nat-hunt commited on
Commit
69b202b
·
verified ·
1 Parent(s): c53bb75

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:fd9df1b35cbfb9c2227a4211d01eb6a5e1e875b7158056e946b26eace3630c6b
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15afa01ff8df921b459df14fc93ee9cba6b9aa55122cf657d0503e37f9e04ba0
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c0d801a04a82e6e1ff1e8cd097d226490661dc17c2fc3516f9351843637f475
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674ff218646e9986ced424a0b470eeff54f994435651e3fd6126f82188949c97
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3da36683a47a91a9ad772f7df43342ed45380cacff56c8d7dcb5142c555aaa0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcdccc249fee2c1ad1a5096f95a837d69e1cc085a05644f1180a19891ee93076
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": 0.008336227856894755,
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": 38.777,
74
  "eval_steps_per_second": 19.453,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 492029198991360.0,
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": 0.012504341785342132,
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": 38.777,
74
  "eval_steps_per_second": 19.453,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.009725599166377214,
79
+ "grad_norm": 0.8317832350730896,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.2603,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.011114970475859673,
86
+ "grad_norm": 0.8683997392654419,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.3767,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.012504341785342132,
93
+ "grad_norm": 0.8667774796485901,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.3886,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.012504341785342132,
100
+ "eval_loss": 1.2922290563583374,
101
+ "eval_runtime": 7.819,
102
+ "eval_samples_per_second": 38.752,
103
+ "eval_steps_per_second": 19.44,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 738043798487040.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null