tuanna08go commited on
Commit
2890730
·
verified ·
1 Parent(s): c5d3aa4

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 sha256:2f4e80ef2f99dd46b47d1e965ac945717aab3f76cbbbcc1893df8fce15c48cef
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6456bcd6e396b9ecedfcecd217242dbdc4580ef6056ffbcf2ae775e09e1b45e1
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78feee20b47bcbc966806ec3ca71b47e91983c5ffee458cccae2f5f678eb93b3
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17b2c828d13bc8c06b76da012acb10020bc10f9a9a3c5806cf228b74d2f4d4a2
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:181e5474a909cc41ef3f21a854a475dc123b4f13c0930c491c5a5cb33ca6e896
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e52ba9079da753deff357d9c4a428b9b6ca2de2d54c84b4e417f6ae74bd2edce
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": 0.0223463687150838,
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": 1.3272,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1106300305932288.0,
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": 0.0335195530726257,
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": 1.3272,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.02578427159432746,
72
+ "grad_norm": 0.7843586206436157,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.218,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.02578427159432746,
79
+ "eval_loss": 1.217673659324646,
80
+ "eval_runtime": 14.7055,
81
+ "eval_samples_per_second": 33.321,
82
+ "eval_steps_per_second": 16.66,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.030081650193382038,
87
+ "grad_norm": 0.9873902797698975,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.217,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1662647858626560.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null