chauhoang commited on
Commit
42c58ec
·
verified ·
1 Parent(s): 9fd6104

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 sha256:881cfcbd6f950cb34d109f271ffd93deaf809f9a82e86f1b398c26d46fae0673
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea33113df6ff170c758ae64e27d15fc3b3c86599402e51625d329bcdf1be452b
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7debe4a9565b53a3a41e8762eaab21c1cda70ae636012bf44fd3aa6978a9868c
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53aebabcee745664de39d4f0265f7ce831f7e9fac4f7a2b11709498a59db350
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87978ca9d3adca18fc041565b3eaec92643378b395f062b777bc42dd5d640455
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cacaf8ca7dccda8c7558dd4f048e47ecbfd6553f222b04583f4b378449c85d41
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.0015661471274753408,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.3348,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 7353159911473152.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0023492206912130113,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.3348,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0018070928393946238,
72
+ "grad_norm": 5.103176116943359,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.0001,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0018070928393946238,
79
+ "eval_loss": 0.8057319521903992,
80
+ "eval_runtime": 647.3135,
81
+ "eval_samples_per_second": 10.798,
82
+ "eval_steps_per_second": 5.399,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.002108274979293728,
87
+ "grad_norm": 3.2122302055358887,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.5477,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.1214595842637824e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null