Hugging Face's logo

vilm
/
Quyen-Mini-4e

Text Generation
Transformers
PyTorch
Safetensors
qwen2
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Quyen-Mini-4e / README.md
qnguyen3's picture
qnguyen3
Upload folder using huggingface_hub
755ec6d verified
preview code
|
raw
history blame contribute delete
2.82 kB
metadata
license: other
base_model: Qwen/Qwen2-beta-1_8B
tags:
  - generated_from_trainer
model-index:
  - name: quyen-1_8b
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: Qwen/Qwen2-beta-1_8B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

is_qwen_derived_model:
trust_remote_code:

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: teknium/OpenHermes-2.5
    type: sharegpt
    conversation: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./quyen-1_8b

sequence_len: 4096  # supports up to 8192
sample_packing: true
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

wandb_project: quyen-hermes
wandb_entity:
wandb_watch:
wandb_name: quyen-1_8b-hermes
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 8
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0001

train_on_inputs: false
group_by_length: false
bf16: true
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch:
eval_table_size:
eval_table_max_new_tokens:
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  eos_token: "<|im_end|>"
tokens:
  - "<|im_start|>"

quyen-1_8b

This model is a fine-tuned version of Qwen/Qwen2-beta-1_8B on the None 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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • 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: 4

Training results

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.16.1
  • Tokenizers 0.15.0