rizkyjun commited on
Commit
6d1c83f
1 Parent(s): b459dcd

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 sha256:3ac93ba84e679b3bfdbed1aa4a511fc2fd7668cb8d73b38aaa9593401908fe44
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:610daa3a985b7936da98214445935aaebed6843797f1f7e3690a625f2a0a9bcb
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de577d967c10e597c8c23b3751a4e00f403786cbf695cd42dc5741fe4de523ad
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e39812ebdeb08e530e4d20862010a61f4da895dddf99324907b047f1892d00c
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85a355cfb19d81e3463ec580a4d7cbcf7f7cfb13b0254e266e3297bbafa58661
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bff83aa64785e622545a98dc743e577a347f7967e41f1b5f37a5363446796c3
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": 2.1318325996398926,
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": 30.541,
372
  "eval_steps_per_second": 3.821,
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": 7.590446666901504e+16,
381
  "trial_name": null,
382
  "trial_params": null
383
  }
 
1
  {
2
+ "best_metric": 2.1178267002105713,
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": 30.541,
372
  "eval_steps_per_second": 3.821,
373
  "step": 2600
374
+ },
375
+ {
376
+ "epoch": 1.97,
377
+ "learning_rate": 0.0002,
378
+ "loss": 2.1077,
379
+ "step": 2700
380
+ },
381
+ {
382
+ "epoch": 1.97,
383
+ "eval_loss": 2.1178267002105713,
384
+ "eval_runtime": 205.6052,
385
+ "eval_samples_per_second": 30.515,
386
+ "eval_steps_per_second": 3.818,
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": 7.88266658608128e+16,
395
  "trial_name": null,
396
  "trial_params": null
397
  }