philip-hightech commited on
Commit
7c348d3
·
verified ·
1 Parent(s): 43fbc97

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 sha256:26840657de0900d2a44de9f8ad4c4d8d86cbe04163eadd8ad03c0bca8474e16b
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d6fd7bb549dc2cf080762fb65cd5a0db1eee68e497c36dc9e45a530bda77748
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8c695f05cb6d264d6d5b9991d7c809573a58b32f083e495f6c761dec188cca6
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b253596035c5c7608941c4fde09dc7312bad36967a44073b0e268e45ebbd5003
3
  size 56950676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:836bdf6622005bd1eae48ddbb8f060c7755138b25b822e798006703ec4217354
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e339279e44c5c15da33d41816eb20d1d43d6744958966d073b2d253a0420c7
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": 0.0003050873312485699,
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": 17.234,
103
  "eval_steps_per_second": 8.618,
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": 3057630629068800.0,
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": 0.0003389859236095221,
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": 17.234,
103
  "eval_steps_per_second": 8.618,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0003389859236095221,
108
+ "grad_norm": 2.9018757343292236,
109
+ "learning_rate": 0.0002,
110
+ "loss": 4.9559,
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": 3397367365632000.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null