See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/llama-3-8b-Instruct
bf16: true
chat_template: llama3
dataloader_num_workers: 24
dataset_prepared_path: null
datasets:
- data_files:
  - 8a2a24f0cac8156c_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/8a2a24f0cac8156c_train_data.json
  type:
    field_input: input
    field_instruction: query
    field_output: output
    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: 2
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: false
group_by_length: true
hub_model_id: abaddon182/1e0ef6d2-328f-4902-81d8-01c3f9ac705d
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: 1
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_steps: 3000
micro_batch_size: 2
mlflow_experiment_name: /tmp/8a2a24f0cac8156c_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1000
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: 300
saves_per_epoch: null
sequence_len: 512
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: cbbd25ac-741b-4336-b196-9dd9694bcd33
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: cbbd25ac-741b-4336-b196-9dd9694bcd33
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

1e0ef6d2-328f-4902-81d8-01c3f9ac705d

This model is a fine-tuned version of unsloth/llama-3-8b-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7840

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 10
• training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss
1.3211	0.0002	1	1.3909
0.6119	0.0479	300	0.9019
0.5054	0.0959	600	0.8794
0.5264	0.1438	900	0.8573
0.5578	0.1917	1200	0.8368
0.4299	0.2397	1500	0.8229
0.3824	0.2876	1800	0.8077
0.3214	0.3356	2100	0.7933
0.7356	0.3835	2400	0.7884
0.2613	0.4314	2700	0.7851
0.4915	0.4794	3000	0.7840

Framework versions

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