See axolotl config

axolotl version: 0.4.1

adapter: qlora
auto_resume_from_checkpoints: true
base_model: Qwen/Qwen2.5-0.5B
bf16: auto
chat_template: llama3
dataloader_num_workers: 6
dataset_prepared_path: null
datasets:
- data_files:
  - 725b3781d264fb5d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/725b3781d264fb5d_train_data.json
  type:
    field_input: commit_message
    field_instruction: func_before
    field_output: func_after
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: true
hub_model_id: error577/019827b0-008a-464f-9a79-ff9c8c09e10e
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 128
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1000
micro_batch_size: 1
mlflow_experiment_name: /tmp/725b3781d264fb5d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 50
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.002
wandb_entity: null
wandb_mode: online
wandb_name: 3d86abba-3884-409b-8fe3-e3bede03dca5
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 3d86abba-3884-409b-8fe3-e3bede03dca5
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

019827b0-008a-464f-9a79-ff9c8c09e10e

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0191

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: 0.0003
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 10
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
0.1143	0.0001	1	0.5170
0.1187	0.0037	50	0.0280
0.0366	0.0074	100	0.0280
0.0381	0.0111	150	0.0264
0.0156	0.0148	200	0.0175
0.0214	0.0185	250	0.0237
0.0057	0.0222	300	0.0221
0.0575	0.0259	350	0.0191

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1