rizkyjun commited on
Commit
d13d8a3
1 Parent(s): efe23df

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:eb42b3951c0196c952e2ae19e43a8d0bcc6bffd53742c673a50523c96c833432
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9e2aedd434829d29234e445a678e6db064213c18af1bd529b6b767497d3e19
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47c11bfba102f129aa6291146966a6f0fb152fb3d36d7f56bf6eddb8694d00cf
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2202569e505c612858af0ffd6e4166f8fb36d94f9b50767c11a6f544a5ed341c
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:fd1cdd076b217373af7247c4e5586438d32391ac0523ee9c4ea56789d6d16d28
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4990b57e009f07924326e7ab4d50989339930d6a542dfcc59f2ec6a0cb45c651
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.1339216232299805,
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": 30.558,
456
  "eval_steps_per_second": 3.823,
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": 9.113803498211328e+16,
465
  "trial_name": null,
466
  "trial_params": null
467
  }
 
1
  {
2
+ "best_metric": 2.1192281246185303,
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": 30.558,
456
  "eval_steps_per_second": 3.823,
457
  "step": 3200
458
+ },
459
+ {
460
+ "epoch": 2.4,
461
+ "learning_rate": 0.0002,
462
+ "loss": 2.0736,
463
+ "step": 3300
464
+ },
465
+ {
466
+ "epoch": 2.4,
467
+ "eval_loss": 2.1192281246185303,
468
+ "eval_runtime": 208.2692,
469
+ "eval_samples_per_second": 30.124,
470
+ "eval_steps_per_second": 3.769,
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": 9.39792070812672e+16,
479
  "trial_name": null,
480
  "trial_params": null
481
  }