nathanialhunt commited on
Commit
cc20628
·
verified ·
1 Parent(s): 70eab54

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 sha256:123cb0a564ca85d34c2fc1dda00413c4fa1fddb221fbc455acf672db2d307103
3
  size 65309632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d5b31216d4ba11c25064a7125df1e242f87f39bc757ee1f54b466ebf0831fa5
3
  size 65309632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34ad009221d3f0d058408567dc7638fea786545fd7d64707619c3c7d62ed882c
3
  size 33424212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad5784d7e46f121431f9afb04f246cd35a2610f3a02f5c4397c68aea6794068
3
  size 33424212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39980cd61931bd29819cca9f98b8da1b6b84e6588ddc01792f938fd65cbb3a49
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3818e95074faa0d9cd258190f04acef580a83fcaa738e0b748c985ee478a8f7
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": 0.2982791586998088,
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": 36.025,
61
  "eval_steps_per_second": 18.34,
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": 6366664319827968.0,
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": 0.3824091778202677,
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": 36.025,
61
  "eval_steps_per_second": 18.34,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.30592734225621415,
66
+ "grad_norm": 6.404417514801025,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.91,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.3824091778202677,
73
+ "grad_norm": 4.661633014678955,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.681,
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": 8162390153625600.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null