See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2.5-3B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 7802088fc0404c2b_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/7802088fc0404c2b_train_data.json
  type:
    field_input: group
    field_instruction: input
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: sn56a1/81f09d3b-04de-4550-92fd-5c3d6110bc8a
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 72GB
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/7802088fc0404c2b_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: false
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: 81f09d3b-04de-4550-92fd-5c3d6110bc8a
wandb_project: god
wandb_run: mz6h
wandb_runid: 81f09d3b-04de-4550-92fd-5c3d6110bc8a
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

81f09d3b-04de-4550-92fd-5c3d6110bc8a

This model is a fine-tuned version of Qwen/Qwen2.5-3B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4569

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• total_eval_batch_size: 32
• 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0004	1	0.7439
0.73	0.0020	5	0.6637
0.6281	0.0040	10	0.5600
0.5158	0.0060	15	0.5159
0.5092	0.0080	20	0.4912
0.4776	0.0100	25	0.4769
0.4738	0.0120	30	0.4677
0.4645	0.0140	35	0.4619
0.4718	0.0160	40	0.4586
0.4591	0.0180	45	0.4571
0.4592	0.0200	50	0.4569

Framework versions

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