See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2-0.5B
bf16: true
chat_template: llama3
data_processes: 54
dataset_prepared_path: null
datasets:
- data_files:
  - b973d55f42cfe085_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/b973d55f42cfe085_train_data.json
  type:
    field_input: prediction_agent
    field_instruction: id
    field_output: text
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
distributed_training:
  backend: nccl
  multi_gpu: true
  num_gpus: 2
do_eval: true
early_stopping_patience: 4
eval_batch_size: 16
eval_max_new_tokens: 128
eval_steps: 150
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp:
- full_shard
fsdp_config:
  backward_prefetch: BACKWARD_PRE
  cpu_offload: false
  forward_prefetch: false
  mixed_precision: bf16
  sharding_strategy: FULL_SHARD
  use_orig_params: true
gradient_accumulation_steps: 1
gradient_checkpointing: true
group_by_length: true
hub_ignore_patterns:
- README.md
- config.json
hub_model_id: cimol/3a48d94d-6406-4b11-a8fb-f42d50273305
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: polynomial
lr_scheduler_warmup_steps: 75
max_grad_norm: 0.5
max_memory:
  0: 75GB
  1: 75GB
max_steps: 1950
micro_batch_size: 16
mlflow_experiment_name: /tmp/b973d55f42cfe085_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  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
seed: 17333
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
total_train_batch_size: 32
train_batch_size: 32
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 0a4e6580-4386-4e34-a04e-7f6adebdf9f1
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 0a4e6580-4386-4e34-a04e-7f6adebdf9f1
warmup_steps: 150
weight_decay: 0.01
xformers_attention: null

3a48d94d-6406-4b11-a8fb-f42d50273305

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

• Loss: 2.2988

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: 16
• eval_batch_size: 16
• seed: 17333
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 32
• total_eval_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=0.95,adam_epsilon=1e-8
• lr_scheduler_type: polynomial
• lr_scheduler_warmup_steps: 150
• training_steps: 1950

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0016	1	2.6957
2.2442	0.2381	150	2.4509
2.2058	0.4762	300	2.3882
2.1434	0.7143	450	2.3595
2.0915	0.9524	600	2.3382
2.2356	1.1905	750	2.3310
2.2304	1.4286	900	2.3187
2.167	1.6667	1050	2.3100
2.1963	1.9048	1200	2.2987
2.1883	2.1429	1350	2.3045
2.2211	2.3810	1500	2.3047
2.217	2.6190	1650	2.2979
2.2194	2.8571	1800	2.2953
2.2695	3.0952	1950	2.2988

Framework versions

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