nblinh commited on
Commit
af2a796
1 Parent(s): 1028d11

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:d659ca35eb5a657687ae7553515882c754653f737128f2e7a48c242ed0415a44
3
  size 101752088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfac046940791f65e909ffea4add299d5ce3528a1f3c18ff6202da2899f4b506
3
  size 101752088
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35d85d4d6843816035b7f1c17007f3f15c7d5a277246448192d191ac66ef1aa0
3
  size 52046596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f0370603d9c727923ea0131621060111394903a01968a6e64090418eda5fb37
3
  size 52046596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d667d834c40be4f29c0c338bfb48af43a7c6e83e4b812ca94a4a148c58b863d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f2aaa3af6c2c926396cb6c23e08f3110a050760bf02a9e4ae16a8642653feb
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": 0.0006896155393368198,
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": 5.876,
103
  "eval_steps_per_second": 2.939,
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": 2963422807326720.0,
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": 0.0007662394881520219,
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": 5.876,
103
  "eval_steps_per_second": 2.939,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0007662394881520219,
108
+ "grad_norm": 0.6949341297149658,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.0878,
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": 3292692008140800.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null