Bisher commited on
Commit
f17bcec
·
verified ·
1 Parent(s): e38fbbd

Upload entire folder

Browse files
checkpoint-310/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb29a336fb7c16fa2b9f3f921b624eea6225d78b5ba860e9d3028f06e7f752e2
3
  size 28331952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ebd6a023e4e819f8bcb1f32439c2c0b9ac5ff453fa42aec35c09baed025593
3
  size 28331952
checkpoint-310/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14891de336f61125f1540145de451e9857a98fa1b3a7844094931297803a6027
3
  size 14546810
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ef1bde1651105bc61989fe80656811a1fd873e542770b305d6f8855b3b6249
3
  size 14546810
checkpoint-310/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d5421214f71b2e397f12f6cde843ec6102dc82d42aa7cfa63a3956eb6eaf835
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee937e14ac48385b79669e194350a424b1cbbe9cf80e49925248845a88d1c37f
3
  size 14244
checkpoint-310/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dda5e8457f00737922e74526b65f0677ee7b56ea9b42ef2dbdf805a0f1790a9c
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8932229084ae0fa0b69aba8b4e2ec2d82640ead843d1e7de99e829e945029440
3
  size 988
checkpoint-310/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53038fffbdc465b8750384c7d9bfe9bb6b2d3c7677f7a9ab32cd65c2b774a239
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38908d4a81924eea4798638d2d854343587e6ff5be9d889fe9cb61feb48fc6d0
3
  size 1064
checkpoint-310/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.9779179810725552,
6
  "eval_steps": 10,
7
- "global_step": 310,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -456,12 +456,12 @@
456
  "should_evaluate": false,
457
  "should_log": false,
458
  "should_save": true,
459
- "should_training_stop": false
460
  },
461
  "attributes": {}
462
  }
463
  },
464
- "total_flos": 1.4819366928384e+18,
465
  "train_batch_size": 16,
466
  "trial_name": null,
467
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
  "eval_steps": 10,
7
+ "global_step": 317,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
456
  "should_evaluate": false,
457
  "should_log": false,
458
  "should_save": true,
459
+ "should_training_stop": true
460
  },
461
  "attributes": {}
462
  }
463
  },
464
+ "total_flos": 1.51271078141952e+18,
465
  "train_batch_size": 16,
466
  "trial_name": null,
467
  "trial_params": null