great0001 commited on
Commit
7629861
·
verified ·
1 Parent(s): 3c58f7a

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 sha256:58fbbd3758ca728b013e1c238d0add48620a637527fbffe50b1516c915228810
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c200f8080879cbdb94192a94f2ee913759370c86ecd52135c0c011ec3b44bd
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb05b8c3f2ceb28969a1c7e84a4d5eb2a3c146aa7d950bdeae122576c85a6c51
3
  size 79968772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49fe178afb66485f5df32c037af5d0e645832bc1a90170f60869c1a89ab08d30
3
  size 79968772
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bceb7de99ff7b17d6ec7d794e86c7f9fba87fb5bd36c827c120924e029007a1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b07705cdd965f3a6be3f96556df5291ffbacca044c445cd4e4aab2e1bcb8ff
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": 0.46706586826347307,
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": 58.433,
61
  "eval_steps_per_second": 29.217,
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": 968579491037184.0,
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": 0.5988023952095808,
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": 58.433,
61
  "eval_steps_per_second": 29.217,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.47904191616766467,
66
+ "grad_norm": 0.0009081371244974434,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.0,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.5988023952095808,
73
+ "grad_norm": 0.00041487993439659476,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.0,
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": 1241768578252800.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null