smilemikan commited on
Commit
5051d46
1 Parent(s): e195baf

Training in progress, step 21500, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0532922c0755883c1f75431e58cd197c55e739151b005def28c2978caefe0b99
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ecdef4b08c8be4aabf1d5e802e412b177f576c78f2bc807daed1c549d77ce7e
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bf8d8456febe4ee85e1c4ec003a2db58283eafbfe284d5446916b79f3e7a0ac
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab742e625ede0ba602e22a91599f53d5624d655343052fe4ad2585b6c785d95
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f600d0753ed00fe58785f22863b5c8f5c8aab579af93a924b04ef738081a16d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90fe8cae02e4cf366692222fde80c5819cf644e79de818fc5796fceea713547
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7633c094444bb7e56a9f9b4293e2cee3115c6d985113b21c584ad616baf8d5ca
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eec213109d2daa8671c1da04dc5024b2510fc7dc64fc83cd79f362f99f63e0f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4811300039291382,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-21000",
4
- "epoch": 4.626569729015202,
5
  "eval_steps": 500,
6
- "global_step": 21000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -595,13 +595,27 @@
595
  "eval_samples_per_second": 210.038,
596
  "eval_steps_per_second": 13.142,
597
  "step": 21000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
598
  }
599
  ],
600
  "logging_steps": 500,
601
  "max_steps": 60000,
602
  "num_train_epochs": 14,
603
  "save_steps": 500,
604
- "total_flos": 2.130825916632269e+16,
605
  "trial_name": null,
606
  "trial_params": null
607
  }
 
1
  {
2
+ "best_metric": 1.4702121019363403,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-21500",
4
+ "epoch": 4.7367261511346115,
5
  "eval_steps": 500,
6
+ "global_step": 21500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
595
  "eval_samples_per_second": 210.038,
596
  "eval_steps_per_second": 13.142,
597
  "step": 21000
598
+ },
599
+ {
600
+ "epoch": 4.74,
601
+ "learning_rate": 1.2836000000000002e-05,
602
+ "loss": 1.4527,
603
+ "step": 21500
604
+ },
605
+ {
606
+ "epoch": 4.74,
607
+ "eval_loss": 1.4702121019363403,
608
+ "eval_runtime": 43.7967,
609
+ "eval_samples_per_second": 207.276,
610
+ "eval_steps_per_second": 12.969,
611
+ "step": 21500
612
  }
613
  ],
614
  "logging_steps": 500,
615
  "max_steps": 60000,
616
  "num_train_epochs": 14,
617
  "save_steps": 500,
618
+ "total_flos": 2.182480886484173e+16,
619
  "trial_name": null,
620
  "trial_params": null
621
  }