See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2-0.5B-Instruct
bf16: true
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
  - ef276d365b7b60ca_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/ef276d365b7b60ca_train_data.json
  type:
    field_input: topic_3
    field_instruction: topic_1
    field_output: text
    format: '{instruction} {input}'
    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: 300
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: nttx/73736fa7-0a64-4a3f-88d8-7b691bba9c6d
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 3e-5
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 3000
micro_batch_size: 8
mlflow_experiment_name: /tmp/ef276d365b7b60ca_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 100
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-8
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: 300
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: 25189865-2807-4bf3-9461-9dc1ee3613fe
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 25189865-2807-4bf3-9461-9dc1ee3613fe
warmup_steps: 50
weight_decay: 0.1
xformers_attention: null

73736fa7-0a64-4a3f-88d8-7b691bba9c6d

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: 2.7537

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-8
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0003	1	2.8476
3.0603	0.1021	300	2.7802
3.0276	0.2041	600	2.7688
2.9262	0.3062	900	2.7622
2.9139	0.4083	1200	2.7594
3.014	0.5103	1500	2.7566
2.9849	0.6124	1800	2.7551
2.9459	0.7145	2100	2.7552
2.9851	0.8165	2400	2.7530
2.9972	0.9186	2700	2.7533
2.7404	1.0207	3000	2.7537

Framework versions

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