nat-hunt commited on
Commit
fb6c287
·
verified ·
1 Parent(s): 69b202b

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15afa01ff8df921b459df14fc93ee9cba6b9aa55122cf657d0503e37f9e04ba0
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa67759d699657c1f339a0c12668174b72dfdc28b8b6ddcf8fdcde4baea53c3
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:674ff218646e9986ced424a0b470eeff54f994435651e3fd6126f82188949c97
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05ab607f0802b19f55d9fa8fe77434375b2adbb5c06bd4362fa00e217e4d3ba0
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:fcdccc249fee2c1ad1a5096f95a837d69e1cc085a05644f1180a19891ee93076
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88dae949d5be32055af49c9dcd763c9b06b19fdc2d661fa84cd17b93ca67c421
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.012504341785342132,
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,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 38.752,
103
  "eval_steps_per_second": 19.44,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 738043798487040.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.013893713094824591,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 38.752,
103
  "eval_steps_per_second": 19.44,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.013893713094824591,
108
+ "grad_norm": 0.983684778213501,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.1264,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 820048664985600.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null