517a6
1
Parent(s):
0f000cc
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 +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +8 -246
- 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 sha256:5d184fe2a459d72ab4f17f9800832f7189c8809e50bf6f25e22d726b15e12b61
|
| 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 sha256:78b8af0529522cbae8a484627f1931663045d8e1f9d51e2919c7c377f92e91cf
|
| 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 14639
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c2d6b5f0154fde0c288bdb2ab6d96ec62bdc8d9fe5703db59a28c412b3261fa
|
| 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 sha256:9b63cb11ac01032c977cdc85c62fc3b92562156ab5c4471214784ecf2efc9205
|
| 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:e89163b4d12e6402024e5086a1eecd70185a21973d01ffc02723c8dcbaa443b9
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 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,
|
|
@@ -10,262 +10,24 @@
|
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
"learning_rate": 9.832425638877252e-05,
|
| 13 |
-
"loss":
|
| 14 |
"step": 670
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
"eval_cer": 1.0,
|
| 19 |
-
"eval_loss":
|
| 20 |
"eval_new_wer": 1.0,
|
| 21 |
"eval_old_wer": 1.0,
|
| 22 |
-
"eval_runtime": 6.
|
| 23 |
-
"eval_samples_per_second":
|
| 24 |
-
"eval_steps_per_second": 3.
|
| 25 |
"step": 670
|
| 26 |
-
},
|
| 27 |
-
{
|
| 28 |
-
"epoch": 2.0,
|
| 29 |
-
"learning_rate": 9.130708001675745e-05,
|
| 30 |
-
"loss": 3.6163,
|
| 31 |
-
"step": 1340
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 2.0,
|
| 35 |
-
"eval_cer": 1.0,
|
| 36 |
-
"eval_loss": 3.9380106925964355,
|
| 37 |
-
"eval_new_wer": 1.0,
|
| 38 |
-
"eval_old_wer": 1.0,
|
| 39 |
-
"eval_runtime": 6.9825,
|
| 40 |
-
"eval_samples_per_second": 25.779,
|
| 41 |
-
"eval_steps_per_second": 3.294,
|
| 42 |
-
"step": 1340
|
| 43 |
-
},
|
| 44 |
-
{
|
| 45 |
-
"epoch": 3.0,
|
| 46 |
-
"learning_rate": 8.428990364474236e-05,
|
| 47 |
-
"loss": 3.4075,
|
| 48 |
-
"step": 2010
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 3.0,
|
| 52 |
-
"eval_cer": 1.0,
|
| 53 |
-
"eval_loss": 3.9024274349212646,
|
| 54 |
-
"eval_new_wer": 1.0,
|
| 55 |
-
"eval_old_wer": 1.0,
|
| 56 |
-
"eval_runtime": 7.1179,
|
| 57 |
-
"eval_samples_per_second": 25.288,
|
| 58 |
-
"eval_steps_per_second": 3.231,
|
| 59 |
-
"step": 2010
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 4.0,
|
| 63 |
-
"learning_rate": 7.727272727272727e-05,
|
| 64 |
-
"loss": 3.3579,
|
| 65 |
-
"step": 2680
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 4.0,
|
| 69 |
-
"eval_cer": 1.0,
|
| 70 |
-
"eval_loss": 3.84831166267395,
|
| 71 |
-
"eval_new_wer": 1.0,
|
| 72 |
-
"eval_old_wer": 1.0,
|
| 73 |
-
"eval_runtime": 7.0506,
|
| 74 |
-
"eval_samples_per_second": 25.53,
|
| 75 |
-
"eval_steps_per_second": 3.262,
|
| 76 |
-
"step": 2680
|
| 77 |
-
},
|
| 78 |
-
{
|
| 79 |
-
"epoch": 5.0,
|
| 80 |
-
"learning_rate": 7.02555509007122e-05,
|
| 81 |
-
"loss": 3.322,
|
| 82 |
-
"step": 3350
|
| 83 |
-
},
|
| 84 |
-
{
|
| 85 |
-
"epoch": 5.0,
|
| 86 |
-
"eval_cer": 1.0,
|
| 87 |
-
"eval_loss": 3.8365871906280518,
|
| 88 |
-
"eval_new_wer": 1.0,
|
| 89 |
-
"eval_old_wer": 1.0,
|
