---
license: other
base_model: Qwen/Qwen1.5-MoE-A2.7B
tags:
- generated_from_trainer
model-index:
- name: out
results: []
---
[](https://github.com/OpenAccess-AI-Collective/axolotl)
See axolotl config
axolotl version: `0.4.0`
```yaml
base_model: Qwen/Qwen1.5-MoE-A2.7B
trust_remote_code: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: Drewskidang/chatlaw
type: sharegpt
- path: swag/articles_and_summaries.jsonl
ds_type: json # see other options below
type: summarizetldr
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out
sequence_len: 4096 # supports up to 32k
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
wandb_project: Qwen Qwen
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 4
num_epochs: 3
optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
```
# out
This model is a fine-tuned version of [Qwen/Qwen1.5-MoE-A2.7B](https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8947
## 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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6446 | 0.13 | 1 | 1.6456 |
| 1.639 | 0.26 | 2 | 1.3070 |
| 1.1786 | 0.52 | 4 | 1.1381 |
| 1.0398 | 0.79 | 6 | 1.0396 |
| 1.0073 | 1.02 | 8 | 1.0162 |
| 0.9318 | 1.28 | 10 | 1.0095 |
| 0.9704 | 1.54 | 12 | 0.9867 |
| 0.8477 | 1.8 | 14 | 0.9405 |
| 0.7665 | 2.03 | 16 | 0.9073 |
| 0.6283 | 2.3 | 18 | 0.9021 |
| 0.6257 | 2.56 | 20 | 0.8947 |
### Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.1.1
- Datasets 2.18.0
- Tokenizers 0.15.0