philip-hightech commited on
Commit
d86c494
·
verified ·
1 Parent(s): e26072e

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87a7c2a900dbcd8136f474e46a1ae985232a6054742a76964df18f95f610fad9
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41af16fee6e6447b5ce564cb17454b03b4e7414dcadc125167dd9b93765e6f72
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:282a4d96fa74cfee818f6ff8e052be51b369a2b9626e9c2a33055a7f2ca5dd50
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24d09afa22450a2fdcc38c99ced8a5b69a5afe423e796cc46c593232448fd80c
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb5677937911af181f78d9756ab6c551456588a495f0d9f0bab1942f26b5a232
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c793dd9643d1f0d7428a5c0f419836ac84444ecb2d94c90a6fc687d539bed3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
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": 0.0035110620962841258,
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,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 14.828,
61
  "eval_steps_per_second": 7.416,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 1.559365470388224e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.004501361661902726,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 14.828,
61
  "eval_steps_per_second": 7.416,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0036010893295221804,
66
+ "grad_norm": 2.1414716243743896,
67
+ "learning_rate": 7.3223304703363135e-06,
68
+ "loss": 5.8964,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.004501361661902726,
73
+ "grad_norm": 0.6878616213798523,
74
+ "learning_rate": 0.0,
75
+ "loss": 6.5208,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 1.978890190848e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null