rizkyjun commited on
Commit
62b7385
1 Parent(s): 75e78ea

Training in progress, step 2700, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8db659dcfdb4644f61332a415dde38be4268e1c3417994257062fbdf42fcf4ec
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a686b25aadabfd969db63f9fcee5e8592f0678ccf2f26e1900c154517d76ce9f
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a174902e7dbc745ef9338339c92292b1b52ad451e9d55e323c576dd2a5109e3
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad9fb73ac808bcdde73c4676f90fae11a0281088c194954130c20d11da85c2fb
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5c2d63dea053348e8fd5bf01076f2a5708c04d86cae79e488be63be4a9b0c83
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:728a8ed7ae1358e13d655e3713af360a7485c55ba9e86c8d5822cb07a30b4a27
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d747a341abc7681ba1384e20b96e3fad64e2a0f72aee64e5047f8f5bba229c8f
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.201737880706787,
3
- "best_model_checkpoint": "./outputs/checkpoint-2600",
4
- "epoch": 1.8943533697632058,
5
  "eval_steps": 100,
6
- "global_step": 2600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -371,13 +371,27 @@
371
  "eval_samples_per_second": 30.59,
372
  "eval_steps_per_second": 3.827,
373
  "step": 2600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
374
  }
375
  ],
376
  "logging_steps": 100,
377
  "max_steps": 4116,
378
  "num_train_epochs": 3,
379
  "save_steps": 100,
380
- "total_flos": 7.408408364292096e+16,
381
  "trial_name": null,
382
  "trial_params": null
383
  }
 
1
  {
2
+ "best_metric": 2.185546636581421,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2700",
4
+ "epoch": 1.9672131147540983,
5
  "eval_steps": 100,
6
+ "global_step": 2700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
371
  "eval_samples_per_second": 30.59,
372
  "eval_steps_per_second": 3.827,
373
  "step": 2600
374
+ },
375
+ {
376
+ "epoch": 1.97,
377
+ "learning_rate": 0.0002,
378
+ "loss": 2.1825,
379
+ "step": 2700
380
+ },
381
+ {
382
+ "epoch": 1.97,
383
+ "eval_loss": 2.185546636581421,
384
+ "eval_runtime": 204.9463,
385
+ "eval_samples_per_second": 30.613,
386
+ "eval_steps_per_second": 3.83,
387
+ "step": 2700
388
  }
389
  ],
390
  "logging_steps": 100,
391
  "max_steps": 4116,
392
  "num_train_epochs": 3,
393
  "save_steps": 100,
394
+ "total_flos": 7.69362929814528e+16,
395
  "trial_name": null,
396
  "trial_params": null
397
  }