See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Qwen2-0.5B-Instruct
bf16: auto
chat_template: llama3
cosine_min_lr_ratio: 0.1
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - a0caaa0cbf3148b6_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/a0caaa0cbf3148b6_train_data.json
  type:
    field_instruction: instruction
    field_output: output
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: '{'''':torch.cuda.current_device()}'
do_eval: true
early_stopping_patience: 30
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: 64
gradient_checkpointing: true
group_by_length: true
hub_model_id: alicegoesdown/151c116f7a
hub_repo: stevemonite
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 70GiB
max_steps: 500
micro_batch_size: 1
mlflow_experiment_name: /tmp/a0caaa0cbf3148b6_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
save_strategy: steps
sequence_len: 1028
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_project: Public_TuningSN
wandb_run: miner_id_24
wandb_runid: 1c116f7a
warmup_raio: 0.03
warmup_ratio: 0.03
weight_decay: 0.01
xformers_attention: null

151c116f7a

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

• Loss: nan

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: 64
• total_train_batch_size: 64
• 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: 15
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	0.0004	1	nan
0.0	0.0098	25	nan
0.0	0.0197	50	nan
0.0	0.0295	75	nan
0.0	0.0394	100	nan
0.0	0.0492	125	nan
0.0	0.0590	150	nan
0.0	0.0689	175	nan
0.0	0.0787	200	nan
0.0	0.0886	225	nan
0.0	0.0984	250	nan
0.0	0.1082	275	nan
0.0	0.1181	300	nan
0.0	0.1279	325	nan
0.0	0.1377	350	nan
0.0	0.1476	375	nan
0.0	0.1574	400	nan
0.0	0.1673	425	nan
0.0	0.1771	450	nan
0.0	0.1869	475	nan
0.0	0.1968	500	nan

Framework versions

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