smilemikan commited on
Commit
bf25c0f
1 Parent(s): d5872c3

Training in progress, step 15500, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13f502610765760c71e5be2e0b43b8dfe8cc57432b9072880225fddcf95f7dce
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229b79b125af81157351b5318d62faf0eb15b805a09db589e39ae185e0f0ad42
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55963ff3e7e0bca12ac6d6c828e71a10022405570e5a1dd33db79266027dd5b0
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb9881801ddfd8054ae89cd0a09e8e5ee4300cba94297f025422fc3095cb0bd
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:e381eb5ebcc867e0006a1ab5831912b4647fea2cc08d257842200c6775cd2e76
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72356675d3f419dada7f7dbaae6c8479256c6e40b2e511e65a55f2eb71383ab7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75a3ec8031b045404b46a0b2666afbb22f5591e8385676b87697112be97ac0ac
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7dccfec89c23b95f2b98f5afccd44cf89a3b9cf8c8f6861beb6cbebdd36768
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5842323303222656,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-15000",
4
- "epoch": 3.304692663582287,
5
  "eval_steps": 500,
6
- "global_step": 15000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -427,13 +427,27 @@
427
  "eval_samples_per_second": 208.271,
428
  "eval_steps_per_second": 13.031,
429
  "step": 15000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
430
  }
431
  ],
432
  "logging_steps": 500,
433
  "max_steps": 60000,
434
  "num_train_epochs": 14,
435
  "save_steps": 500,
436
- "total_flos": 1.5212667974713344e+16,
437
  "trial_name": null,
438
  "trial_params": null
439
  }
 
1
  {
2
+ "best_metric": 1.5732085704803467,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-15500",
4
+ "epoch": 3.4148490857016967,
5
  "eval_steps": 500,
6
+ "global_step": 15500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
427
  "eval_samples_per_second": 208.271,
428
  "eval_steps_per_second": 13.031,
429
  "step": 15000
430
+ },
431
+ {
432
+ "epoch": 3.41,
433
+ "learning_rate": 1.4835000000000001e-05,
434
+ "loss": 1.6031,
435
+ "step": 15500
436
+ },
437
+ {
438
+ "epoch": 3.41,
439
+ "eval_loss": 1.5732085704803467,
440
+ "eval_runtime": 42.6594,
441
+ "eval_samples_per_second": 212.802,
442
+ "eval_steps_per_second": 13.315,
443
+ "step": 15500
444
  }
445
  ],
446
  "logging_steps": 500,
447
  "max_steps": 60000,
448
  "num_train_epochs": 14,
449
  "save_steps": 500,
450
+ "total_flos": 1.5723088830529536e+16,
451
  "trial_name": null,
452
  "trial_params": null
453
  }