rizkyjun commited on
Commit
be86897
1 Parent(s): ad64a92

Training in progress, step 4100, 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:bd24f47a1e570f5b49b7ddadb651013bc1df444373b9921ce4dbed94387dc76f
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a951a90b7232750c7d5629e6913ceddcb4cee3930522803c1373f307a8d6ea6
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c7272b486f82888654b85c752aa5c55bad128759e1ab4642ab54c4e6ec67bef
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7980ebc8e7fb584dab6b5b9260cc37c7e7956585c7078f2c2ee7e0eaeead7db9
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:fe072b43116ea6af1d9839ff9078df37c5fb13f3285b4cbe739c3c5d14228bdf
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a0d9d4b9143f23093465c736b344edb94f3988c049bd9c6571469763fcf7a30
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f55ebe991e4838deda9ff3044672335e03697b65b3fe0753cca61998e974ee51
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.9734764099121094,
3
- "best_model_checkpoint": "./outputs/checkpoint-4000",
4
- "epoch": 2.9143897996357016,
5
  "eval_steps": 100,
6
- "global_step": 4000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -567,13 +567,27 @@
567
  "eval_samples_per_second": 17.733,
568
  "eval_steps_per_second": 2.219,
569
  "step": 4000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
570
  }
571
  ],
572
  "logging_steps": 100,
573
  "max_steps": 4116,
574
  "num_train_epochs": 3,
575
  "save_steps": 100,
576
- "total_flos": 1.1744177835220992e+17,
577
  "trial_name": null,
578
  "trial_params": null
579
  }
 
1
  {
2
+ "best_metric": 1.9584715366363525,
3
+ "best_model_checkpoint": "./outputs/checkpoint-4100",
4
+ "epoch": 2.987249544626594,
5
  "eval_steps": 100,
6
+ "global_step": 4100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
567
  "eval_samples_per_second": 17.733,
568
  "eval_steps_per_second": 2.219,
569
  "step": 4000
570
+ },
571
+ {
572
+ "epoch": 2.99,
573
+ "learning_rate": 0.0002,
574
+ "loss": 1.9379,
575
+ "step": 4100
576
+ },
577
+ {
578
+ "epoch": 2.99,
579
+ "eval_loss": 1.9584715366363525,
580
+ "eval_runtime": 354.4627,
581
+ "eval_samples_per_second": 17.7,
582
+ "eval_steps_per_second": 2.215,
583
+ "step": 4100
584
  }
585
  ],
586
  "logging_steps": 100,
587
  "max_steps": 4116,
588
  "num_train_epochs": 3,
589
  "save_steps": 100,
590
+ "total_flos": 1.2037527679500288e+17,
591
  "trial_name": null,
592
  "trial_params": null
593
  }