nat-hunt commited on
Commit
b077502
·
verified ·
1 Parent(s): 1238fd2

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 sha256:756188899ea55140acd72c29e31c96cea85fff87cbe0258bac20c9f9276ad0ab
3
  size 5327744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:360e5cdfe8cb2495a1216bfe2677b7a3c39265bd285f02d566f8107eb9b1f235
3
  size 5327744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c457cc10c5310f9055813bb0f70a9ddb24a2c06e00b740c57778c87648c30cdf
3
  size 2857722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587b319b65693405179b14cb1de8aec26b282d27ff037e3d78f8131b00a8f54a
3
  size 2857722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cda0ba450d27bbf2281f6a3a6a9d6b8e9a27248312721aa88724608eaf3ee7a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0508585c9fe24f58afe76f4785f10d81474c66e1c4c5763458f7a0c3f7b88ae7
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": 0.0006614121148652373,
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": 136.184,
103
  "eval_steps_per_second": 68.092,
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": 19106560475136.0,
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": 0.0007349023498502636,
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": 136.184,
103
  "eval_steps_per_second": 68.092,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0007349023498502636,
108
+ "grad_norm": 7.899801731109619,
109
+ "learning_rate": 0.0002,
110
+ "loss": 14.047,
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": 21229511639040.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null