lesso commited on
Commit
95083ae
·
verified ·
1 Parent(s): a4c5a76

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 sha256:4fc8f9f9fb33ad10ebea974fc37d0ba1a177d6603b9d9487788440cdf3e2031b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0498060716ac1841c41c3f01b83d522fdb54df9b9596d6b441d4ac3adc601cc4
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da9d5b0c3cbc91cd33520030a0bf872c9c12222a227f3391ae41adebad173e6e
3
  size 168037178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:786915ec584f3316b78fb02d9041116ff2c317cfc25d1dadec273fb1f77b012b
3
  size 168037178
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d79213b91105086d030b1e0778fbe7d6283f4c083ba909b2ec62c9e7ab91b108
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21f7eadd2da0fdaa1df31db2f7e4034feec67fc55c23f4bb989d8ad1fbdf25b1
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b610e79daca538339e134160174e96c554fad20f4a4463e6c489c0e388d47d5e
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:859887ca88f9fa64e0df0ffa0367098b179fa3861c8d451393be4c1463944f45
3
  size 14512
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": 0.023653088042049936,
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": 14.252,
103
  "eval_steps_per_second": 7.17,
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": 3329215646662656.0,
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": 0.026281208935611037,
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": 14.252,
103
  "eval_steps_per_second": 7.17,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.026281208935611037,
108
+ "grad_norm": 1.9171342849731445,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.8412,
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": 3699128496291840.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null