smilemikan commited on
Commit
24d7eca
1 Parent(s): 965129d

Training in progress, step 25000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab903c388a1316163f4c03985bea2aa1bccabb2de83e5d099e543d53a2a4bd24
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c94570a99927e591f1eb5e08057b3c3123d44a1f8814728baaea3ee84f5b6ee
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fcf27d360f555aee57f4cdd3f1b0117db4d32aa1f3f4cffcef63905b29447cf
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743cecc190db59d197b7bd3523638b6ffe8b31e3c57d6c260fee7a3b3695637e
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:a98fe984610d3154ad7e1626295fddc4cc07a279f045d7f058d9da9fb0fe198e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb220adbfc9e59581895a9ef03bf68d443c814d1a00e84a4181a098ece9b8ec
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5f8b99c7d953fa43770dbc516acb083b7e689c52db9836fe30479d24d71cfa1
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5808ee445f3c4e972d76ccb971d8af8148ee8818364ac4b9d603e01c02af20
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4372690916061401,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-24500",
4
- "epoch": 5.397664683851069,
5
  "eval_steps": 500,
6
- "global_step": 24500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -693,13 +693,27 @@
693
  "eval_samples_per_second": 199.916,
694
  "eval_steps_per_second": 12.508,
695
  "step": 24500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
696
  }
697
  ],
698
  "logging_steps": 500,
699
  "max_steps": 60000,
700
  "num_train_epochs": 14,
701
  "save_steps": 500,
702
- "total_flos": 2.487026805099725e+16,
703
  "trial_name": null,
704
  "trial_params": null
705
  }
 
1
  {
2
+ "best_metric": 1.4315961599349976,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-25000",
4
+ "epoch": 5.5078211059704785,
5
  "eval_steps": 500,
6
+ "global_step": 25000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
693
  "eval_samples_per_second": 199.916,
694
  "eval_steps_per_second": 12.508,
695
  "step": 24500
696
+ },
697
+ {
698
+ "epoch": 5.51,
699
+ "learning_rate": 1.1669666666666668e-05,
700
+ "loss": 1.3446,
701
+ "step": 25000
702
+ },
703
+ {
704
+ "epoch": 5.51,
705
+ "eval_loss": 1.4315961599349976,
706
+ "eval_runtime": 44.7878,
707
+ "eval_samples_per_second": 202.689,
708
+ "eval_steps_per_second": 12.682,
709
+ "step": 25000
710
  }
711
  ],
712
  "logging_steps": 500,
713
  "max_steps": 60000,
714
  "num_train_epochs": 14,
715
  "save_steps": 500,
716
+ "total_flos": 2.536917616361472e+16,
717
  "trial_name": null,
718
  "trial_params": null
719
  }