mgh6 commited on
Commit
25482a2
·
verified ·
1 Parent(s): 6638747

Training in progress, step 5400, 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:c18bf22da50ee7e621053083f197766e32e004389d73ee642b168a9743bd93f3
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:014fee06c40abe14189555c9ed4b025e6ee8cd4e072236a6535f45528f8d6229
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bddaa93ad22a96ad4c306a5057d1244a3c06ab340e36b9872a4b49b80cddcdbc
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd913717e7a6e4112d3543f341b7a262c1da4ae52ac1ad2834e5b246991f9026
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fa4756020fa5980ff5a63fa7658f43b2bfa6af01ca36c8e11fa1866fca196d4
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:924549db5c8fa7c6722b2717239f1aff8fd1b5bfacb8266579f90ebe96787e6a
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58b3b470bfc7be4867e68290c747de33d63c74880aa25662880b5df50a1bd0fc
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80145150a24a2d588a25fa8b47e99a841735b6543ce3ee2a1cf42f0c87555d79
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 10.598344008748633,
5
  "eval_steps": 500,
6
- "global_step": 5300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -458,6 +458,13 @@
458
  "learning_rate": 6.466666666666666e-05,
459
  "loss": 1.2471,
460
  "step": 5300
 
 
 
 
 
 
 
461
  }
462
  ],
463
  "logging_steps": 100,
@@ -477,7 +484,7 @@
477
  "attributes": {}
478
  }
479
  },
480
- "total_flos": 8.271881904270082e+18,
481
  "train_batch_size": 8,
482
  "trial_name": null,
483
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 10.798312763630683,
5
  "eval_steps": 500,
6
+ "global_step": 5400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
458
  "learning_rate": 6.466666666666666e-05,
459
  "loss": 1.2471,
460
  "step": 5300
461
+ },
462
+ {
463
+ "epoch": 10.798312763630683,
464
+ "grad_norm": 0.20083682239055634,
465
+ "learning_rate": 6.400000000000001e-05,
466
+ "loss": 1.2461,
467
+ "step": 5400
468
  }
469
  ],
470
  "logging_steps": 100,
 
484
  "attributes": {}
485
  }
486
  },
487
+ "total_flos": 8.427956875458249e+18,
488
  "train_batch_size": 8,
489
  "trial_name": null,
490
  "trial_params": null