shibajustfor commited on
Commit
2f85f44
·
verified ·
1 Parent(s): d4a656e

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21ffe40a3d30f8ad0a887600839946c14584dfd5010442076d953bb71b1888ac
3
  size 104902272
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d52e4a241b47c43e5cee9b1dcc04a0578f48bd83e458ad8cac49d6d48dda81
3
  size 104902272
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a08ea029dc4de6cb4718a944c7d3533e06694d6ea128d83a2a1d9a8ad38fb45
3
  size 53622996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fddae390da9274aef273df97d48404586d24742142a58465e3ec49dad4e26571
3
  size 53622996
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6801404673153c1dd04b6bd0f8848791eb80fae74c9ced3bafcc30ce63bad546
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f623204bcee724fbc39aa4376a468d3cd84172e6facf6eb7ed854a05a34881e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.024344569288389514,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 23.709,
46
  "eval_steps_per_second": 11.855,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 9019809752678400.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03651685393258427,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 23.709,
46
  "eval_steps_per_second": 11.855,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.028089887640449437,
51
+ "grad_norm": 5.763250350952148,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 6.6716,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.03651685393258427,
58
+ "eval_loss": 1.5344139337539673,
59
+ "eval_runtime": 18.9954,
60
+ "eval_samples_per_second": 23.69,
61
+ "eval_steps_per_second": 11.845,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 1.341206493659136e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null