nathanialhunt commited on
Commit
badf885
·
verified ·
1 Parent(s): 234e46f

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:e10ff7d14d260b8c35d20aa94f3fa4dae034412ca9fcf0807739efa544c434ff
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5567dab7b52e4da756b4a773097122ecdbb21114c1b30d64947c258a594426d
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be314395c111e9bfd88d03872ab61e74f664051bf428251f5db39ea3b7518ff5
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9217c7f750a62a3b929a9d0327035410bd99a7b56e43db8999e78fdcc6bf824
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:ef85f51d139fa88c501e9c10d2687be0cda0b477cc0a0033709ee647d8e59c50
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f95c7b2cec186bbbca93d9ef2e21f40410129093a693280167cb44fd0b4020a
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": 0.005531653349723417,
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": 22.228,
103
  "eval_steps_per_second": 11.13,
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": 2589389947404288.0,
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": 0.006146281499692686,
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": 22.228,
103
  "eval_steps_per_second": 11.13,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.006146281499692686,
108
+ "grad_norm": 0.5443244576454163,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.0572,
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": 2866824584626176.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null