duyphu commited on
Commit
87295c7
·
verified ·
1 Parent(s): eb67f54

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:de9f82a1c16d739bef4794e02b878b2c5f599d530720d5e3c56273dd2c8a9f68
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d8a5cfa008be2a3e66c86cfb075f6663d48bcc4314c01e4634109ab6193d664
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e33b8f4709854bb805ea59772545bc4517a51935b2a1ef4a7949967b7c91b172
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e500af2cb4ca1336ace8d46617ebf96b5aa12fe255f1316aac7dade674575ce
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ab39d8fbd2c874407a81c5039399b6ff46c2237e5cccded63b3457667cba4d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c1a9efc636b7b869b56b9a3c249a5137faaba5ff8c17f65984f4c6ae31ad9e
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": 0.010593867780380972,
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": 4.4021,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5038925634600960.0,
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": 0.01589080167057146,
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": 4.4021,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.012223693592747276,
72
+ "grad_norm": 12.776435852050781,
73
+ "learning_rate": 5e-05,
74
+ "loss": 4.1317,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.012223693592747276,
79
+ "eval_loss": 1.0448427200317383,
80
+ "eval_runtime": 75.0361,
81
+ "eval_samples_per_second": 13.78,
82
+ "eval_steps_per_second": 6.89,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.014260975858205155,
87
+ "grad_norm": 9.15871524810791,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 3.9519,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7405029845630976.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null