Hugging Face's logo

musr
/
usgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
musr commited on
Commit
6a9da55
·
verified ·
1 Parent(s): afeb30e

musr/usssgpt-ft

Browse files
Files changed (4) hide show
  1. README.md +48 -20
  2. adapter_model.safetensors +1 -1
  3. runs/Feb05_13-38-01_a25d9d7f004d/events.out.tfevents.1738762747.a25d9d7f004d.2450.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -35,32 +35,60 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0001
39
- - train_batch_size: 8
40
- - eval_batch_size: 8
41
  - seed: 42
42
  - gradient_accumulation_steps: 4
43
- - total_train_batch_size: 32
44
- - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
- - lr_scheduler_type: cosine
46
- - lr_scheduler_warmup_ratio: 0.1
47
- - num_epochs: 10
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:------:|:----:|:---------------:|
54
- | 23.7335 | 0.5714 | 1 | 11.9321 |
55
- | 23.7344 | 1.5714 | 2 | 11.9321 |
56
- | 23.7394 | 2.5714 | 3 | 11.9321 |
57
- | 23.7366 | 3.5714 | 4 | 11.9321 |
58
- | 23.7318 | 4.5714 | 5 | 11.9321 |
59
- | 23.7391 | 5.5714 | 6 | 11.9321 |
60
- | 23.738 | 6.5714 | 7 | 11.9321 |
61
- | 23.7316 | 7.5714 | 8 | 11.9321 |
62
- | 23.7385 | 8.5714 | 9 | 11.9321 |
63
- | 11.8708 | 9.5714 | 10 | 11.9321 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0002
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
  - seed: 42
42
  - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 16
44
+ - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 2
47
+ - num_epochs: 50
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-------:|:----:|:---------------:|
54
+ | 11.8582 | 1.0 | 4 | 11.9321 |
55
+ | 11.857 | 2.0 | 8 | 11.9321 |
56
+ | 11.8625 | 3.0 | 12 | 11.9321 |
57
+ | 11.8615 | 4.0 | 16 | 11.9321 |
58
+ | 11.8576 | 5.0 | 20 | 11.9321 |
59
+ | 11.8603 | 6.0 | 24 | 11.9321 |
60
+ | 11.8671 | 7.0 | 28 | 11.9321 |
61
+ | 11.8587 | 8.0 | 32 | 11.9321 |
62
+ | 11.8577 | 9.0 | 36 | 11.9321 |
63
+ | 11.8578 | 10.0 | 40 | 11.9321 |
64
+ | 11.866 | 11.0 | 44 | 11.9321 |
65
+ | 11.8586 | 12.0 | 48 | 11.9321 |
66
+ | 11.8643 | 13.0 | 52 | 11.9321 |
67
+ | 11.8563 | 14.0 | 56 | 11.9321 |
68
+ | 11.8659 | 15.0 | 60 | 11.9321 |
69
+ | 11.8603 | 16.0 | 64 | 11.9321 |
70
+ | 11.8641 | 17.0 | 68 | 11.9321 |
71
+ | 11.8656 | 18.0 | 72 | 11.9321 |
72
+ | 11.8591 | 19.0 | 76 | 11.9321 |
73
+ | 11.8576 | 20.0 | 80 | 11.9321 |
74
+ | 11.8685 | 21.0 | 84 | 11.9321 |
75
+ | 11.8668 | 22.0 | 88 | 11.9321 |
76
+ | 11.8662 | 23.0 | 92 | 11.9321 |
77
+ | 11.8658 | 24.0 | 96 | 11.9321 |
78
+ | 11.869 | 25.0 | 100 | 11.9321 |
79
+ | 11.8656 | 26.0 | 104 | 11.9321 |
80
+ | 11.8581 | 27.0 | 108 | 11.9321 |
81
+ | 11.8575 | 28.0 | 112 | 11.9321 |
82
+ | 11.8587 | 29.0 | 116 | 11.9321 |
83
+ | 11.8571 | 30.0 | 120 | 11.9321 |
84
+ | 11.8612 | 31.0 | 124 | 11.9321 |
85
+ | 11.8662 | 32.0 | 128 | 11.9321 |
86
+ | 11.8636 | 33.0 | 132 | 11.9321 |
87
+ | 11.8593 | 34.0 | 136 | 11.9321 |
88
+ | 11.8571 | 35.0 | 140 | 11.9321 |
89
+ | 11.8644 | 36.0 | 144 | 11.9321 |
90
+ | 11.8594 | 37.0 | 148 | 11.9321 |
91
+ | 11.8645 | 37.6154 | 150 | 11.9321 |
92
 
93
 
94
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d5c3c9a8101c83e451c705c261cbdfc1a3b74214138d3aa59bce884b50165ff
3
  size 6429920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f2ffe3c13c4a1349c34fa1992739012de270ba0aa03ee1b1855e8d1be1670f
3
  size 6429920
runs/Feb05_13-38-01_a25d9d7f004d/events.out.tfevents.1738762747.a25d9d7f004d.2450.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:046d0aac28b53b761dbd0a66b9db580e87a9ece15afe05fabb8782b8e56fdc61
3
+ size 23663
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5fb3dbcc6128e98d4088a963ad28b3b480f8f7ab8ca0273575d1dd22698c1d8
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba4ca5f3fcad30fa407ba781ee45b9eb82f2b570e07ffbe8a0a4856b6bc459dd
3
  size 5304