ClarenceDan commited on
Commit
6370467
·
verified ·
1 Parent(s): 5ed1ebe

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 sha256:623fbf5cb703bbc48c2ca785edc9ba025b56e71a2e6584994a1617c853388c28
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92401f853c9445592c3f19329184789223695feb2475c727d5569e0c755deeed
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d84d475f06ba3337cf990ad8ef9c5214a1e799b58e3c640f5dfe12a4826a895
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10bb8d7c04160f9aceff957a72ded5e68a9c1b57e6c8b0bc9dbed6fde1e1e29c
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9a65387ba1ec6c284b308cada9b73ceeb24869d32fa7f81a3120b72b695c1d6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fa808660ddbc52908e9ed2eaba07f255839ebe308cc6b503b8b517a081559eb
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": 0.0002702580964821404,
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": 12.807,
103
  "eval_steps_per_second": 6.403,
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": 4986771571998720.0,
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": 0.00030028677386904494,
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": 12.807,
103
  "eval_steps_per_second": 6.403,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.00030028677386904494,
108
+ "grad_norm": 0.46173959970474243,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.3107,
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": 5540857302220800.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null