lesso commited on
Commit
1fcdc5c
1 Parent(s): ea06cb0

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 sha256:0101ccb552ae91a5ed6c63bbd673feb4f05271462a92fd4a262a7704f354cb7f
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47996c764cd985bd5c354e255b6e4826181eb315b9a695d5c105a370a73027ad
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fac4d673e351e3b51e4defdaa93875b1ed2b49ba5ca0ed4ccb6e1c4b70f3a510
3
  size 168037178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a1d49c9f2e39e8651e298e709bbced7f9a9691eb35074e551741143984c2ac2
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 sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
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": 0.007598142676234698,
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": 14.763,
103
  "eval_steps_per_second": 7.396,
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": 0.008442380751371888,
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": 14.763,
103
  "eval_steps_per_second": 7.396,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.008442380751371888,
108
+ "grad_norm": 4.914198875427246,
109
+ "learning_rate": 0.00014,
110
+ "loss": 5.7317,
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