rizkyjun commited on
Commit
0e750d5
1 Parent(s): e0ec20f

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:d05b2c2c9b2d581d92485eba6a860e07b6da956c48a009e5a6f791785845071e
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5faca0ecf1792634d74e8ec8a005b9ae0bf89a2f072966660de68e7150c52bdc
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e950a510fa6a75d273af5a873d09436db017fab6e710e9e506f6ff12b291b94
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9395f3bc4ebaccb11cc34cfdb6e223429077745e41eb2e8d28731bb9450dd2db
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:759e77ccf458a889b7b5189552587bc5a6060b4a877912775f82bf425e75e65c
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2976c6db6ebcdf9dabf12702a779e061718bd1c4ef8e49e51b66e2a5fcb97d74
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": 2.107461929321289,
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": 30.396,
372
  "eval_steps_per_second": 3.803,
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": 7.639893171800064e+16,
381
  "trial_name": null,
382
  "trial_params": null
383
  }
 
1
  {
2
+ "best_metric": 2.09187388420105,
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": 30.396,
372
  "eval_steps_per_second": 3.803,
373
  "step": 2600
374
+ },
375
+ {
376
+ "epoch": 1.97,
377
+ "learning_rate": 0.0002,
378
+ "loss": 2.0873,
379
+ "step": 2700
380
+ },
381
+ {
382
+ "epoch": 1.97,
383
+ "eval_loss": 2.09187388420105,
384
+ "eval_runtime": 206.3333,
385
+ "eval_samples_per_second": 30.407,
386
+ "eval_steps_per_second": 3.805,
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": 7.934011037632512e+16,
395
  "trial_name": null,
396
  "trial_params": null
397
  }