duyphu commited on
Commit
17d970a
·
verified ·
1 Parent(s): 9b22370

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 sha256:8661537ad86d1fa8b5c100fec1ddcec28dbb78f6e2ba5ee266df6453f7af548e
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5d3e84d70c399d06eede2034e8c66bef5828c19289fe377240aae686b16ef76
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c355f395f4622f63dd83b1c886bd24c91568d5ce988970a748548a88f7a4f5dc
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cab93b41be8cfc892832b7eb5fc6728c1b6ee84914e96f7342d668f77f52acd
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2aff1a6c4cc7a958d2f4e8ae002b51812321a670105c72ba191a30258605048d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:097dd997230514a6e98f8e2793b4ce5ec0bfb1dcbc062e11f1986f1876be0f9b
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": 0.0019311830352997975,
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": 6.0852,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 6265801682190336.0,
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": 0.0028967745529496964,
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": 6.0852,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0022282881176536127,
72
+ "grad_norm": 10.96812915802002,
73
+ "learning_rate": 5e-05,
74
+ "loss": 5.6197,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0022282881176536127,
79
+ "eval_loss": 1.431856632232666,
80
+ "eval_runtime": 468.2349,
81
+ "eval_samples_per_second": 12.107,
82
+ "eval_steps_per_second": 6.055,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0025996694705958815,
87
+ "grad_norm": 9.371012687683105,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 5.7799,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 9201526945873920.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null