smilemikan commited on
Commit
6b37c91
1 Parent(s): 04e86b1

Training in progress, step 6500, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:215003a50b8f24c7272539832a0fb14618692b2ee0b017b4e7d1318e49efe1b3
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7123ce151f884c4e93893bf99bee06f1d2dda4ac64fc1741ea269839a6978bc
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67b8d47dfc827744bf2df7d7a5f49592571325ea98986d1c3a06ba257bc4050a
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d646d528dc984236b1b4ff16f557a7c8814f94ad5aaa9c3d882c29ad688ff2dd
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0be28834dc48bfbc1da80285e00e53316bd7a8fe69a474f8af17af734e5ba2f9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3c6fc27feca48e70907ed2899d8d58bc54e4a17cae5603c99d3cc69bdf4709
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc464c2cb7393ae85c5c74058e5c9d9f714a415cb50f7138fd5f72ac09ddf910
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29bd0dc8a9e64d7351734a3b4826f2cbfcc41a081faf279afc8c4c4f2ccda886
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.0015575885772705,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-6000",
4
- "epoch": 1.3218770654329148,
5
  "eval_steps": 500,
6
- "global_step": 6000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -175,13 +175,27 @@
175
  "eval_samples_per_second": 210.083,
176
  "eval_steps_per_second": 13.145,
177
  "step": 6000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
178
  }
179
  ],
180
  "logging_steps": 500,
181
  "max_steps": 60000,
182
  "num_train_epochs": 14,
183
  "save_steps": 500,
184
- "total_flos": 6071109681807360.0,
185
  "trial_name": null,
186
  "trial_params": null
187
  }
 
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,
 
175
  "eval_samples_per_second": 210.083,
176
  "eval_steps_per_second": 13.145,
177
  "step": 6000
178
+ },
179
+ {
180
+ "epoch": 1.43,
181
+ "learning_rate": 1.7834000000000002e-05,
182
+ "loss": 2.0542,
183
+ "step": 6500
184
+ },
185
+ {
186
+ "epoch": 1.43,
187
+ "eval_loss": 1.951575517654419,
188
+ "eval_runtime": 43.3919,
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
  }