nat-hunt commited on
Commit
71ad216
·
verified ·
1 Parent(s): 4f7898f

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bf64353182eec04b39aa8eab02560846edd9311dbbbb5d5042e0addd77c5f86
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f23fb54f3b8a7cd95c446008eed9a71c49943461914ef6587a6dd5e76a1f0f1
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b97ecbba5e5c139e040d1f9f83f04b5f0f6ebdb0e077cac80938b7091a80ab28
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90021a9cfa81abadddd33adb8ecdc523dc110962ce4d1e07a7ba5db685d67fe3
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8aeca134f7586c746af7a8dabb5d65178bb190c2f8f63160e7b8259f3f735ec0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f835cac311d0645293406c48973e65d7c21b68a87b9a52a2a49c7a825f66bc9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.003955826602933905,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 28.794,
74
  "eval_steps_per_second": 14.419,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1095418616217600.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005933739904400857,
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,
 
73
  "eval_samples_per_second": 28.794,
74
  "eval_steps_per_second": 14.419,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.004615131036756222,
79
+ "grad_norm": 12.2399320602417,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.4812,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00527443547057854,
86
+ "grad_norm": 14.318899154663086,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.5268,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.005933739904400857,
93
+ "grad_norm": 17.184829711914062,
94
+ "learning_rate": 0.00018,
95
+ "loss": 6.084,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.005933739904400857,
100
+ "eval_loss": 1.6159027814865112,
101
+ "eval_runtime": 22.1682,
102
+ "eval_samples_per_second": 28.825,
103
+ "eval_steps_per_second": 14.435,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1708853041299456.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null