adel-cybral commited on
Commit
c50ea1d
·
verified ·
1 Parent(s): ef269d6

Training in progress, step 4390, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfb65887ccaf6e8c5863bd10b22f0e05b2a592a14d27e5e7f97d0412c78e05a3
3
  size 57029756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:762566100d643c393dc9765c901427a1a7e585f80720544f1d9732e8c2f1a638
3
  size 57029756
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db337206f74e5e5b319a5aa52c2a6609a5f30d5dedd1cbb21af2882b08a8143a
3
  size 114100410
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73eb6618c19390aa57b57efc6e80aa55d60ef89276374392558a5141f6563c2a
3
  size 114100410
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f1989d61365cedf2f1c16580285a59519c5eb1a1a0ea8d68bd8b683cf13fc92
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d172399ef3366064f2426bb341e0c2875d4dcfd2615777d3613f0258a4aaa64
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a183883ee8e58295787420a0ce466b53d4ca6caf41afa2729239cfa1e74f58f6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db35652316cd18818079609bdbd22b09de59e7ca3cd85099fc0bf1dbb6d1001
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": 4.555808656036446,
5
  "eval_steps": 500,
6
- "global_step": 4000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -125,12 +125,12 @@
125
  "should_evaluate": false,
126
  "should_log": false,
127
  "should_save": true,
128
- "should_training_stop": false
129
  },
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 83333714201082.0,
134
  "train_batch_size": 16,
135
  "trial_name": null,
136
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
  "eval_steps": 500,
6
+ "global_step": 4390,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
125
  "should_evaluate": false,
126
  "should_log": false,
127
  "should_save": true,
128
+ "should_training_stop": true
129
  },
130
  "attributes": {}
131
  }
132
  },
133
+ "total_flos": 91500454459296.0,
134
  "train_batch_size": 16,
135
  "trial_name": null,
136
  "trial_params": null