Hugging Face's logo

FrederikKlinkby
/
shawgpt-ft-rank15

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
FrederikKlinkby commited on
Commit
6cad9f8
•
1 Parent(s): 511e251

shawgpt-ft-rank15

Browse files
Files changed (3) hide show
  1. README.md +16 -14
  2. runs/Oct22_10-55-18_99867d27916d/events.out.tfevents.1729594518.99867d27916d.882.47 +3 -0
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.4906
20
 
21
  ## Model description
22
 
@@ -44,25 +44,27 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 2
47
- - num_epochs: 12
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
- | 4.5923 | 0.9231 | 3 | 3.9658 |
55
- | 4.0441 | 1.8462 | 6 | 3.4365 |
56
- | 3.451 | 2.7692 | 9 | 2.9600 |
57
- | 2.2208 | 4.0 | 13 | 2.4960 |
58
- | 2.5836 | 4.9231 | 16 | 2.2153 |
59
- | 2.2284 | 5.8462 | 19 | 1.9993 |
60
- | 1.9357 | 6.7692 | 22 | 1.7904 |
61
- | 1.3278 | 8.0 | 26 | 1.6449 |
62
- | 1.6406 | 8.9231 | 29 | 1.5613 |
63
- | 1.5307 | 9.8462 | 32 | 1.5156 |
64
- | 1.5151 | 10.7692 | 35 | 1.4931 |
65
- | 0.2742 | 11.0769 | 36 | 1.4906 |
 
 
66
 
67
 
68
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.3663
20
 
21
  ## Model description
22
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 2
47
+ - num_epochs: 15
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
+ | 4.5909 | 0.9231 | 3 | 3.9607 |
55
+ | 4.0305 | 1.8462 | 6 | 3.4190 |
56
+ | 3.4227 | 2.7692 | 9 | 2.9340 |
57
+ | 2.2008 | 4.0 | 13 | 2.4790 |
58
+ | 2.5483 | 4.9231 | 16 | 2.1770 |
59
+ | 2.1551 | 5.8462 | 19 | 1.9264 |
60
+ | 1.8321 | 6.7692 | 22 | 1.7147 |
61
+ | 1.2386 | 8.0 | 26 | 1.5355 |
62
+ | 1.4952 | 8.9231 | 29 | 1.4535 |
63
+ | 1.3923 | 9.8462 | 32 | 1.4129 |
64
+ | 1.3843 | 10.7692 | 35 | 1.3921 |
65
+ | 0.9917 | 12.0 | 39 | 1.3751 |
66
+ | 1.3332 | 12.9231 | 42 | 1.3687 |
67
+ | 1.1067 | 13.8462 | 45 | 1.3663 |
68
 
69
 
70
  ### Framework versions
runs/Oct22_10-55-18_99867d27916d/events.out.tfevents.1729594518.99867d27916d.882.47 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e280f766d647eb9ff21043a19a9b648c8c3b97c26c95b2cb0b7037368365b7
3
+ size 12573
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe2bd0787ce2d2c3bae22e838f391bf15e085d1ecb681083acb22ebedbc2fb38
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:997157d142991aa78774e8182a1da5eaaafed179f219a2d23230373db795e035
3
  size 5176