cwaud commited on
Commit
ed74fc4
·
verified ·
1 Parent(s): fc140a4

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 sha256:0dc224b999eea28dfd6fc70f9b5d14365ef6e3897f62d2f321730bf9d76c8c4b
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c14c27446042527f50a82fef7190f38e353a270c88efdd8f80fab876bff84421
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70b7c4ce50184ed77f6f17de67bdfc37a8e25415ead5b46108ff51d3a83af205
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0a6f2c573a0e1d024a3fa131c3dafc3463853fd2d92dba0aa41a06c0d1c639b
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa55bb1211b966ee38680600e87c633649407947bf0fb7e8011fe6d5c3e8c50b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa1c11cc02ca6c0d441d7517efb44d7c4ea980e6fce251e31e8f625c6ac0020e
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": 0.0183206106870229,
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": 7.064,
74
  "eval_steps_per_second": 3.532,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1231436170395648.0,
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": 0.02748091603053435,
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": 7.064,
74
  "eval_steps_per_second": 3.532,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.021374045801526718,
79
+ "grad_norm": 6.759243965148926,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.655,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.024427480916030534,
86
+ "grad_norm": 0.7865249514579773,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.0324,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.02748091603053435,
93
+ "grad_norm": 1.0031616687774658,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.7614,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.02748091603053435,
100
+ "eval_loss": 2.113194227218628,
101
+ "eval_runtime": 19.745,
102
+ "eval_samples_per_second": 6.989,
103
+ "eval_steps_per_second": 3.495,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1847154255593472.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null