Hugging Face's logo

lukasgrouleff
/
shawgpt-ft

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
lukasgrouleff commited on
Commit
4f8b955
·
verified ·
1 Parent(s): 856c5b8

lukasgrouleff/shawgpt-ft-lr1e-4

Browse files
Files changed (3) hide show
  1. README.md +15 -13
  2. adapter_model.safetensors +1 -1
  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: 1.4815
20
 
21
  ## Model description
22
 
@@ -35,30 +35,32 @@ More information needed
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
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 2
45
- - num_epochs: 10
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | 3.2757 | 1.0 | 13 | 2.0919 |
53
- | 1.4655 | 2.0 | 26 | 1.2813 |
54
- | 1.083 | 3.0 | 39 | 1.2278 |
55
- | 0.955 | 4.0 | 52 | 1.2262 |
56
- | 0.8728 | 5.0 | 65 | 1.2411 |
57
- | 0.7577 | 6.0 | 78 | 1.2721 |
58
- | 0.6645 | 7.0 | 91 | 1.3039 |
59
- | 0.6134 | 8.0 | 104 | 1.4319 |
60
- | 0.5539 | 9.0 | 117 | 1.4250 |
61
- | 0.5064 | 10.0 | 130 | 1.4815 |
 
 
62
 
63
 
64
  ### 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: 1.3064
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
  - train_batch_size: 4
40
  - eval_batch_size: 4
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 2
45
+ - num_epochs: 12
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 3.6686 | 1.0 | 13 | 2.8302 |
53
+ | 2.3256 | 2.0 | 26 | 1.6927 |
54
+ | 1.3394 | 3.0 | 39 | 1.3108 |
55
+ | 1.1095 | 4.0 | 52 | 1.2532 |
56
+ | 1.0687 | 5.0 | 65 | 1.2385 |
57
+ | 0.9773 | 6.0 | 78 | 1.2419 |
58
+ | 0.9038 | 7.0 | 91 | 1.2381 |
59
+ | 0.883 | 8.0 | 104 | 1.2653 |
60
+ | 0.8353 | 9.0 | 117 | 1.2638 |
61
+ | 0.7847 | 10.0 | 130 | 1.2803 |
62
+ | 0.7793 | 11.0 | 143 | 1.3103 |
63
+ | 0.7277 | 12.0 | 156 | 1.3064 |
64
 
65
 
66
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f37c668bdb9a10cd49a1e281da9e564e5c3246d3111894d38fa83b67417389df
3
  size 13650608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f1ca2c516f486690d220c674e3c37eaee734999f4a1f4b7091b1b5140e472a3
3
  size 13650608
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:086d2c0e5102ad0aef3809c960a797cab9aa54ab34c46de47a5efe0c8c298e75
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada0e7f1784c49223a31be4084a520694c2946f79b871a485c7f21e110a0464a
3
  size 5176