Hugging Face's logo

smilemikan
/
nllb-finetuned-jpn-to-ain-2

Text2Text Generation
Transformers
PyTorch
m2m_100
Inference Endpoints
Model card Files Community
smilemikan commited on
Commit
704df83
•
1 Parent(s): f05e831

Training in progress, step 29500, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +17 -3
  6. last-checkpoint/training_args.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aa2668846e9a33a8090234cd39de2dd4cf301d2d756547d380c8c278a06f2e2
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f88fe8b5691e16857f9954b3d534e5182ee6c597d5853439c4d6bcf4441ad5f
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:ed7faccf2d02094ad99fa5065d8df9c269984dc2f0eb60b8072bd5dc20fd021a
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db928ac8c95c578c8e77d3153bf7d2d3915d48c1e14a80adf7981f54ebf9ce72
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c02898f79565e6b2e91b1b935fbf97b8f7a90a66b89afbadcd5206758c4ffb9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:032cb2b989e166103881c6cc088d91e02e177002184215243bfe1c51aefd96d3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89ad63f4a333c21f00cebde42b984d54181b343653ad6324c844f565a0e396d1
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c040d9ffc17d73f0be34121ab32faf0f755372b9a1e93790cc6b215bf4462b8
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.403244972229004,
3
  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-29000",
4
- "epoch": 6.389072482925755,
5
  "eval_steps": 500,
6
- "global_step": 29000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -819,13 +819,27 @@
819
  "eval_samples_per_second": 203.258,
820
  "eval_steps_per_second": 12.718,
821
  "step": 29000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
822
  }
823
  ],
824
  "logging_steps": 500,
825
  "max_steps": 60000,
826
  "num_train_epochs": 14,
827
  "save_steps": 500,
828
- "total_flos": 2.941184207683584e+16,
829
  "trial_name": null,
830
  "trial_params": null
831
  }
 
1
  {
2
  "best_metric": 1.403244972229004,
3
  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-29000",
4
+ "epoch": 6.499228905045165,
5
  "eval_steps": 500,
6
+ "global_step": 29500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
819
  "eval_samples_per_second": 203.258,
820
  "eval_steps_per_second": 12.718,
821
  "step": 29000
822
+ },
823
+ {
824
+ "epoch": 6.5,
825
+ "learning_rate": 1.017e-05,
826
+ "loss": 1.2631,
827
+ "step": 29500
828
+ },
829
+ {
830
+ "epoch": 6.5,
831
+ "eval_loss": 1.4050610065460205,
832
+ "eval_runtime": 44.987,
833
+ "eval_samples_per_second": 201.792,
834
+ "eval_steps_per_second": 12.626,
835
+ "step": 29500
836
  }
837
  ],
838
  "logging_steps": 500,
839
  "max_steps": 60000,
840
  "num_train_epochs": 14,
841
  "save_steps": 500,
842
+ "total_flos": 2.991809802849485e+16,
843
  "trial_name": null,
844
  "trial_params": null
845
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e3f80fbe7aa2ced1195759a9a79a4a6a1c77c295c21fc90affe4bbb9114a987
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:327c0ad12ebaaca1e41402e71de23928bcc81d9bd807676419e50451260f49b3
3
  size 4664