nathanialhunt commited on
Commit
d75700a
·
verified ·
1 Parent(s): 6ea4f6e

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 sha256:92e98bb8b69c41eb204f90171786f2e84ca0b1ce303ba58c674c678a70ddf6b5
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f172b6b1d078d8419f850a861dba0ded9cd87bded9e04527b8644d173c8cd325
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bb2761d1499c96b9e68ee55c62dc3e2f48237f1d624667095e29888f444777d
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e80fd726a422b0c2b9e19f688a3e9d8f456fb3279a453b002ba96b22092be02e
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:a7d873e5981a74ca193df96e36ccebe68055d4a9941f3ec8ce17e5615941b9a7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:836bdf6622005bd1eae48ddbb8f060c7755138b25b822e798006703ec4217354
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": 0.0016770316539724687,
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": 17.496,
74
  "eval_steps_per_second": 8.754,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2038420419379200.0,
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": 0.002515547480958703,
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": 17.496,
74
  "eval_steps_per_second": 8.754,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.001956536929634547,
79
+ "grad_norm": 9.246593475341797,
80
+ "learning_rate": 0.00014,
81
+ "loss": 18.576,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.002236042205296625,
86
+ "grad_norm": 12.987396240234375,
87
+ "learning_rate": 0.00016,
88
+ "loss": 14.8416,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.002515547480958703,
93
+ "grad_norm": 14.694947242736816,
94
+ "learning_rate": 0.00018,
95
+ "loss": 13.1413,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.002515547480958703,
100
+ "eval_loss": 2.7212073802948,
101
+ "eval_runtime": 86.3595,
102
+ "eval_samples_per_second": 17.45,
103
+ "eval_steps_per_second": 8.731,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3057630629068800.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null