quannh197 commited on
Commit
11ec406
·
verified ·
1 Parent(s): 08d367a

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:b24bfeec0f09e54fa2fd327a51dc2eca8973e1d4f00fca4c9f19c3cf9f6fc16c
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee25833a399ccaa3378eda70e927f9383b519a4defe1fa66047fa2674219bbeb
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:318543ecb9bcad1709112d9db7f62ba89d23129f2291146fee6dbbba4b93d21a
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c0e9be072cfa8bbc6be62396d858a9f4ed84684a5378ee5939f418318862c92
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d68d2a8ec68d97e9f6781386cdc5d11673589bf128caf93d024b660045d53f99
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c794a47edc9435384cbc7bbda79d6455642ccecbb17e631e8dfd483567816013
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": 0.0001279795232762758,
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": 14.765,
74
  "eval_steps_per_second": 7.382,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1954499090448384.0,
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": 0.00019196928491441368,
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": 14.765,
74
  "eval_steps_per_second": 7.382,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00014930944382232175,
79
+ "grad_norm": 0.6192784905433655,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.5229,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00017063936436836772,
86
+ "grad_norm": 0.6975032687187195,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.5503,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00019196928491441368,
93
+ "grad_norm": 0.9542371034622192,
94
+ "learning_rate": 0.00018,
95
+ "loss": 4.5562,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00019196928491441368,
100
+ "eval_loss": 0.9606015086174011,
101
+ "eval_runtime": 1335.5592,
102
+ "eval_samples_per_second": 14.78,
103
+ "eval_steps_per_second": 7.39,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2931748635672576.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null