Modelpublic

AnatolyCat/Russian-Memolog-Qwen

sourceHugging Faceapache-2.0updated 6mo agoView on Hugging Face

0likes4downloads

Model Card

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>

axolotl version: 0.16.0.dev0

yaml

base_model: Qwen/Qwen2.5-1.5B
tokenizer_config: Qwen/Qwen2.5-1.5B
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: memes_alpaca.jsonl
  ds_type: json
  type: alpaca
dataset_prepared_path: null
val_set_size: 0.05
output_dir: ./memolog-out
adapter: qlora
lora_model_dir: null
sequence_len: 1096
sample_packing: true
pad_to_sequence_len: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 4
max_steps: 20
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: false
fp16: true
tf32: false
gradient_checkpointing: true
logging_steps: 1
flash_attention: false
warmup_steps: 10
weight_decay: 0.0

</details><br>

memolog-out

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B on the memes_alpaca.jsonl dataset.

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
—trainbatchsize: 1
—evalbatchsize: 1
—seed: 42
—optimizer: Use OptimizerNames.PAGEDADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: cosine
—lrschedulerwarmup_steps: 10
—training_steps: 20
—mixedprecisiontraining: Native AMP

Training results

Framework versions

—PEFT 0.18.1
—Transformers 5.3.0
—Pytorch 2.8.0+cu128
—Datasets 4.5.0
—Tokenizers 0.22.2