jssky commited on
Commit
46adc86
1 Parent(s): 903a24a

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:a49d83e389ad887b1763b72c12b0a12fe41aedaaeb82546e9d6f19f7904a34a4
3
  size 228140600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99aae0b8f742262aafb799cdb4d820c10f93df7f1b79a395855906c2125d4af
3
  size 228140600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85b03db9aeb0407d75951040b44bdc4c6bf88d7d878842433160a87cde91024e
3
  size 116472340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a37e7e7ccd62bab415145f3af28bcf4ef389cc870b310527adceb4207dfbc1
3
  size 116472340
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:940d78ce95bb8f7eb48adc329f7531c0db71f4ebde5ffbc17217d635e541d518
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba93f8db423cb3b679c79a7db27151bfbed53e821114d602901acf9157000a85
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
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": 0.00046463603510583376,
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": 3.53,
103
  "eval_steps_per_second": 3.53,
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": 1.029276212133888e+16,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0005162622612287042,
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": 3.53,
103
  "eval_steps_per_second": 3.53,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0005162622612287042,
108
+ "grad_norm": 98.54031372070312,
109
+ "learning_rate": 0.0001,
110
+ "loss": 11.2608,
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": 1.14364023570432e+16,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null