smilemikan commited on
Commit
06996e7
1 Parent(s): 073d7a5

Training in progress, step 19000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee8d14031344632f9a83d65cbeb334fd222e2206788562f1d0ef7f92f6755dc5
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc21bed1c700b79476606b59f65fc788138afd3e144dff9329c0e23cf11dcda8
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c9b66246e212762c9bce54efe452a5660f3a27fc5f3db25a15258d1b546cd7e
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31eef198c1918646399f9d583cf4bdab87e302c875d9ea290a6f53bfe1fecc17
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:b3a5307f1b9f3a753ffca16a6487033857c954277ede0e43f06c48d6e6e506a1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a715ef9c9e3c6137bc6be27929047572c9fb2ebbb8ad488e351de8f9f9aa02fc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54e83d3d1c149aaff4f610278a355ef4e3e24cd2d1673a5e4041c0a10c815d4e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:105d68c0e33227a0278f5a19a90a0dcc1f849a0194111ea604489d62cfced2f5
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.519882082939148,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-18500",
4
- "epoch": 4.075787618418154,
5
  "eval_steps": 500,
6
- "global_step": 18500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -525,13 +525,27 @@
525
  "eval_samples_per_second": 207.132,
526
  "eval_steps_per_second": 12.96,
527
  "step": 18500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
528
  }
529
  ],
530
  "logging_steps": 500,
531
  "max_steps": 60000,
532
  "num_train_epochs": 14,
533
  "save_steps": 500,
534
- "total_flos": 1.8773830334152704e+16,
535
  "trial_name": null,
536
  "trial_params": null
537
  }
 
1
  {
2
+ "best_metric": 1.5142260789871216,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-19000",
4
+ "epoch": 4.185944040537564,
5
  "eval_steps": 500,
6
+ "global_step": 19000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
525
  "eval_samples_per_second": 207.132,
526
  "eval_steps_per_second": 12.96,
527
  "step": 18500
528
+ },
529
+ {
530
+ "epoch": 4.19,
531
+ "learning_rate": 1.3669e-05,
532
+ "loss": 1.4613,
533
+ "step": 19000
534
+ },
535
+ {
536
+ "epoch": 4.19,
537
+ "eval_loss": 1.5142260789871216,
538
+ "eval_runtime": 43.3978,
539
+ "eval_samples_per_second": 209.181,
540
+ "eval_steps_per_second": 13.088,
541
+ "step": 19000
542
  }
543
  ],
544
  "logging_steps": 500,
545
  "max_steps": 60000,
546
  "num_train_epochs": 14,
547
  "save_steps": 500,
548
+ "total_flos": 1.927822393029427e+16,
549
  "trial_name": null,
550
  "trial_params": null
551
  }