Aivesa commited on
Commit
0e466f0
·
verified ·
1 Parent(s): 5b89223

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 sha256:76335c71e05c52620d37bbddc8a79a181232d4f33e33a5385b46be893a44a60e
3
  size 12609312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bfeaa4f41af9acdbcf53b7c396bb297231552ad5f5e194308eb6c4f199588cd
3
  size 12609312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7172e88647e6b42e132f888f4e66eb3e75429e4beff3f537cd2417aab063f915
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92731bd807fc4b39a192185d58a1001409036a47607dc2328a51746c39191d3c
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:c08cb012f68d5fb209b1b3dd6f8f55841816cbeb8f6f20b824d9cf9376e11d91
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131b17a7e1d00bcdb9090d8b874e017ab6a066f125e4e78db746a5292c395118
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": 0.0008361592418822874,
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,
@@ -94,6 +94,13 @@
94
  "eval_samples_per_second": 38.912,
95
  "eval_steps_per_second": 19.456,
96
  "step": 9
 
 
 
 
 
 
 
97
  }
98
  ],
99
  "logging_steps": 1,
@@ -108,12 +115,12 @@
108
  "should_evaluate": false,
109
  "should_log": false,
110
  "should_save": true,
111
- "should_training_stop": false
112
  },
113
  "attributes": {}
114
  }
115
  },
116
- "total_flos": 83342137491456.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0009290658243136526,
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,
 
94
  "eval_samples_per_second": 38.912,
95
  "eval_steps_per_second": 19.456,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0009290658243136526,
100
+ "grad_norm": 53.029144287109375,
101
+ "learning_rate": 0.0002,
102
+ "loss": 14.5572,
103
+ "step": 10
104
  }
105
  ],
106
  "logging_steps": 1,
 
115
  "should_evaluate": false,
116
  "should_log": false,
117
  "should_save": true,
118
+ "should_training_stop": true
119
  },
120
  "attributes": {}
121
  }
122
  },
123
+ "total_flos": 92114994069504.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null