Merge-A-MoE/Model
Collection
A collection of danube2 models to mix and merge together.
•
13 items
•
Updated
•
1
This model was first fine-tuned with BAdam on m-a-p/CodeFeedback-Filtered-Instruction and m-a-p/Code-Feedback, unfiltered from the latest dolphin dataset, using LLama-Factory.
Thanks to mradermacher!
<|im_start|>system
You are a helpful coding assistant.<|im_end|>
<|im_start|>user
{{instruction}}<|im_end|>
<|im_start|>assistant
{{response}}<|im_end|>
System: You are a helpful coding assistant.
### model
model_name_or_path: danube2-base-chatml
### method
stage: sft
do_train: true
finetuning_type: full
use_badam: true
badam_switch_mode: ascending
badam_switch_interval: 50
badam_verbose: 1
badam_start_block: 10
seed: 720
### dataset
dataset: codefeedback_instruct_unfiltered,codefeedback_unfiltered
template: hermes_chatml
cutoff_len: 8192
overwrite_cache: false
preprocessing_num_workers: 12
### output
output_dir: code-feedback-chatml-badam
logging_steps: 5
save_steps: 1
save_strategy: epoch
plot_loss: true
overwrite_output_dir: false
### train
per_device_train_batch_size: 2
gradient_accumulation_steps: 8
learning_rate: 0.00001
num_train_epochs: 1
lr_scheduler_type: cosine
warmup_ratio: 0.01
bf16: true
flash_attn: fa2
### eval
val_size: 0.01
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 2000
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.6181 | 0.1789 | 2000 | 0.6044 |
0.6835 | 0.3578 | 4000 | 0.5949 |
0.5649 | 0.5367 | 6000 | 0.5893 |
0.6559 | 0.7155 | 8000 | 0.5850 |
0.6591 | 0.8944 | 10000 | 0.5839 |