smilemikan commited on
Commit
4b7f024
1 Parent(s): b456b43

Training in progress, step 7000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7123ce151f884c4e93893bf99bee06f1d2dda4ac64fc1741ea269839a6978bc
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e959a330387240449b901e75b7a6ef16cb9f4f82dcec7e5593171a88a581e3d9
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:d646d528dc984236b1b4ff16f557a7c8814f94ad5aaa9c3d882c29ad688ff2dd
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b51291055568ca0febca3bbd78eb4ba544c0d5a1c63087b6ef5329eb2462aa
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:fc3c6fc27feca48e70907ed2899d8d58bc54e4a17cae5603c99d3cc69bdf4709
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eccb98e0738ec57bdf016a712a8236a396301af4e872c0ecf399c886888ade2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29bd0dc8a9e64d7351734a3b4826f2cbfcc41a081faf279afc8c4c4f2ccda886
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e4ce9a72830b8f6052e51c381c235c56a972c690a0fe102234b59057ffc4a68
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.951575517654419,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-6500",
4
- "epoch": 1.4320334875523244,
5
  "eval_steps": 500,
6
- "global_step": 6500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -189,13 +189,27 @@
189
  "eval_samples_per_second": 209.209,
190
  "eval_steps_per_second": 13.09,
191
  "step": 6500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
192
  }
193
  ],
194
  "logging_steps": 500,
195
  "max_steps": 60000,
196
  "num_train_epochs": 14,
197
  "save_steps": 500,
198
- "total_flos": 6586474244997120.0,
199
  "trial_name": null,
200
  "trial_params": null
201
  }
 
1
  {
2
+ "best_metric": 1.9161829948425293,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-7000",
4
+ "epoch": 1.542189909671734,
5
  "eval_steps": 500,
6
+ "global_step": 7000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
189
  "eval_samples_per_second": 209.209,
190
  "eval_steps_per_second": 13.09,
191
  "step": 6500
192
+ },
193
+ {
194
+ "epoch": 1.54,
195
+ "learning_rate": 1.7667333333333333e-05,
196
+ "loss": 2.0216,
197
+ "step": 7000
198
+ },
199
+ {
200
+ "epoch": 1.54,
201
+ "eval_loss": 1.9161829948425293,
202
+ "eval_runtime": 43.6948,
203
+ "eval_samples_per_second": 207.759,
204
+ "eval_steps_per_second": 12.999,
205
+ "step": 7000
206
  }
207
  ],
208
  "logging_steps": 500,
209
  "max_steps": 60000,
210
  "num_train_epochs": 14,
211
  "save_steps": 500,
212
+ "total_flos": 7097199849897984.0,
213
  "trial_name": null,
214
  "trial_params": null
215
  }