smilemikan commited on
Commit
915a58b
1 Parent(s): 0a2942b

Training in progress, step 9000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f94e35755520a0f7e5cb3e04c51948616dd93f8faed15240eae4cd76ff5701a
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c17a3a57a42ea6c3790c0dcbc5ca3a9a77e87c1e0aa37aa1b9bfaa1b250e2fa
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22bc33c1b08185780070fb9de3c0e3544d6f1e9ea83ecbe2c1adc475a6cf633b
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d95f9e412accbc64ef62488cbad02d94a5fbff9a89cfea493c7cf65f045d24
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:a131a175c5566e57b28eaa6e2f8992dce40add13d847e57f6cdc32ef74ccde8a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf7a26ed57eadd5fd2099b52ca0397444407c48580e0dfd1b2c12d77136d9a94
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87aa9497739f6faf83c415d8ea20f74ba8b21a289f3e19579e4ca76487913fba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:accc886422ed384d8c8af951e950f1506eb317e41c5d3afc2702aa946a8ee0c0
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.8124595880508423,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-8500",
4
- "epoch": 1.8726591760299627,
5
  "eval_steps": 500,
6
- "global_step": 8500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -245,13 +245,27 @@
245
  "eval_samples_per_second": 208.398,
246
  "eval_steps_per_second": 13.039,
247
  "step": 8500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
248
  }
249
  ],
250
  "logging_steps": 500,
251
  "max_steps": 60000,
252
  "num_train_epochs": 14,
253
  "save_steps": 500,
254
- "total_flos": 8633541568757760.0,
255
  "trial_name": null,
256
  "trial_params": null
257
  }
 
1
  {
2
+ "best_metric": 1.7888203859329224,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-9000",
4
+ "epoch": 1.9828155981493722,
5
  "eval_steps": 500,
6
+ "global_step": 9000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
245
  "eval_samples_per_second": 208.398,
246
  "eval_steps_per_second": 13.039,
247
  "step": 8500
248
+ },
249
+ {
250
+ "epoch": 1.98,
251
+ "learning_rate": 1.7000666666666668e-05,
252
+ "loss": 1.905,
253
+ "step": 9000
254
+ },
255
+ {
256
+ "epoch": 1.98,
257
+ "eval_loss": 1.7888203859329224,
258
+ "eval_runtime": 43.4924,
259
+ "eval_samples_per_second": 208.726,
260
+ "eval_steps_per_second": 13.06,
261
+ "step": 9000
262
  }
263
  ],
264
  "logging_steps": 500,
265
  "max_steps": 60000,
266
  "num_train_epochs": 14,
267
  "save_steps": 500,
268
+ "total_flos": 9132144932290560.0,
269
  "trial_name": null,
270
  "trial_params": null
271
  }