trenden commited on
Commit
194fff4
1 Parent(s): 59fcdcf

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:e4f946e7a5ec90033e7ecc04df5b1f227e0976cdaf759557383c422112437afe
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2865a09adf7df7fdf74dc57dfb890686b42870ad26db5c6beaa380879208ab2c
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:373f473ae42e9da045b2de2c02420739e32136d155d854887680375d68bc581f
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cee1fbc4b1606d68cf1b241c98058d180b02bee1997e4f250e8748477681631
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c55d7eec620b3744307ce43f7537787a20690e46babf77f9d2e73260f51a43b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d1ba91d25b429efbcdd30d62a4a8076f6dd369bc223af7cfa0b01dac576227
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": 0.0007319155857357784,
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": 268.069,
103
  "eval_steps_per_second": 134.035,
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": 1063452672.0,
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": 0.0008132395397064205,
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": 268.069,
103
  "eval_steps_per_second": 134.035,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0008132395397064205,
108
+ "grad_norm": 0.007081515155732632,
109
+ "learning_rate": 0.0002,
110
+ "loss": 11.9329,
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": 1181614080.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null