mprzibilla commited on
Commit
75124e9
1 Parent(s): e0fb156

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:e3223be3d310a8c1741df1146bdcc52bdd518b6ae23a80a635cb0eab2c718b53
3
  size 721661957
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05731dcf02bf708271b8d9296f9a839cb1d0bd916d78b83db53ce37744670802
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:e90576186148b38d8b52c186fcf34d51a10b1b76088ab48d340d5cfaef7cc2d9
3
  size 377646433
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35ecf21bce5465121c60085034f3adece25c96f8d9f94e3b173b51e88b41179a
3
  size 377646433
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a85199c465f085e896330d27f064bf52b62949b139d1feaa1c2b115b95a8480
3
- size 14639
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:072a32c4764567c31f6bc914df6832f68d8674c9ce0337636c98227f192de029
3
+ size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eaa0b2e7a9672ac926bfe513be5f1b7cfb095966699b7cdff6f5a8511943ff9
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58355fb8236e4b98acfdfa577ebbfaef262afab852fcea71d776120e1ca4c58d
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a876736d0c60e4ecc12ffacff7de89ea9ab4ede46a916c3bdc242123417fae6
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a51833aa1c506f86df58d311c9ea885908e851b98000a4dc076cbf03a804b8
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": 4424,
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": 28.482,
245
  "eval_steps_per_second": 3.662,
246
  "step": 4424
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
247
  }
248
  ],
249
  "max_steps": 4740,
250
  "num_train_epochs": 15,
251
- "total_flos": 3.27261455483179e+18,
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": 4740,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
244
  "eval_samples_per_second": 28.482,
245
  "eval_steps_per_second": 3.662,
246
  "step": 4424
247
+ },
248
+ {
249
+ "epoch": 15.0,
250
+ "learning_rate": 1.554519209415945e-07,
251
+ "loss": 3.3732,
252
+ "step": 4740
253
+ },
254
+ {
255
+ "epoch": 15.0,
256
+ "eval_cer": 1.0,
257
+ "eval_loss": 3.251002311706543,
258
+ "eval_new_wer": 1.0,
259
+ "eval_old_wer": 1.0,
260
+ "eval_runtime": 4.9335,
261
+ "eval_samples_per_second": 28.377,
262
+ "eval_steps_per_second": 3.649,
263
+ "step": 4740
264
  }
265
  ],
266
  "max_steps": 4740,
267
  "num_train_epochs": 15,
268
+ "total_flos": 3.506464286899876e+18,
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:e90576186148b38d8b52c186fcf34d51a10b1b76088ab48d340d5cfaef7cc2d9
3
  size 377646433
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35ecf21bce5465121c60085034f3adece25c96f8d9f94e3b173b51e88b41179a
3
  size 377646433