shibajustfor commited on
Commit
a14e882
·
verified ·
1 Parent(s): 2f74ba7

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 sha256:8f983cb2a5f612e326031e443873d48711cb94e10592cf1d65c72712da0ea605
3
  size 65309632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1be397dbb11d20a3bcb4f61970b1797073842ee9e8f93b4645b156f49a5f3d7
3
  size 65309632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a37ae8e651a837336ce84cccd145fd48dba2dfc770f3ec3406d986b2022d5b56
3
  size 33424212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b42c650ae0f9a3bcb0db409be4faa3feb02a900bd53a01335a5f5b331f31c59
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:f33fbf0dd2fa93f33d420c86701ae4a65abf42d9f472aa29c65ae1f2d0d73758
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd2b885d1f9554bcd47678716f5e6c8cf0e3a9dc317405cf3f3b1ff46849c730
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": 0.04508670520231214,
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": 36.289,
61
  "eval_steps_per_second": 18.194,
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": 6611536024436736.0,
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": 0.057803468208092484,
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": 36.289,
61
  "eval_steps_per_second": 18.194,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.046242774566473986,
66
+ "grad_norm": 21.361957550048828,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 9.5961,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.057803468208092484,
73
+ "grad_norm": 29.381607055664062,
74
+ "learning_rate": 0.0,
75
+ "loss": 8.722,
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": 8407261858234368.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null