Hugging Face's logo

kk-aivio
/
189cee1c-0270-4877-8909-95d7c74d62fe

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
kk-aivio commited on
Commit
9cbbeef
·
verified ·
1 Parent(s): 15b378b

Training in progress, step 10, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c1a11cd4cc34c5b8dfc0eb98addad70ce80bff2b46e8d2b29678b8089f3795f
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02dbc6ebb26dd9878c174fe474685e1e92441b44de1f783961e0e2d2fb17c107
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ef046421fdbb0236b51a8bf859d85f193ae46c2c8862a3df5a14ff90713ef22
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afd6f1963e7f5af41c48aaebf553890456a04369650c66ce5eb390b5894575ca
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da36e2ea815ae653436e2a7b5a28f0ebc7cc2b234e406849f72af1785b768699
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9adb5ee314935bca3f91975cefb6876b6e167fb77efc10175a88c35427783ff
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": 0.0038115404976177872,
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": 23.805,
103
  "eval_steps_per_second": 11.915,
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": 2439690464526336.0,
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": 0.004235044997353097,
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": 23.805,
103
  "eval_steps_per_second": 11.915,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.004235044997353097,
108
+ "grad_norm": 0.37966233491897583,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.532,
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": 2744651772592128.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null