See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Qwen2.5-3B-Instruct
bf16: true
chat_template: llama3
data_processes: 24
dataset_prepared_path: null
datasets:
- data_files:
  - 8297157d33aee2c5_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/8297157d33aee2c5_train_data.json
  type:
    field_input: content
    field_instruction: question
    field_output: answer
    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: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
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: cimol/876f47f3-d7a8-443f-b163-c2d3a4de2524
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
lr_scheduler_warmup_steps: 50
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 600
micro_batch_size: 8
mlflow_experiment_name: /tmp/8297157d33aee2c5_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
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: 150
saves_per_epoch: null
seed: 17333
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
total_train_batch_size: 32
train_batch_size: 8
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 25b1e79d-e9a3-44d7-afa4-81f2a04de332
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 25b1e79d-e9a3-44d7-afa4-81f2a04de332
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

876f47f3-d7a8-443f-b163-c2d3a4de2524

This model is a fine-tuned version of unsloth/Qwen2.5-3B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5158

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: 0.0002
• train_batch_size: 8
• eval_batch_size: 4
• seed: 17333
• 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=0.95,adam_epsilon=1e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 600

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0032	1	5.5330
0.6143	0.1606	50	0.6347
0.5494	0.3213	100	0.5591
0.5701	0.4819	150	0.5467
0.4572	0.6426	200	0.5309
0.4867	0.8032	250	0.5149
0.508	0.9639	300	0.5061
0.3433	1.1245	350	0.5131
0.331	1.2851	400	0.5137
0.303	1.4458	450	0.5240
0.3091	1.6064	500	0.5103
0.2648	1.7671	550	0.5158

Framework versions

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