nat-hunt commited on
Commit
23fd0bc
·
verified ·
1 Parent(s): e9b1f80

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 sha256:0b507faa51f0c1702aba61be80d38252cb8559adb0f334cf01337224293a3e02
3
  size 5327744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de0d2ab64e54d67b502fb52975ff599d8e98cc06f794f8aed97f1d252384871
3
  size 5327744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b12e3c28e3da6260fbbfad235f14a1b6bb89647c6f6e9bca460fea057363b3f
3
  size 2857722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082a304085f5f0e51dd10dee0c94c0ba4cf651995237d501a60c9b8ec844664f
3
  size 2857722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19abc7973eb0745be949bfaba5fa367d7354355aacc46abefd78c710773f9cea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a0ec8376f808f06175bdace44006bdc5c9473bbbfb80dec778a3c949b17a586
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": 0.00022067139271232726,
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": 115.407,
74
  "eval_steps_per_second": 57.709,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 25475413966848.0,
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": 0.0003310070890684909,
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": 115.407,
74
  "eval_steps_per_second": 57.709,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0002574499581643818,
79
+ "grad_norm": 3.8548436164855957,
80
+ "learning_rate": 0.00014,
81
+ "loss": 13.6021,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00029422852361643635,
86
+ "grad_norm": 3.81418514251709,
87
+ "learning_rate": 0.00016,
88
+ "loss": 14.7787,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003310070890684909,
93
+ "grad_norm": 3.5406877994537354,
94
+ "learning_rate": 0.00018,
95
+ "loss": 14.514,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003310070890684909,
100
+ "eval_loss": 3.558913469314575,
101
+ "eval_runtime": 98.7028,
102
+ "eval_samples_per_second": 115.995,
103
+ "eval_steps_per_second": 58.002,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 38213120950272.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null