tuanna08go commited on
Commit
b0cb903
·
verified ·
1 Parent(s): 305413a

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 sha256:4b230d0a7e167c12594365fc8f637b3ec9b28dc7c44271b8edcbe870da511d69
3
  size 12609416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:691a08ccf2b1b967d034c43e0b8d418078f72bf2666c3e5b7ec342696d720cf9
3
  size 12609416
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0f0cb1235f1923caf0caef4048d3cd71eec708524ad50316971e4ecb5f9ed08
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7688c80e59a5704772c8a39a2dfd7a2b24e10f5fa38e2c76865145bbd1a231ec
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e0fea1666a0acf445062b178f8c65da1afcd3e5006f1780cc246c23df365132
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db7649aa3d75e5d6374a79c834bacb769f27bfd7c17dce1ae63aba9b819ad74
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": 0.014678899082568808,
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": 7.4351,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 223332217651200.0,
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": 0.022018348623853212,
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": 7.4351,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.016937191249117856,
72
+ "grad_norm": 3.883378267288208,
73
+ "learning_rate": 5e-05,
74
+ "loss": 7.6614,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.016937191249117856,
79
+ "eval_loss": 1.8544365167617798,
80
+ "eval_runtime": 44.5521,
81
+ "eval_samples_per_second": 16.744,
82
+ "eval_steps_per_second": 8.372,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.019760056457304165,
87
+ "grad_norm": 4.95913028717041,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 7.8261,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 337813438464000.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null