DeepDream2045 commited on
Commit
8a08c71
·
verified ·
1 Parent(s): 362c6ea

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:e54a6c94ab4dc0984c8231ad00270fd2495b2979d045d4136ce5d2b49fa1ba10
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc9421b94a0c760681b1b87b9efe94fbf012f28c080d01d4b24b16cf43fbb806
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0e8b2c07d145dc22719993dbd956dce7a8a2f565916ab46e77861bbfafddd6d
3
  size 18810036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:370f2439d8007af76fdded0b7d6a70844e1020e667508148ceb06670ee4f84ab
3
  size 18810036
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01ae0673394c6d0448d87a05b8dce85b58d04fafa4d6c418a5ee6c92aeaab53d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e80e63932c8eae7c99e68576eba41b28c2be6da6d5728e9d2106b0941dfcd24
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": 0.0008207185847163961,
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": 4.887,
103
  "eval_steps_per_second": 2.443,
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": 648858870743040.0,
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": 0.0009119095385737735,
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": 4.887,
103
  "eval_steps_per_second": 2.443,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0009119095385737735,
108
+ "grad_norm": 4.873310565948486,
109
+ "learning_rate": 0.0002,
110
+ "loss": 3.4354,
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": 720954300825600.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null