smilemikan commited on
Commit
a24159c
1 Parent(s): 50ac602

Training in progress, step 13000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78d6f18043997ba6c5f72b35d08e7d9d57cff6dfa6353fa46313d842ab92f74b
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91972e5f12688430b4fe3bfec4b305061d5cb51ce217fb7902693b5fa93928d2
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:c0edd5c4bcf31ae78ac35f08ba69a78253a15627cb942b130989c2f3625a36c7
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:490c945987a04643240b2d876bef97ca10f5cc366efd76136ace44c51851eaf7
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ca1555f29260587b9e25d9a2345c989e19c723ac7e9da97a1c81769d1a479f0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23d7fb9e6812e16763acc588968f05e2bd6c5ffb6e8ce2effff1ee35d82978c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e18a5aa14a087ff69df53418c23cd916d7aa2a72db184ecee6ea1072f8f7dde
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0eebf581e457262291a896dc3f9f0155336ae90363aeb110525eb279a220028
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.6570212841033936,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-12500",
4
- "epoch": 2.7539105529852392,
5
  "eval_steps": 500,
6
- "global_step": 12500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -357,13 +357,27 @@
357
  "eval_samples_per_second": 212.765,
358
  "eval_steps_per_second": 13.312,
359
  "step": 12500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
360
  }
361
  ],
362
  "logging_steps": 500,
363
  "max_steps": 60000,
364
  "num_train_epochs": 14,
365
  "save_steps": 500,
366
- "total_flos": 1.269127563116544e+16,
367
  "trial_name": null,
368
  "trial_params": null
369
  }
 
1
  {
2
+ "best_metric": 1.6376469135284424,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-13000",
4
+ "epoch": 2.864066975104649,
5
  "eval_steps": 500,
6
+ "global_step": 13000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
357
  "eval_samples_per_second": 212.765,
358
  "eval_steps_per_second": 13.312,
359
  "step": 12500
360
+ },
361
+ {
362
+ "epoch": 2.86,
363
+ "learning_rate": 1.5668333333333334e-05,
364
+ "loss": 1.6725,
365
+ "step": 13000
366
+ },
367
+ {
368
+ "epoch": 2.86,
369
+ "eval_loss": 1.6376469135284424,
370
+ "eval_runtime": 43.1686,
371
+ "eval_samples_per_second": 210.292,
372
+ "eval_steps_per_second": 13.158,
373
+ "step": 13000
374
  }
375
  ],
376
  "logging_steps": 500,
377
  "max_steps": 60000,
378
  "num_train_epochs": 14,
379
  "save_steps": 500,
380
+ "total_flos": 1.3207012665458688e+16,
381
  "trial_name": null,
382
  "trial_params": null
383
  }