Hugging Face's logo

daniel40
/
c3133151-7981-4291-8afb-857d2689c894

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
daniel40 commited on
Commit
cd4ff98
·
verified ·
1 Parent(s): c5483a5

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 sha256:1a14d377cf2d200b2ce3e998588b6b7aedcae4bc0f64fe8da58d821d724fd0d7
3
  size 124756544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a239095ec8031d77767cf2fe9aaa4596302e6155e85d9bb6a1a3995e6aac642a
3
  size 124756544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35c64b77235a4577845f7b8841c11228a1643ffd4fc5b03f42b39c4310b4f1c8
3
  size 63958740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be577ff417c961cb335d8092d755806dc7de1fddde641c1eca089c5ac14a6564
3
  size 63958740
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e13e8fa1b4daf38b47a9aa5b8c83ba2ba283e5b2df40ee87829536758eb1a8d9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f3901b344b7246f2d043046e0714c92d2e14ab609c6e45212d05aad58ea3b22
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": 0.0015218769816106531,
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": 10.705,
103
  "eval_steps_per_second": 5.352,
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": 5771627908300800.0,
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": 0.0016909744240118367,
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": 10.705,
103
  "eval_steps_per_second": 5.352,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0016909744240118367,
108
+ "grad_norm": 0.3739120364189148,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.5047,
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": 6431242526392320.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null