Hugging Face's logo

swkong
/
Adapter-Phi-3-medium-128k-instruct-lora-hrdx-gptq

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
 Community
swkong commited on
Commit
1d51a82
·
verified ·
1 Parent(s): 8882482

Model save

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.4620
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 1e-05
41
  - train_batch_size: 32
42
  - eval_batch_size: 32
43
  - seed: 42
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
- | No log | 1.4023 | 30 | 2.5073 |
56
- | No log | 2.8046 | 60 | 2.4822 |
57
- | No log | 4.2299 | 90 | 2.4620 |
58
 
59
 
60
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.0599
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
  - train_batch_size: 32
42
  - eval_batch_size: 32
43
  - seed: 42
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
+ | No log | 1.4023 | 30 | 2.3764 |
56
+ | No log | 2.8046 | 60 | 2.1774 |
57
+ | No log | 4.2299 | 90 | 2.0599 |
58
 
59
 
60
  ### Framework versions