ramdhanfirdaus commited on
Commit
4d3558b
1 Parent(s): a6e2574

Training in progress, step 2800, 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:e15f6f8a1c74ee1c50a533e91f8dc55aab33781475907e3cfd29cfe229cdc393
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ce10b52c34521da3527ec14933f59ce7da0c2f2f20e39ce7a1fd8ef8170c4a
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22a8b6522d298f5a1edc763ecc5ed68639b683c8dbf4708ab9dda9db901124e0
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e7f380efe9dbb38a6b89f237e07c5a68066845521727111f140ec60329eb35
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:852c3549f3820e15177f2fb596f07ccf8f099f9430fc2054948ec692e9be0b1a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e774b6f5f6d011a8bfc0a40be4c997cf31f87d5dc031814a84d7bd848d0c3c8
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c717fe9cf16244515cfd5ef71c3568c9f4f82b198f2a2eda00b7b6d3dadae13
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbad9b8a27781262e8d219547870cd4a5243b6b2eabc860ee48e6517ff8422dd
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4760063886642456,
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,
@@ -385,13 +385,27 @@
385
  "eval_samples_per_second": 43.701,
386
  "eval_steps_per_second": 5.468,
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": 1.6076866793843098e+17,
395
  "trial_name": null,
396
  "trial_params": null
397
  }
 
1
  {
2
+ "best_metric": 1.4635066986083984,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2800",
4
+ "epoch": 2.040072859744991,
5
  "eval_steps": 100,
6
+ "global_step": 2800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
385
  "eval_samples_per_second": 43.701,
386
  "eval_steps_per_second": 5.468,
387
  "step": 2700
388
+ },
389
+ {
390
+ "epoch": 2.04,
391
+ "learning_rate": 0.0002,
392
+ "loss": 1.4426,
393
+ "step": 2800
394
+ },
395
+ {
396
+ "epoch": 2.04,
397
+ "eval_loss": 1.4635066986083984,
398
+ "eval_runtime": 143.5367,
399
+ "eval_samples_per_second": 43.71,
400
+ "eval_steps_per_second": 5.469,
401
+ "step": 2800
402
  }
403
  ],
404
  "logging_steps": 100,
405
  "max_steps": 4116,
406
  "num_train_epochs": 3,
407
  "save_steps": 100,
408
+ "total_flos": 1.6672454855162266e+17,
409
  "trial_name": null,
410
  "trial_params": null
411
  }