| 90 |
-
"eval_runtime": 7.7477,
|
| 91 |
-
"eval_samples_per_second": 23.233,
|
| 92 |
-
"eval_steps_per_second": 2.969,
|
| 93 |
-
"step": 3350
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 6.0,
|
| 97 |
-
"learning_rate": 6.323837452869711e-05,
|
| 98 |
-
"loss": 3.2953,
|
| 99 |
-
"step": 4020
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 6.0,
|
| 103 |
-
"eval_cer": 1.0,
|
| 104 |
-
"eval_loss": 3.838519334793091,
|
| 105 |
-
"eval_new_wer": 1.0,
|
| 106 |
-
"eval_old_wer": 1.0,
|
| 107 |
-
"eval_runtime": 8.1306,
|
| 108 |
-
"eval_samples_per_second": 22.139,
|
| 109 |
-
"eval_steps_per_second": 2.829,
|
| 110 |
-
"step": 4020
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 7.0,
|
| 114 |
-
"learning_rate": 5.622119815668203e-05,
|
| 115 |
-
"loss": 3.2672,
|
| 116 |
-
"step": 4690
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 7.0,
|
| 120 |
-
"eval_cer": 1.0,
|
| 121 |
-
"eval_loss": 3.821115016937256,
|
| 122 |
-
"eval_new_wer": 1.0,
|
| 123 |
-
"eval_old_wer": 1.0,
|
| 124 |
-
"eval_runtime": 7.1147,
|
| 125 |
-
"eval_samples_per_second": 25.3,
|
| 126 |
-
"eval_steps_per_second": 3.233,
|
| 127 |
-
"step": 4690
|
| 128 |
-
},
|
| 129 |
-
{
|
| 130 |
-
"epoch": 8.0,
|
| 131 |
-
"learning_rate": 4.920402178466695e-05,
|
| 132 |
-
"loss": 3.2428,
|
| 133 |
-
"step": 5360
|
| 134 |
-
},
|
| 135 |
-
{
|
| 136 |
-
"epoch": 8.0,
|
| 137 |
-
"eval_cer": 1.0,
|
| 138 |
-
"eval_loss": 3.810203790664673,
|
| 139 |
-
"eval_new_wer": 1.0,
|
| 140 |
-
"eval_old_wer": 1.0,
|
| 141 |
-
"eval_runtime": 8.283,
|
| 142 |
-
"eval_samples_per_second": 21.731,
|
| 143 |
-
"eval_steps_per_second": 2.777,
|
| 144 |
-
"step": 5360
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"epoch": 9.0,
|
| 148 |
-
"learning_rate": 4.2186845412651864e-05,
|
| 149 |
-
"loss": 3.219,
|
| 150 |
-
"step": 6030
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 9.0,
|
| 154 |
-
"eval_cer": 1.0,
|
| 155 |
-
"eval_loss": 3.7927558422088623,
|
| 156 |
-
"eval_new_wer": 1.0,
|
| 157 |
-
"eval_old_wer": 1.0,
|
| 158 |
-
"eval_runtime": 8.3214,
|
| 159 |
-
"eval_samples_per_second": 21.631,
|
| 160 |
-
"eval_steps_per_second": 2.764,
|
| 161 |
-
"step": 6030
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"epoch": 10.0,
|
| 165 |
-
"learning_rate": 3.516966904063678e-05,
|
| 166 |
-
"loss": 3.1953,
|
| 167 |
-
"step": 6700
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 10.0,
|
| 171 |
-
"eval_cer": 1.0,
|
| 172 |
-
"eval_loss": 3.765852212905884,
|
| 173 |
-
"eval_new_wer": 1.0,
|
| 174 |
-
"eval_old_wer": 1.0,
|
| 175 |
-
"eval_runtime": 7.1004,
|
| 176 |
-
"eval_samples_per_second": 25.351,
|
| 177 |
-
"eval_steps_per_second": 3.239,
|
| 178 |
-
"step": 6700
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 11.0,
|
| 182 |
-
"learning_rate": 2.8152492668621706e-05,
|
| 183 |
-
"loss": 3.1763,
|
| 184 |
-
"step": 7370
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 11.0,
|
| 188 |
-
"eval_cer": 1.0,
|
| 189 |
-
"eval_loss": 3.7410292625427246,
|
| 190 |
-
"eval_new_wer": 1.0,
|
| 191 |
-
"eval_old_wer": 1.0,
|
| 192 |
-
"eval_runtime": 7.0826,
|
| 193 |
-
"eval_samples_per_second": 25.414,
|
| 194 |
-
"eval_steps_per_second": 3.247,
|
| 195 |
-
