ardaspear commited on
Commit
a1540c7
·
verified ·
1 Parent(s): aec1d9c

Training in progress, step 27, 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:a3e1aa679d40a9a1acf08562cce1e33e7082f0e4b554075e2b8723645bfb490a
3
  size 338298
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56e8bb5c125fcff458d82cdb8c0ec84c5d582592ae772394df2af01fa1df0eb
3
  size 338298
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c045843135f55f6513beba9ce9b82f04db6e29af8edf75c7731a40f4020ee74
3
  size 418030
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e69c2dd56bcd5db304d9f8af68291f35485aa4d160072e4c2d64999746de96c
3
  size 418030
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bf4a70b2f1e0083900a8a144d37753c55636b180594109e7e6c3f925b4e7d11
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9df42a9d1501f6518540f2f97c2607aaa7a902f0945692ed6b6ad9ee3c0889b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
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": 0.09183673469387756,
5
  "eval_steps": 9,
6
- "global_step": 18,
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": 608.897,
74
  "eval_steps_per_second": 154.992,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 173003046912.0,
96
  "train_batch_size": 4,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.1377551020408163,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 608.897,
74
  "eval_steps_per_second": 154.992,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.10714285714285714,
79
+ "grad_norm": 0.5388941168785095,
80
+ "learning_rate": 9.635919272833938e-05,
81
+ "loss": 6.8956,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.12244897959183673,
86
+ "grad_norm": 0.5204723477363586,
87
+ "learning_rate": 9.414737964294636e-05,
88
+ "loss": 6.885,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.1377551020408163,
93
+ "grad_norm": 0.4605754613876343,
94
+ "learning_rate": 9.145187862775209e-05,
95
+ "loss": 6.8733,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.1377551020408163,
100
+ "eval_loss": 6.866656303405762,
101
+ "eval_runtime": 0.2715,
102
+ "eval_samples_per_second": 607.839,
103
+ "eval_steps_per_second": 154.723,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 259504570368.0,
125
  "train_batch_size": 4,
126
  "trial_name": null,
127
  "trial_params": null