quan-1.8b-base-v2

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.3.0

base_model: qnguyen3/quan-1.8b-1e
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: false

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: vilm/pretrained_baomoi_2023
    type: completion
  - path: vilm/pretrained_baomoi_2022_1
    type: completion
dataset_prepared_path: ./qwen_prepared
val_set_size: 0.00
output_dir: ./qwen-1.8b-vi

sequence_len: 4096  # supports up to 8192
sample_packing: true
pad_to_sequence_len:
wandb_project: qwen-vi-pt
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00003

train_on_input: true
group_by_length: false
bf16: true
fp16: false
tf32: false

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

warmup_steps: 100
evals_per_epoch: 0
eval_table_size:
eval_table_max_new_tokens:
saves_per_epoch: 4
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
special_tokens:
  eos_token: "<|im_end|>"
  pad_token: "<|im_end|>"

</details><br>

qwen-1.8b-vi

This model is a fine-tuned version of qnguyen3/quan-1.8b-1e 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: 3e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 1

Training results

Framework versions

• Transformers 4.37.0
• Pytorch 2.0.1+cu118
• Datasets 2.16.1
• Tokenizers 0.15.0