JacksonBrune commited on
Commit
98f1afa
·
verified ·
1 Parent(s): 83408c7

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:be31d2a11ba71aa7de668911ac5add5a216979db09d4ce0b7204119b8c0e9315
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b1d813462e0848f47d799b159a51ab250120608ec320ed9759677d8f3068c0b
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c0946f9fa09e73e1fb5917efc08907229c213d0c47c143504f8d12f23f0fd29
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2d887cd9da0f46907562d0b46a5c11121fc6eab19c453eaf0e12f6993e125b3
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f26e16ac608da09f1760eae69aec0ce67d647fa1cc7e2b7ba4d78e3e730bf0e0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c45fdd17dd9f8645f89ad3d99d22c16e042b55bc8777e3b5c35b7f1c6d6a3491
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": 0.042105263157894736,
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": 22.308,
103
  "eval_steps_per_second": 11.154,
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": 1285134728822784.0,
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": 0.04678362573099415,
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": 22.308,
103
  "eval_steps_per_second": 11.154,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.04678362573099415,
108
+ "grad_norm": 1.120149850845337,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.8044,
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": 1422827735482368.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null