phungkhaccuong commited on
Commit
45a1d2f
·
verified ·
1 Parent(s): 4e0449d

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:b458179a0d505a195f5e64ef1a7e79e7d71bc4142418c340bdc5f689b1ebcc59
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5676b1fab164f622838fb60ae0630b3dfd94ff147bbf20dfe9452014d3db366e
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c6402f408df38bd8641dd1bf80b7799ac3f75fd0c03f2fb71851c73a5caa6c9
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3520d799ef2880ad29434999856bc553c6b5d32958a06a467be9ff6400b33603
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19345076a59d2345cb36b77781c9e57468c57d8d41c5a6f2c85d50f71a6f780a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cfd169eaaa2e100acfe8ba68db24784222eedca4046124bbd3f932d9cc2b713
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": 0.011057947900053162,
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": 0.5737,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 7675691629805568.0,
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": 0.016586921850079744,
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": 0.5737,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.012759170653907496,
72
+ "grad_norm": 0.47978395223617554,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.5898,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.012759170653907496,
79
+ "eval_loss": 0.5690296292304993,
80
+ "eval_runtime": 105.8613,
81
+ "eval_samples_per_second": 9.352,
82
+ "eval_steps_per_second": 4.676,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.014885699096225412,
87
+ "grad_norm": 0.45397356152534485,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.552,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.1744732975726592e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null