Best000 commited on
Commit
298011f
·
verified ·
1 Parent(s): c13f49f

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 sha256:62a08398e36e7855ad1449efcab861c27ccc9312395ccaaae6776e306340f108
3
  size 5752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96052ae372db17bcd3a7a163d209fd1c238196520b93415fa40cff2dd7c3c713
3
  size 5752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abbf5cce6cb6d3bb58e5cccf5d7fd78c53eeccd37b26daa24e6d4fb696fac1b5
3
  size 15814
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1416ad21701f038dcd2a12524c884202b1789ac293456de425be49f11da3bec
3
  size 15814
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4e103f057cbf52631a0f74dec69e271b2b990ec70bac9b6694c66ba4e1959d
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": 0.0006143764079459349,
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": 26.244,
103
  "eval_steps_per_second": 13.122,
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": 219151663104.0,
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": 0.0006826404532732609,
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": 26.244,
103
  "eval_steps_per_second": 13.122,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0006826404532732609,
108
+ "grad_norm": 1.5078968317538965e-05,
109
+ "learning_rate": 0.0002,
110
+ "loss": 46.0,
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": 254016700416.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null