Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2.5-Math-7B-Instruct
bf16: auto
chat_template: llama3
cosine_min_lr_ratio: 0.1
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - a107d281103d6e55_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/a107d281103d6e55_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: response
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 1
eval_batch_size: 1
eval_sample_packing: false
eval_steps: 25
evaluation_strategy: steps
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: true
hub_model_id: dada22231/e6e0f21e-0601-4c84-8936-07618d5f356d
hub_strategy: checkpoint
hub_token: null
hub_username: dada22231
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 70GiB
  1: 70GiB
  2: 70GiB
  3: 70GiB
max_steps: 200
micro_batch_size: 1
mlflow_experiment_name: /tmp/a107d281103d6e55_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
repository_id: dada22231/e6e0f21e-0601-4c84-8936-07618d5f356d
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 25
save_strategy: steps
sequence_len: 2048
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: false
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: null
wandb_mode: online
wandb_name: e6e0f21e-0601-4c84-8936-07618d5f356d
wandb_project: Public_TuningSN
wandb_runid: e6e0f21e-0601-4c84-8936-07618d5f356d
warmup_ratio: 0.04
weight_decay: 0.01
xformers_attention: null

e6e0f21e-0601-4c84-8936-07618d5f356d

This model is a fine-tuned version of Qwen/Qwen2.5-Math-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0016

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: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 128
  • total_eval_batch_size: 4
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 8
  • training_steps: 200

Training results

Training Loss Epoch Step Validation Loss
4.5908 0.0049 1 4.4578
0.0336 0.1222 25 0.0820
0.0197 0.2443 50 0.0342
0.0037 0.3665 75 0.0191
0.004 0.4887 100 0.0107
0.0012 0.6109 125 0.0037
0.0015 0.7330 150 0.0021
0.0006 0.8552 175 0.0020
0.0003 0.9774 200 0.0016

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1
Downloads last month
21
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for dada22231/e6e0f21e-0601-4c84-8936-07618d5f356d

Base model

Qwen/Qwen2.5-7B
Adapter
(74)
this model