vilm/Quyen-SE-4e

See axolotl config

axolotl version: 0.4.0

base_model: Qwen/Qwen2-beta-0_5B
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-0_5b

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-0_5b-hermes
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 8
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
max_grad_norm: 1.0
adam_beta2: 0.95
adam_epsilon: 0.00001

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-0_5b

This model is a fine-tuned version of Qwen/Qwen2-beta-0_5B 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: 0.0002
• 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=(0.9,0.95) and epsilon=1e-05
• 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