Qwen2-finetuned / README.md
leo009's picture
Upload folder using huggingface_hub
df586a8 verified
---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: Qwen/Qwen2-7B
model-index:
- name: outputs/out
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
base_model: Qwen/Qwen2-7B
trust_remote_code: true
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: tatsu-lab/alpaca
type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/out
sequence_len: 2048
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: qlora
lora_model_dir:
lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 4
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: false
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: false
warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
special_tokens:
```
</details><br>
# outputs/out
This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 4.3265
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 10.7953 | 0.0031 | 1 | 10.8104 |
| 5.4963 | 0.2513 | 80 | 5.4101 |
| 5.0323 | 0.5026 | 160 | 5.0758 |
| 4.9877 | 0.7538 | 240 | 4.8417 |
| 4.7408 | 1.0051 | 320 | 4.6180 |
| 4.5097 | 1.2442 | 400 | 4.5066 |
| 4.3959 | 1.4955 | 480 | 4.4513 |
| 4.2488 | 1.7468 | 560 | 4.4107 |
| 4.3507 | 1.9980 | 640 | 4.3784 |
| 4.2352 | 2.2352 | 720 | 4.3684 |
| 4.2141 | 2.4865 | 800 | 4.3505 |
| 4.2739 | 2.7377 | 880 | 4.3375 |
| 4.4037 | 2.9890 | 960 | 4.3310 |
| 4.195 | 3.2269 | 1040 | 4.3287 |
| 4.1996 | 3.4782 | 1120 | 4.3268 |
| 4.1353 | 3.7295 | 1200 | 4.3265 |
### Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.1.2+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1