smilemikan commited on
Commit
cbcbebe
1 Parent(s): f485b74

Training in progress, step 18000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b769b963079720399bddcf8f6713eb4f0ccae41546917240896f767e067fd97
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1535202f47ea8847be7177abc3b113de060034c4d967d0a1efac4c2724c2068
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86411b0eb06b2a940a0ba6fd89a46289fa982e96af14690b8a45cfae4fe0ebbd
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2567983426d814eb583e058844d7c3c949c458d3e2ba5ab187de22f62974f1d
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:ce02e0f280ae812f660d3304d512201620a85f7cf68fde2ecd2498750093e2d3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9ff9a0beb47a5c694497e062f42a55477bbdb638a8059fee9b186d6bcf6111c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ef6353bbbc8c448898893d32d6996e6a0eb823f2ea7b5f853d375c80881815f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9383bd703f2e2b314358fbcfff4794afb50f09dbec39a256e4e3fe424b7952e7
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5335613489151,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-17500",
4
- "epoch": 3.855474774179335,
5
  "eval_steps": 500,
6
- "global_step": 17500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -497,13 +497,27 @@
497
  "eval_samples_per_second": 208.632,
498
  "eval_steps_per_second": 13.054,
499
  "step": 17500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500
  }
501
  ],
502
  "logging_steps": 500,
503
  "max_steps": 60000,
504
  "num_train_epochs": 14,
505
  "save_steps": 500,
506
- "total_flos": 1.7759219048251392e+16,
507
  "trial_name": null,
508
  "trial_params": null
509
  }
 
1
  {
2
+ "best_metric": 1.5262504816055298,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-18000",
4
+ "epoch": 3.965631196298744,
5
  "eval_steps": 500,
6
+ "global_step": 18000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
497
  "eval_samples_per_second": 208.632,
498
  "eval_steps_per_second": 13.054,
499
  "step": 17500
500
+ },
501
+ {
502
+ "epoch": 3.97,
503
+ "learning_rate": 1.4002333333333335e-05,
504
+ "loss": 1.4781,
505
+ "step": 18000
506
+ },
507
+ {
508
+ "epoch": 3.97,
509
+ "eval_loss": 1.5262504816055298,
510
+ "eval_runtime": 43.3365,
511
+ "eval_samples_per_second": 209.477,
512
+ "eval_steps_per_second": 13.107,
513
+ "step": 18000
514
  }
515
  ],
516
  "logging_steps": 500,
517
  "max_steps": 60000,
518
  "num_train_epochs": 14,
519
  "save_steps": 500,
520
+ "total_flos": 1.827475291648819e+16,
521
  "trial_name": null,
522
  "trial_params": null
523
  }