See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: Qwen/Qwen2-0.5B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 885d04d2490f6ef8_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/885d04d2490f6ef8_train_data.json
  type:
    field_input: Example
    field_instruction: '@partOfSpeech'
    field_output: Definition
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 50
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
group_by_length: true
hub_model_id: lesso13/d38711e6-f83f-405c-8f78-fca499dcc4fe
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000213
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 500
micro_batch_size: 4
mlflow_experiment_name: /tmp/885d04d2490f6ef8_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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
saves_per_epoch: null
seed: 130
sequence_len: 512
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 36a8de66-ecec-4b15-ab19-b5863b4c1a11
wandb_project: 13a
wandb_run: your_name
wandb_runid: 36a8de66-ecec-4b15-ab19-b5863b4c1a11
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

d38711e6-f83f-405c-8f78-fca499dcc4fe

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

• Loss: 3.3096

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: 0.000213
• train_batch_size: 4
• eval_batch_size: 4
• seed: 130
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	6.4931
4.4182	0.0035	50	4.7229
4.1223	0.0070	100	4.2444
4.3057	0.0105	150	4.0504
3.7327	0.0140	200	3.8524
3.7738	0.0175	250	3.6954
3.9019	0.0211	300	3.4901
3.6586	0.0246	350	3.3937
3.9927	0.0281	400	3.3199
4.129	0.0316	450	3.3102
3.8922	0.0351	500	3.3096

Framework versions

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