adammandic87 commited on
Commit
bebdd22
·
verified ·
1 Parent(s): 3c05401

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 sha256:0e02b16238cc9a689ef4cc394f791a2dde10563b7e28fa8f9970383ca6cff4a4
3
  size 15182728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9de1da6d5ed447f6daed8ee40f8fc9b4ae4dc897934786978473e1d3233c74
3
  size 15182728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a957c6254c6d2af630203438fa1cbc88ad140bf2a6b7a55c2cef042e09426ad
3
  size 8075796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e68c36b7cb1c9debce78cab2d93441a428153550ac162df60b02388bb783c1
3
  size 8075796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8b1ba37de46bd55947921e981af81175de41ab0e33c654019eefd79b863b1a5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d75357bb9903605214df4fb02563039e8e5f7c1a61673e6ee0c2f306a7cfec6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.0032959371236610255,
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": 61.566,
61
  "eval_steps_per_second": 30.789,
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": 360601872236544.0,
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": 0.004225560414950032,
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": 61.566,
61
  "eval_steps_per_second": 30.789,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.003380448331960026,
66
+ "grad_norm": 0.7871419787406921,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 3.3147,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.004225560414950032,
73
+ "grad_norm": 2.028604507446289,
74
+ "learning_rate": 0.0,
75
+ "loss": 3.6075,
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": 464179005751296.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null