duyphu commited on
Commit
3ffc8f3
·
verified ·
1 Parent(s): 9c9a75c

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 sha256:2e5a68b511b82a2a8a2b074d8679cdc86402f4d80aae49a8ce9fcee8ac917063
3
  size 30026872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c7c0bd6426d5a97049550cd96cd8cd8cc58da8c92a873360a5fefdd5961e24
3
  size 30026872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0738a224ce4f75fce6844fabf6823d2c0cc5345ecf63314f8172233f74e8f9cb
3
  size 15611412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:575dbe7adca18cdf6dc933f69e4e95a5479a782fc062a7cf4448639290474adc
3
  size 15611412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:534fd80f4a36921aa36f02966232895e27318825fe994a2792a763901e8e85a0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9a55ac0c992411009853207820ca4f6897afa3f8dc742e986d6f2be555193f7
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": 0.022569444444444444,
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": 1.8513,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 822606865367040.0,
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": 0.033854166666666664,
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": 1.8513,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.026041666666666668,
72
+ "grad_norm": 3.8759148120880127,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.4983,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.026041666666666668,
79
+ "eval_loss": 1.2910934686660767,
80
+ "eval_runtime": 16.1354,
81
+ "eval_samples_per_second": 30.058,
82
+ "eval_steps_per_second": 15.06,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.030381944444444444,
87
+ "grad_norm": 2.2127106189727783,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.0924,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1233910298050560.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null