|
|
--- |
|
|
base_model: unsloth/deepseek-r1-distill-qwen-14b-bnb-4bit |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- qwen2 |
|
|
- trl |
|
|
- sft |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
from trl import SFTTrainer |
|
|
from transformers import TrainingArguments |
|
|
from unsloth import is_bfloat16_supported |
|
|
|
|
|
trainer = SFTTrainer( |
|
|
model = model, |
|
|
tokenizer = tokenizer, |
|
|
train_dataset = dataset, |
|
|
dataset_text_field = "text", |
|
|
max_seq_length = max_seq_length, |
|
|
dataset_num_proc = 2, |
|
|
packing = False, # Can make training 5x faster for short sequences. |
|
|
args = TrainingArguments( |
|
|
per_device_train_batch_size = 2, |
|
|
gradient_accumulation_steps = 4, |
|
|
warmup_steps = 5, |
|
|
num_train_epochs = 1, # Set this for 1 full training run. |
|
|
max_steps = 100, |
|
|
learning_rate = 2e-4, |
|
|
fp16 = not is_bfloat16_supported(), |
|
|
bf16 = is_bfloat16_supported(), |
|
|
logging_steps = 1, |
|
|
optim = "adamw_8bit", |
|
|
weight_decay = 0.01, |
|
|
lr_scheduler_type = "linear", |
|
|
seed = 3407, |
|
|
output_dir = "outputs", |
|
|
save_strategy = "steps", |
|
|
save_steps = 60, |
|
|
report_to = "none", # Use this for WandB etc |
|
|
), |
|
|
) |
|
|
|
|
|
|
|
|
|
|
|
# Uploaded model |
|
|
|
|
|
- **Developed by:** VortexHunter23 |
|
|
- **License:** apache-2.0 |
|
|
- **Finetuned from model :** unsloth/deepseek-r1-distill-qwen-14b-bnb-4bit |
|
|
|
|
|
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
|
|
|
