kostiantynk commited on
Commit
8fb347f
·
verified ·
1 Parent(s): 47e0af3

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 sha256:3be5e10aa1b2c1d0dee952b1a3a7e3acf14f3926f6b77fffbcc7417bd28b1051
3
  size 12609416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58ee7af99b603d2ea6eae5e6816ffd04488b3b4cb51b16d0bb11fa6175b5b7ee
3
  size 12609416
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea1f094629876a9b37c0f3038bca97b09cf258daaa72dab4bba3e36d0e93abfb
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d68d8fc4e3f6eb12c1d89e91eaafd38aa03c39f287b2c56b0589fb1132ddf6
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37a1d57dcf6d6a809cbd33f03ec44415e52213e48cac682f33531386d9556ac5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6279e2d6d30b2ce7f2189e648e383ab146d51fb0fecf44d1e16d05504562e6f8
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": 0.008959681433549029,
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": 31.123,
103
  "eval_steps_per_second": 15.598,
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": 67562687692800.0,
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": 0.009955201592832254,
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": 31.123,
103
  "eval_steps_per_second": 15.598,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.009955201592832254,
108
+ "grad_norm": 6.100696086883545,
109
+ "learning_rate": 0.0002,
110
+ "loss": 10.7305,
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": 75069652992000.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null