duyphu commited on
Commit
2eb3c2d
·
verified ·
1 Parent(s): 5b55514

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 sha256:4eb0797651d3cd6a3ff2660eff58ce3795ca1bab9eec3ec4e54d5aed5dcfeb45
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e68440a452efd701302045df191140c3c93f08323cdf79c4a497c2431387fd8e
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20ce5992ac6109d1858e790959fd04499724119bd9e51a840fc3b0dbcce5f8b9
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7357f8127379be5f1701500c4319128b8987533d4e287d88c9067843b2fd7974
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b550eddb1fd0b6c7745761b04141bf71e2f5f8aef394e37d964f7d28953bcf3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9f821a5545c75b1cfa1a06b1823d7b35dba42e6f8dc963e0faf49c548c574b
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": 0.009261733012734884,
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": 1.5521,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 721636546314240.0,
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": 0.013892599519102324,
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": 1.5521,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.010686615014694095,
72
+ "grad_norm": 0.8884016871452332,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.4202,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.010686615014694095,
79
+ "eval_loss": 1.789035439491272,
80
+ "eval_runtime": 34.3248,
81
+ "eval_samples_per_second": 34.436,
82
+ "eval_steps_per_second": 17.218,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.012467717517143111,
87
+ "grad_norm": 1.110180139541626,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.4386,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1082454819471360.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null