"step": 7370
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 12.0,
|
| 199 |
-
"learning_rate": 2.113531629660662e-05,
|
| 200 |
-
"loss": 3.1599,
|
| 201 |
-
"step": 8040
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 12.0,
|
| 205 |
-
"eval_cer": 1.0,
|
| 206 |
-
"eval_loss": 3.718080759048462,
|
| 207 |
-
"eval_new_wer": 1.0,
|
| 208 |
-
"eval_old_wer": 1.0,
|
| 209 |
-
"eval_runtime": 7.1262,
|
| 210 |
-
"eval_samples_per_second": 25.259,
|
| 211 |
-
"eval_steps_per_second": 3.228,
|
| 212 |
-
"step": 8040
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 13.0,
|
| 216 |
-
"learning_rate": 1.4118139924591539e-05,
|
| 217 |
-
"loss": 3.1486,
|
| 218 |
-
"step": 8710
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 13.0,
|
| 222 |
-
"eval_cer": 1.0,
|
| 223 |
-
"eval_loss": 3.698702096939087,
|
| 224 |
-
"eval_new_wer": 1.0,
|
| 225 |
-
"eval_old_wer": 1.0,
|
| 226 |
-
"eval_runtime": 7.1837,
|
| 227 |
-
"eval_samples_per_second": 25.057,
|
| 228 |
-
"eval_steps_per_second": 3.202,
|
| 229 |
-
"step": 8710
|
| 230 |
-
},
|
| 231 |
-
{
|
| 232 |
-
"epoch": 14.0,
|
| 233 |
-
"learning_rate": 7.100963552576456e-06,
|
| 234 |
-
"loss": 3.1406,
|
| 235 |
-
"step": 9380
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 14.0,
|
| 239 |
-
"eval_cer": 1.0,
|
| 240 |
-
"eval_loss": 3.6906392574310303,
|
| 241 |
-
"eval_new_wer": 1.0,
|
| 242 |
-
"eval_old_wer": 1.0,
|
| 243 |
-
"eval_runtime": 6.667,
|
| 244 |
-
"eval_samples_per_second": 26.999,
|
| 245 |
-
"eval_steps_per_second": 3.45,
|
| 246 |
-
"step": 9380
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 15.0,
|
| 250 |
-
"learning_rate": 8.378718056137412e-08,
|
| 251 |
-
"loss": 3.1362,
|
| 252 |
-
"step": 10050
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"epoch": 15.0,
|
| 256 |
-
"eval_cer": 1.0,
|
| 257 |
-
"eval_loss": 3.688339948654175,
|
| 258 |
-
"eval_new_wer": 1.0,
|
| 259 |
-
"eval_old_wer": 1.0,
|
| 260 |
-
"eval_runtime": 6.6264,
|
| 261 |
-
"eval_samples_per_second": 27.164,
|
| 262 |
-
"eval_steps_per_second": 3.471,
|
| 263 |
-
"step": 10050
|
| 264 |
}
|
| 265 |
],
|
| 266 |
"max_steps": 10050,
|
| 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": 670,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
"learning_rate": 9.832425638877252e-05,
|
| 13 |
+
"loss": 16.2547,
|
| 14 |
"step": 670
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
"eval_cer": 1.0,
|
| 19 |
+
"eval_loss": 3.4289255142211914,
|
| 20 |
"eval_new_wer": 1.0,
|
| 21 |
"eval_old_wer": 1.0,
|
| 22 |
+
"eval_runtime": 6.8022,
|
| 23 |
+
"eval_samples_per_second": 26.462,
|
| 24 |
+
"eval_steps_per_second": 3.381,
|
| 25 |
"step": 670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
],
|
| 28 |
"max_steps": 10050,
|
| 29 |
"num_train_epochs": 15,
|
| 30 |
+
"total_flos": 4.9786204745604096e+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 sha256:10f57580858b49a35243099dbdd8cae4d75b5c98e2ac927e2270c781b5291665
|
| 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 sha256:78b8af0529522cbae8a484627f1931663045d8e1f9d51e2919c7c377f92e91cf
|
| 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 sha256:10f57580858b49a35243099dbdd8cae4d75b5c98e2ac927e2270c781b5291665
|
| 3 |
size 3387
|