Vipplav commited on
Commit
1bf8012
·
verified ·
1 Parent(s): 39c9435

Training in progress, step 809, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72477bdfa8af67221f7d01002bbc156d50ef30b1de2de21dc531ab3def9e1785
3
  size 4517152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee550e241b26253de2eaac37cd87d3a493c8f75f988744bdfdbaf4b4b197e15
3
  size 4517152
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbb535d6b4d4cab97584221468627230eaa5e390096cbfba38dbcc77969f61be
3
  size 9085370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba83d8075b1ee805473c93f8746effde882dc5182fc5a77b2d3379b347ab9b67
3
  size 9085370
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:235c9e9ddad0793006a4e184928cbbc1ef2c10a724f7ea2ed9159889a224424b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ac97d6f00846fdcd28d139829a1d784181281e632bae0c6a92793fbc027010
3
  size 14244
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52d9c053f828b4b4e7b8b5f67be783f74a1110e2609dcc7af7743fb825eb323c
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b28da5145db930610bdae810afea51d5154f273fcc4031902013045bc502f98a
3
  size 988
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2449f226ad43587a7b6284ca578c5122a86d46998334ad1787cb741cb9547ccd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b2e604a059385e85c26e76c9fb05502e048cb16442aba870dc39c0a540e028
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.9888751545117429,
6
  "eval_steps": 500,
7
- "global_step": 800,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -204,12 +204,12 @@
204
  "should_evaluate": false,
205
  "should_log": false,
206
  "should_save": true,
207
- "should_training_stop": false
208
  },
209
  "attributes": {}
210
  }
211
  },
212
- "total_flos": 1.01807435022336e+16,
213
  "train_batch_size": 1,
214
  "trial_name": null,
215
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
  "eval_steps": 500,
7
+ "global_step": 809,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
204
  "should_evaluate": false,
205
  "should_log": false,
206
  "should_save": true,
207
+ "should_training_stop": true
208
  },
209
  "attributes": {}
210
  }
211
  },
212
+ "total_flos": 1.0295276866633728e+16,
213
  "train_batch_size": 1,
214
  "trial_name": null,
215
  "trial_params": null