nat-hunt commited on
Commit
3e19b14
·
verified ·
1 Parent(s): 3500843

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:ffcfa89727f942ea1f398aa86ade0f1fb7a782cd81a792a98e81ecd4668d695d
3
  size 327040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b4371efed7cc393b3d01ec5e88a498729834e13905772cdac393cf0f60b341
3
  size 327040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e44527256004b128855b16939b5f5d147f44823eba6054dda2678c26894018e
3
  size 739258
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d531791957836332d28de75765f811616dc822e65b82f4a43b3e223e3fd19d89
3
  size 739258
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce48dec86ac6000671bbcda61602ac669c6643b660b3c79e45fe5bfda138dc71
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:731356647582c8ef90f666e46f0dafaa099438d483cb22a0268abc589e0178cb
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": 0.0014563106796116505,
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": 72.405,
103
  "eval_steps_per_second": 36.217,
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": 1282848325632.0,
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": 0.0016181229773462784,
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": 72.405,
103
  "eval_steps_per_second": 36.217,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0016181229773462784,
108
+ "grad_norm": 0.1310613751411438,
109
+ "learning_rate": 0.0002,
110
+ "loss": 11.9309,
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": 1470582226944.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null