Hugging Face's logo

Aivesa
/
c54c306a-c851-4242-bb27-3011d64be847

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
Aivesa commited on
Commit
cee1d64
·
verified ·
1 Parent(s): f8493a3

Training in progress, step 9, 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 +32 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bed9427e2f9dae010f4e35d28da841f018dcba59f445f6f5b6af01d85382297
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e52147b7c4310f3867538ce9b14976e1adcf4a0cf758b0b865e2ab4a9c1a564
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85eed6a74290c260e4bbaf6f95d1a68383ea7ec6c69ed8417a50fe0f4901bf5f
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b587c888e529415eb35ba74af8314cc97381b89fb5fe4d5c524076afd3cf14a1
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ea8f278f29641100a56e280ef65934b0fccc8f8d9851be121c701ebed8ce795
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df170cb6acde393f26f26d8b291e01ba34281d10b477edb2225f4b80d02e472
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.002711558016043385,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 19.995,
66
  "eval_steps_per_second": 9.998,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 1211154432.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.004067337024065077,
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,
 
65
  "eval_samples_per_second": 19.995,
66
  "eval_steps_per_second": 9.998,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.003163484352050616,
71
+ "grad_norm": 0.058283086866140366,
72
+ "learning_rate": 0.00014,
73
+ "loss": 11.9479,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.0036154106880578467,
78
+ "grad_norm": 0.05091653764247894,
79
+ "learning_rate": 0.00016,
80
+ "loss": 11.9463,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.004067337024065077,
85
+ "grad_norm": 0.058415722101926804,
86
+ "learning_rate": 0.00018,
87
+ "loss": 11.9488,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.004067337024065077,
92
+ "eval_loss": 11.947492599487305,
93
+ "eval_runtime": 46.5754,
94
+ "eval_samples_per_second": 20.011,
95
+ "eval_steps_per_second": 10.005,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 1861042176.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null