xiechengqi commited on
Commit
9774904
·
verified ·
1 Parent(s): 17f98f5

Training in progress, step 10, 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:fddccb5ade4453c225224da6bea266721c189b92b885e21175dcca554acc07fd
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e32160b3431d52bdcd52b7caac73cb697f9218ae1e9b52ae036d54e5df6ba13
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d88c956696c48bfb6d42e5e38e5b2c3cd697c12c404a38bf186ce32a8200e0c
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee131087ae68361dc2dd5e085eeaf630afd42b68e47b33ef23b30a2071ee4cdf
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ff81a8bcc953787cfb530262ee46951f0cab3abe55d24348f1999e17a97d611
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5fcb1d6b1cfd02f868b5a053d7a6dc5c32e3c853b64270a3b83865fdd66e2fc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.00131420435877779,
5
  "eval_steps": 3,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 11.48,
103
  "eval_steps_per_second": 5.74,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 2265716203978752.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0014602270653086555,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 11.48,
103
  "eval_steps_per_second": 5.74,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0014602270653086555,
108
+ "grad_norm": 1.094745397567749,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.2249,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 2543150841200640.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null