smilemikan commited on
Commit
e4fd116
1 Parent(s): 32e01ca

Training in progress, step 11000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:118c2e22c16d42dbd2776fbb076e8546e5cb7cd6bf229b723c77ab38e0385425
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d198d822b77624b94feeac70095ad213fa3c09cf180de572324cffc65981e5b
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25857705789979a95a8fff123eea7f489a0c89dcb1912dbf0abc14149ccec348
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0040b20b5bde3e1778480f8b816c8d96ff6bf5c6eba99bebd2da6b3a3ba7f26b
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:198c5817caf91e9f61134f521f55807668fe5b1347f183b2642fbb8d27142fb1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:275937e73c6556008bcc91e22217ae4b08fb4ceab31e75ca5968d9c4c19b4f59
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96b92a7a072ef7600585449bd01b526e3c8816ab7a9ab3013b79d123647e6be5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d18ccd9d69f3cfa240493af3c5aff5588d53c9acf3faa08924bf9f33265cfb3c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7204526662826538,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-10500",
4
- "epoch": 2.313284864507601,
5
  "eval_steps": 500,
6
- "global_step": 10500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -301,13 +301,27 @@
301
  "eval_samples_per_second": 206.032,
302
  "eval_steps_per_second": 12.891,
303
  "step": 10500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
304
  }
305
  ],
306
  "logging_steps": 500,
307
  "max_steps": 60000,
308
  "num_train_epochs": 14,
309
  "save_steps": 500,
310
- "total_flos": 1.0653113752879104e+16,
311
  "trial_name": null,
312
  "trial_params": null
313
  }
 
1
  {
2
+ "best_metric": 1.7068791389465332,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-11000",
4
+ "epoch": 2.4234412866270105,
5
  "eval_steps": 500,
6
+ "global_step": 11000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
301
  "eval_samples_per_second": 206.032,
302
  "eval_steps_per_second": 12.891,
303
  "step": 10500
304
+ },
305
+ {
306
+ "epoch": 2.42,
307
+ "learning_rate": 1.6334666666666668e-05,
308
+ "loss": 1.7527,
309
+ "step": 11000
310
+ },
311
+ {
312
+ "epoch": 2.42,
313
+ "eval_loss": 1.7068791389465332,
314
+ "eval_runtime": 43.4892,
315
+ "eval_samples_per_second": 208.741,
316
+ "eval_steps_per_second": 13.061,
317
+ "step": 11000
318
  }
319
  ],
320
  "logging_steps": 500,
321
  "max_steps": 60000,
322
  "num_train_epochs": 14,
323
  "save_steps": 500,
324
+ "total_flos": 1.1177383761543168e+16,
325
  "trial_name": null,
326
  "trial_params": null
327
  }