See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2.5-0.5B
bf16: true
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
  - 2bb581dcf15d60f2_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2bb581dcf15d60f2_train_data.json
  type:
    field_instruction: tools
    field_output: mock_functions
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 8
eval_max_new_tokens: 128
eval_steps: 200
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: abaddon182/b282f0d5-020a-4358-9db6-e667e9cf5fdb
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 64
lora_dropout: 0.1
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: 2000
micro_batch_size: 8
mlflow_experiment_name: /tmp/2bb581dcf15d60f2_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-8
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: 200
saves_per_epoch: null
sequence_len: 1024
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: 84fb94ea-2573-4b3b-8ea8-2f19c4cc56f1
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 84fb94ea-2573-4b3b-8ea8-2f19c4cc56f1
warmup_steps: 100
weight_decay: 0.1
xformers_attention: null

b282f0d5-020a-4358-9db6-e667e9cf5fdb

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: 0.2526

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-8
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0021	1	0.6320
0.3445	0.4175	200	0.3037
0.3143	0.8351	400	0.2808
0.2664	1.2526	600	0.2690
0.2544	1.6701	800	0.2594
0.2288	2.0877	1000	0.2581
0.2191	2.5052	1200	0.2534
0.221	2.9228	1400	0.2487
0.1766	3.3403	1600	0.2558
0.1655	3.7578	1800	0.2524
0.1845	4.1754	2000	0.2526

Framework versions

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