nat-hunt commited on
Commit
b6acc54
·
verified ·
1 Parent(s): 9c028b9

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:e1db613e106b9983b89219cf83629f9516be0f96c9a8b5c0a3eed1c8bcd3e198
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f3190ca1f156a4c2408c7bc7400eff43342d49765ec280b41c26f010f6195b
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e6b68197fddf17e0ce735e75b95e18d5880320df13ec8e7d2862a1aa98a99ff
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7539c530ba4dde9246eb64ff5787084435396fe7889649dd11c03c276a9b33a7
3
  size 56950676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:653a7d79cc851bf5423ac30748a3285a94a397664d2f1baf19c62f5e6cbf4c2d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:561a55685a3cc1c3c67f8d1b76dcf29e73d0ebb9abc059e3b698558c2be1d65e
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": 0.0015425486331305167,
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": 15.317,
103
  "eval_steps_per_second": 7.662,
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": 3906972470476800.0,
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": 0.0017139429257005741,
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": 15.317,
103
  "eval_steps_per_second": 7.662,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0017139429257005741,
108
+ "grad_norm": 1.0727403163909912,
109
+ "learning_rate": 0.0002,
110
+ "loss": 5.0417,
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": 4246709207040000.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null