Best000 commited on
Commit
3d9d1e2
·
verified ·
1 Parent(s): 007c6bb

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:a5cd7f48edd878e1f4fad2231c01fabbcce8f22ca72ba1838377a88b6083e3d4
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:313dcc1cb3837885acfa16f27654fda4d0cab6ae3cdfd89b76002bbdf06f96e4
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a9d765e9d099be46079453aa79a10332305eebb3a60b38117fabef3f1e8489a
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e55576cf37e96a963f97147b9550f87ca9154654610a5d73215e36951a8415
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce23990253dbcb847c65b8e07df81d199b8cb35ee201419fc10370dd6bcc8fb2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57fe9322ee192f6ca97876187da096d9083f730f45230a65c47e815b5fed1304
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": 0.0030600535509371415,
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": 25.925,
74
  "eval_steps_per_second": 12.962,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 600116796850176.0,
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": 0.004590080326405712,
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": 25.925,
74
  "eval_steps_per_second": 12.962,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0035700624760933316,
79
+ "grad_norm": 0.7155371308326721,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.8848,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.004080071401249522,
86
+ "grad_norm": 0.8622905611991882,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.0579,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.004590080326405712,
93
+ "grad_norm": 1.134154200553894,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.9633,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.004590080326405712,
100
+ "eval_loss": 0.921898365020752,
101
+ "eval_runtime": 31.9041,
102
+ "eval_samples_per_second": 25.89,
103
+ "eval_steps_per_second": 12.945,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 900175195275264.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null