smilemikan commited on
Commit
7a816f5
1 Parent(s): 0dcab72

Training in progress, step 19500, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc21bed1c700b79476606b59f65fc788138afd3e144dff9329c0e23cf11dcda8
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f38d74263534693877152baa21dc59d875f3378c0490ae05ef33eb6dc5f8642
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31eef198c1918646399f9d583cf4bdab87e302c875d9ea290a6f53bfe1fecc17
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a5b66ab356d63c0d08ccf26aeb3eb34e988153f75e8d9b4862476999dfba889
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:a715ef9c9e3c6137bc6be27929047572c9fb2ebbb8ad488e351de8f9f9aa02fc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe1c037a79f5e1ab883af9fdcdcfca89747b7f4e8b7eb549eb91d0066611ac7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:105d68c0e33227a0278f5a19a90a0dcc1f849a0194111ea604489d62cfced2f5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970ff72f9cb5a846ce88a5ea203dc3b82f596d6951a3c394abb92f4ff9fb3a2d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
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,
@@ -539,13 +539,27 @@
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
  }
 
1
  {
2
+ "best_metric": 1.503504753112793,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-19500",
4
+ "epoch": 4.296100462656973,
5
  "eval_steps": 500,
6
+ "global_step": 19500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
539
  "eval_samples_per_second": 209.181,
540
  "eval_steps_per_second": 13.088,
541
  "step": 19000
542
+ },
543
+ {
544
+ "epoch": 4.3,
545
+ "learning_rate": 1.3502333333333335e-05,
546
+ "loss": 1.452,
547
+ "step": 19500
548
+ },
549
+ {
550
+ "epoch": 4.3,
551
+ "eval_loss": 1.503504753112793,
552
+ "eval_runtime": 43.2384,
553
+ "eval_samples_per_second": 209.952,
554
+ "eval_steps_per_second": 13.136,
555
+ "step": 19500
556
  }
557
  ],
558
  "logging_steps": 500,
559
  "max_steps": 60000,
560
  "num_train_epochs": 14,
561
  "save_steps": 500,
562
+ "total_flos": 1.9783227024605184e+16,
563
  "trial_name": null,
564
  "trial_params": null
565
  }