mb00g commited on
Commit
eee403e
·
verified ·
1 Parent(s): 5f9657a

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 sha256:526fda155baa5b41f117b17c28abd6435bb13a1639aa8ee1f4bd12deee2cab85
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3350bf6d78929aaaa3782492c460796d0c98a67d9d267f9240cbbc960137167a
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d0966261aee9f88ccc47f5b4cf680d514accb1f224a33d563b0d6fd2d23ca5a
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68486d3ec92420daca01da57ff1ca9bc869d9f92a729c29c4ca25c5f8318c2da
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8daa47e5fa0e9a4f77b5b5a605545412b886dd6ab0a09e6b5cf492469c6c3e16
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f75e1f9ddaf97d0cbd24e5e4ece44de06394fdb29860b673fff442db3f0f5a6
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": 0.1610738255033557,
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": 1.78,
74
  "eval_steps_per_second": 1.78,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2462872340791296.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.24161073825503357,
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": 1.78,
74
  "eval_steps_per_second": 1.78,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.18791946308724833,
79
+ "grad_norm": 33.47844696044922,
80
+ "learning_rate": 0.00014,
81
+ "loss": 4.5034,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.21476510067114093,
86
+ "grad_norm": 18.189189910888672,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.4897,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.24161073825503357,
93
+ "grad_norm": 14.530669212341309,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.5332,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.24161073825503357,
100
+ "eval_loss": 1.0043643712997437,
101
+ "eval_runtime": 4.4829,
102
+ "eval_samples_per_second": 1.785,
103
+ "eval_steps_per_second": 1.785,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3694308511186944.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null