Model save
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: Qwen/Qwen2-
|
| 3 |
library_name: peft
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
|
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# output
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [Qwen/Qwen2-
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 1.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -37,27 +37,29 @@ More information needed
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
-
- learning_rate:
|
| 41 |
-
- train_batch_size:
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
-
- gradient_accumulation_steps:
|
| 45 |
- total_train_batch_size: 8
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: cosine
|
| 48 |
-
- num_epochs:
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
-
| 1.
|
|
|
|
|
|
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- PEFT 0.12.0
|
| 60 |
-
- Transformers 4.
|
| 61 |
- Pytorch 2.3.1+cu121
|
| 62 |
- Datasets 2.20.0
|
| 63 |
- Tokenizers 0.19.1
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: Qwen/Qwen2-1.5B-Instruct
|
| 3 |
library_name: peft
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
|
|
|
| 16 |
|
| 17 |
# output
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.0250
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
- total_train_batch_size: 8
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: cosine
|
| 48 |
+
- num_epochs: 3
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 1.0812 | 1.0 | 1250 | 1.0450 |
|
| 55 |
+
| 1.012 | 2.0 | 2500 | 1.0273 |
|
| 56 |
+
| 1.0175 | 3.0 | 3750 | 1.0250 |
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
- PEFT 0.12.0
|
| 62 |
+
- Transformers 4.44.0.dev0
|
| 63 |
- Pytorch 2.3.1+cu121
|
| 64 |
- Datasets 2.20.0
|
| 65 |
- Tokenizers 0.19.1
|