ramdhanfirdaus commited on
Commit
f612bdf
1 Parent(s): 1b2c469

Training in progress, step 3700, 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:ab272531ca4f7f21d89ada6774e8e5bc07ab11ecffda04d158c5f53998ca655d
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b8e6335c0d68d88d356b227a8f6ba37aa3844bca171402b19a7345eb3e972e
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c562f3b307809fe2836dff271710f225ad458098595e0784fc6a7f5379d7ae0b
3
  size 100691721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7739c98c4e8e23237ca1e5bca123f18d36ed1e08786c22c54e15d7c90aebf821
3
  size 100691721
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0fe9debfc0931dca2aebaaa146c3890943a5809c00b1b2ba715c1a4eb6e57da
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77cdc8420066e8409c0c17ecbd59183f0ae3319590923e66788ff982d6b2db2e
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c157d4508adfa804f177e78fb4986d5f3ffb3ec20ae255fb757aa13c0595fdb4
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.2722229957580566,
3
  "best_model_checkpoint": "./outputs/checkpoint-3500",
4
- "epoch": 2.62367941712204,
5
  "eval_steps": 100,
6
- "global_step": 3600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -511,13 +511,27 @@
511
  "eval_samples_per_second": 45.441,
512
  "eval_steps_per_second": 5.686,
513
  "step": 3600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
514
  }
515
  ],
516
  "logging_steps": 100,
517
  "max_steps": 4116,
518
  "num_train_epochs": 3,
519
  "save_steps": 100,
520
- "total_flos": 2.146160479353815e+17,
521
  "trial_name": null,
522
  "trial_params": null
523
  }
 
1
  {
2
  "best_metric": 1.2722229957580566,
3
  "best_model_checkpoint": "./outputs/checkpoint-3500",
4
+ "epoch": 2.6965391621129324,
5
  "eval_steps": 100,
6
+ "global_step": 3700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
511
  "eval_samples_per_second": 45.441,
512
  "eval_steps_per_second": 5.686,
513
  "step": 3600
514
+ },
515
+ {
516
+ "epoch": 2.7,
517
+ "learning_rate": 0.0002,
518
+ "loss": 1.2798,
519
+ "step": 3700
520
+ },
521
+ {
522
+ "epoch": 2.7,
523
+ "eval_loss": 1.3004039525985718,
524
+ "eval_runtime": 134.3049,
525
+ "eval_samples_per_second": 46.715,
526
+ "eval_steps_per_second": 5.845,
527
+ "step": 3700
528
  }
529
  ],
530
  "logging_steps": 100,
531
  "max_steps": 4116,
532
  "num_train_epochs": 3,
533
  "save_steps": 100,
534
+ "total_flos": 2.2058248691871744e+17,
535
  "trial_name": null,
536
  "trial_params": null
537
  }