See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: Qwen/Qwen2.5-14B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 7359c40382c08bf9_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/7359c40382c08bf9_train_data.json
  type:
    field_input: context
    field_instruction: question-X
    field_output: answer-Y
    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
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: true
hub_model_id: tuantmdev/1acaa5ed-f1dd-4c1b-b40b-0f774bb7c650
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 1e-4
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 40
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 400
micro_batch_size: 2
mlflow_experiment_name: /tmp/7359c40382c08bf9_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
save_strategy: steps
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 9173758c-9745-461f-a3fa-d63d546c9e6c
wandb_project: Gradients-On-Demand
wandb_run: unknown
wandb_runid: 9173758c-9745-461f-a3fa-d63d546c9e6c
warmup_steps: 80
weight_decay: 0.0
xformers_attention: null

1acaa5ed-f1dd-4c1b-b40b-0f774bb7c650

This model is a fine-tuned version of Qwen/Qwen2.5-14B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.6737

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• 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: 80
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0005	1	8.6257
5.1663	0.0249	50	1.9987
1.8545	0.0499	100	1.8953
1.7926	0.0748	150	1.7953
1.7122	0.0998	200	1.8293
1.7755	0.1247	250	1.7229
1.7366	0.1496	300	1.6872
1.6637	0.1746	350	1.6792
1.6578	0.1995	400	1.6737

Framework versions

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