mprzibilla commited on
Commit
d067aa2
·
1 Parent(s): 09f9715

Training in progress, epoch 15

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2a9adee80e71f329153d2e2b36e7bd92713d8ca9ce2fa7459d72c34a03cea48
3
  size 721655813
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:005b6c3099026bf21fa1d78c9246fc0ab3e59d549d07c5a438d34cebd133811c
3
  size 721655813
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c229719dbf2cb1e3d56234c9d6cce57f9557abe9bdf90a217df858e70c3a070
3
  size 377643361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8bcb5d74d01bb72c789799659e2848b7b9190bb23873735ebf11c0684e38ce0
3
  size 377643361
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23636d31f34ac254710e90fb944afe8f5c27b27188f8d4e0ef8eab0e0493ed61
3
- size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b83ca423dacd383a44a041301745c46c9cfa08886b3204be3101e0ac1ed1244
3
+ size 14639
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b046a9f2f70421c41f3873e2d2d7b69a42581739ba801b92a0f61bcc7a2d48a9
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88c5548bd11701f2107afb4d65aebfaa25d403017b27107a7f18301e99530576
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e49b639dc5c693aec83dfc3b17d4fbf2fb06dd076583b28a7b5d3a1b897b9bd
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b18426d579c40ad8394268052d7d7972521d0b334ee1bb4ac1ddef9d209d0a3
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": 14.0,
5
- "global_step": 60452,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -244,11 +244,28 @@
244
  "eval_samples_per_second": 26.247,
245
  "eval_steps_per_second": 3.354,
246
  "step": 60452
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
247
  }
248
  ],
249
  "max_steps": 64770,
250
  "num_train_epochs": 15,
251
- "total_flos": 4.579562425547309e+19,
252
  "trial_name": null,
253
  "trial_params": null
254
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 15.0,
5
+ "global_step": 64770,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
244
  "eval_samples_per_second": 26.247,
245
  "eval_steps_per_second": 3.354,
246
  "step": 60452
247
+ },
248
+ {
249
+ "epoch": 15.0,
250
+ "learning_rate": 5.2005460573360204e-08,
251
+ "loss": 0.0419,
252
+ "step": 64770
253
+ },
254
+ {
255
+ "epoch": 15.0,
256
+ "eval_cer": 0.3595959595959596,
257
+ "eval_loss": 3.1890017986297607,
258
+ "eval_new_wer": 0.2,
259
+ "eval_old_wer": 0.40555555555555556,
260
+ "eval_runtime": 6.5303,
261
+ "eval_samples_per_second": 27.564,
262
+ "eval_steps_per_second": 3.522,
263
+ "step": 64770
264
  }
265
  ],
266
  "max_steps": 64770,
267
  "num_train_epochs": 15,
268
+ "total_flos": 4.90668177381194e+19,
269
  "trial_name": null,
270
  "trial_params": null
271
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c229719dbf2cb1e3d56234c9d6cce57f9557abe9bdf90a217df858e70c3a070
3
  size 377643361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8bcb5d74d01bb72c789799659e2848b7b9190bb23873735ebf11c0684e38ce0
3
  size 377643361