smilemikan commited on
Commit
45bfc2f
1 Parent(s): 43aad90

Training in progress, step 7500, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e959a330387240449b901e75b7a6ef16cb9f4f82dcec7e5593171a88a581e3d9
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f0f789a8a65f555cbac381aabdb698cee92b2fe07ebc108095baa2a90d444ef
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:c5b51291055568ca0febca3bbd78eb4ba544c0d5a1c63087b6ef5329eb2462aa
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d1c12de2fbb75ae05e3ff6b9fa7b781b5f9f5474ae72073b04c32c555e4508
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4eccb98e0738ec57bdf016a712a8236a396301af4e872c0ecf399c886888ade2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51c21aaa67f2aaaaed026273975ece0dc213e3ca36aa91a26d2b9fb91e6ab6af
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e4ce9a72830b8f6052e51c381c235c56a972c690a0fe102234b59057ffc4a68
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0f66a037624002af5608b72e074eb3a270272f3e059f861a92a97c993094e9
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
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,
@@ -203,13 +203,27 @@
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
  }
 
1
  {
2
+ "best_metric": 1.8790709972381592,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-7500",
4
+ "epoch": 1.6523463317911435,
5
  "eval_steps": 500,
6
+ "global_step": 7500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
203
  "eval_samples_per_second": 207.759,
204
  "eval_steps_per_second": 12.999,
205
  "step": 7000
206
+ },
207
+ {
208
+ "epoch": 1.65,
209
+ "learning_rate": 1.7500666666666667e-05,
210
+ "loss": 1.9926,
211
+ "step": 7500
212
+ },
213
+ {
214
+ "epoch": 1.65,
215
+ "eval_loss": 1.8790709972381592,
216
+ "eval_runtime": 44.1328,
217
+ "eval_samples_per_second": 205.698,
218
+ "eval_steps_per_second": 12.87,
219
+ "step": 7500
220
  }
221
  ],
222
  "logging_steps": 500,
223
  "max_steps": 60000,
224
  "num_train_epochs": 14,
225
  "save_steps": 500,
226
+ "total_flos": 7620555611308032.0,
227
  "trial_name": null,
228
  "trial_params": null
229
  }