pedrosperber760 commited on
Commit
9116443
·
verified ·
1 Parent(s): 5fe75d8

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 sha256:1cde26a5d5e00a77626bb777213f7ce9d0a6465c5c4c9e36263bd48fded84356
3
  size 619632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77a25462fc27e5abd83681a5ed0dbc236b83eb21e714d2f726c2e8fc971bc6cb
3
  size 619632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d459dc46d22c02a3baa12dc4bbd62996b67292ccb165171fd6ebd09105f64c8
3
  size 1324026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c6c52cee4b3c33a1d6b38e4da3b1b2cc99226002ed0dd0d9c6058019681a2c
3
  size 1324026
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60c9e35ce390deeed83aeaef6f7c1f6649ab9ed361bc0bf084a07c434458cee2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6edb4c660568a65bef01d630b56e760940c5b85cc53771b6da9e3adfc2928313
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": 0.1276595744680851,
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": 142.243,
103
  "eval_steps_per_second": 47.414,
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": 6855373357056.0,
125
  "train_batch_size": 3,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.14184397163120568,
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": 142.243,
103
  "eval_steps_per_second": 47.414,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.14184397163120568,
108
+ "grad_norm": 0.2909541130065918,
109
+ "learning_rate": 0.0002,
110
+ "loss": 11.9263,
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": 7617081507840.0,
132
  "train_batch_size": 3,
133
  "trial_name": null,
134
  "trial_params": null