trenden commited on
Commit
d9f1dd0
·
verified ·
1 Parent(s): eadc775

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a4b6b24148884ef808bb4919fc17ad18d939ea402c91089e26b7e48778fe5ff
3
  size 161714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34ad66d61235923a529dfc18e3af6f93c9ccda897a2f39d95a41d98ac6022caa
3
  size 161714
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b942c11561f555df9db07dadd765b0482dd8d6bb71bb704bd762b9c4f0664fdc
3
  size 64750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94bdfa229cb8e13ae6afff0cb5be2f29907f73afb53401e4ccb6b626d147de56
3
  size 64750
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6427ffbd65b4be1b2f3fbb643f167933e7260181d95492a2b6d8cd2d25b75737
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c72530c1181e385391bf43f1fdf08c8275fccd52a2134362ec0beb66af41fd8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
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": 0.0034445450330102233,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 377.733,
61
  "eval_steps_per_second": 188.866,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 102829768704.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.004416083375654132,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 377.733,
61
  "eval_steps_per_second": 188.866,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.003532866700523306,
66
+ "grad_norm": 0.08867950737476349,
67
+ "learning_rate": 7.3223304703363135e-06,
68
+ "loss": 6.9381,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.004416083375654132,
73
+ "grad_norm": 0.09842295199632645,
74
+ "learning_rate": 0.0,
75
+ "loss": 6.9406,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 131503454208.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null