You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Built with Axolotl

See axolotl config

axolotl version: 0.6.0

base_model: Qwen/Qwen2-7B
trust_remote_code: true

strict: false

chat_template: llama3
datasets:
  - path: penfever/allenai_WildChat-1M-Full-Qwen_Qwen2.5-72B-Instruct-lc
    type: chat_template
    split: train[:32%]
    field_messages: conversation
    message_field_role: role
    message_field_content: content

dataset_prepared_path: /scratch/bf996/axolotl/datasets/wildchat-250k-qwen25-72b-lc
val_set_size: 0.02
output_dir: /scratch/bf996/axolotl/outputs/qwen-2-7b-wildchat-250k-qwen25-72b-lc

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

wandb_project: lm-evals
wandb_entity:
wandb_watch:
wandb_name: qwen-2-7b-WildChat-qwen25-72b-lc
wandb_log_model:
hub_model_id: penfever/qwen-2-7b-WildChat-250k-qwen25-72b-lc

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 0
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|eot_id|>
  bos_token: <|begin_of_text|>

qwen-2-7b-WildChat-250k-qwen25-72b-lc

This model is a fine-tuned version of Qwen/Qwen2-7B on the penfever/allenai_WildChat-1M-Full-Qwen_Qwen2.5-72B-Instruct-lc dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8092

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: 2e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • total_eval_batch_size: 4
  • optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.8721 0.9997 3179 0.8092

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.21.0
Downloads last month
5
Safetensors
Model size
7.62B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for nyu-dice-lab/qwen-2-7b-WildChat-250k-qwen25-72b-lc

Base model

Qwen/Qwen2-7B
Finetuned
(58)
this model

Dataset used to train nyu-dice-lab/qwen-2-7b-WildChat-250k-qwen25-72b-lc

Collection including nyu-dice-lab/qwen-2-7b-WildChat-250k-qwen25-72b-lc