smilemikan commited on
Commit
04ab968
1 Parent(s): a89c397

Training in progress, step 28000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2d62619775d43d2cf93a194a2a910892f3f39b1242bb6dd667e55c7fb3ce154
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e656d6d29e5bdf4184675628e325ee8bf61b1421375059bb8a61ac1fe851baa
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e95017e5a4ad86b5ff0851a391da824ab31a84d84f421619c20317622e372cc
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74329bbfdf4b3c0badecf4ec527037112c259541577b466c1c5dfb5166ef80ef
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f0dac653bfe2c7aee298f646a77251b127b2e2f957796f6b24e4bc4d9bfd5a0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2723958486f3c31644c2e93836f066ed3efc20b43c147cbdcfa43e5d91d46d82
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53253dd0116d956eefc0d21d01703cac3649246a63f7114fac3cf4f5a9c9cf97
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba7fc5c0b02e717e9f7e8532434753e0f189a8ecfaf34de78f9861ef1481f15
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4157874584197998,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-27500",
4
- "epoch": 6.058603216567526,
5
  "eval_steps": 500,
6
- "global_step": 27500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -777,13 +777,27 @@
777
  "eval_samples_per_second": 204.927,
778
  "eval_steps_per_second": 12.822,
779
  "step": 27500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
780
  }
781
  ],
782
  "logging_steps": 500,
783
  "max_steps": 60000,
784
  "num_train_epochs": 14,
785
  "save_steps": 500,
786
- "total_flos": 2.789669734986547e+16,
787
  "trial_name": null,
788
  "trial_params": null
789
  }
 
1
  {
2
+ "best_metric": 1.4157196283340454,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-28000",
4
+ "epoch": 6.168759638686936,
5
  "eval_steps": 500,
6
+ "global_step": 28000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
777
  "eval_samples_per_second": 204.927,
778
  "eval_steps_per_second": 12.822,
779
  "step": 27500
780
+ },
781
+ {
782
+ "epoch": 6.17,
783
+ "learning_rate": 1.0669666666666667e-05,
784
+ "loss": 1.2813,
785
+ "step": 28000
786
+ },
787
+ {
788
+ "epoch": 6.17,
789
+ "eval_loss": 1.4157196283340454,
790
+ "eval_runtime": 44.6759,
791
+ "eval_samples_per_second": 203.197,
792
+ "eval_steps_per_second": 12.714,
793
+ "step": 28000
794
  }
795
  ],
796
  "logging_steps": 500,
797
  "max_steps": 60000,
798
  "num_train_epochs": 14,
799
  "save_steps": 500,
800
+ "total_flos": 2.840078619692237e+16,
801
  "trial_name": null,
802
  "trial_params": null
803
  }