ramdhanfirdaus commited on
Commit
1337de4
1 Parent(s): a34f0a2

Training in progress, step 3300, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510639ec914275029ce699b8f395cc1a6104b0efcbf3b0fa6c29af9eeec05cd7
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81cfca91f074eb3fd1a57ab735cb0951f904b2c1043953b0e78d5f22cdb3b15f
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb7ac333324ae4365bb9df7cc6216cbba49db9a5c9da60f712ec88bdc7d18afe
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca8a2716b512f448331946e4957a577a98bed9ca38b351798cd39e434f40157
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d230beeb15f5cac449e9697519a96908c6060afb660e731e7a80310a803abc98
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6fbad0ea34eece1c92d74863d52656aa2afa741f5a63409595d0576b937447
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b29cdb3cbf6e4e08e2f27c0eb794c687591cebafa7e8eb23b1335d0cbe8631d
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9256a803964ffb87bb8f27450ef4542ffa862650dea6451971cd3526e89c291
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.414027214050293,
3
- "best_model_checkpoint": "./outputs/checkpoint-3200",
4
- "epoch": 2.3315118397085612,
5
  "eval_steps": 100,
6
- "global_step": 3200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -455,13 +455,27 @@
455
  "eval_samples_per_second": 43.716,
456
  "eval_steps_per_second": 5.47,
457
  "step": 3200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
458
  }
459
  ],
460
  "logging_steps": 100,
461
  "max_steps": 4116,
462
  "num_train_epochs": 3,
463
  "save_steps": 100,
464
- "total_flos": 1.9054273686596813e+17,
465
  "trial_name": null,
466
  "trial_params": null
467
  }
 
1
  {
2
+ "best_metric": 1.4006284475326538,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3300",
4
+ "epoch": 2.4043715846994536,
5
  "eval_steps": 100,
6
+ "global_step": 3300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
455
  "eval_samples_per_second": 43.716,
456
  "eval_steps_per_second": 5.47,
457
  "step": 3200
458
+ },
459
+ {
460
+ "epoch": 2.4,
461
+ "learning_rate": 0.0002,
462
+ "loss": 1.3785,
463
+ "step": 3300
464
+ },
465
+ {
466
+ "epoch": 2.4,
467
+ "eval_loss": 1.4006284475326538,
468
+ "eval_runtime": 143.6131,
469
+ "eval_samples_per_second": 43.687,
470
+ "eval_steps_per_second": 5.466,
471
+ "step": 3300
472
  }
473
  ],
474
  "logging_steps": 100,
475
  "max_steps": 4116,
476
  "num_train_epochs": 3,
477
  "save_steps": 100,
478
+ "total_flos": 1.964956353440809e+17,
479
  "trial_name": null,
480
  "trial_params": null
481
  }