See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: llamafactory/tiny-random-Llama-3
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 5d93b51dfa8d54b5_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/5d93b51dfa8d54b5_train_data.json
  type:
    field_input: context
    field_instruction: query
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: mamung/4f8eb6b0-1533-424e-8794-7043e335eeec
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: 3
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: cosine
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/5d93b51dfa8d54b5_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
special_tokens:
  pad_token: <|eot_id|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.1
wandb_entity: eddysang
wandb_mode: online
wandb_name: 226a9016-ce3e-4986-b2c2-647820c7339a
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 226a9016-ce3e-4986-b2c2-647820c7339a
warmup_steps: 50
weight_decay: 0.02
xformers_attention: false

4f8eb6b0-1533-424e-8794-7043e335eeec

This model is a fine-tuned version of llamafactory/tiny-random-Llama-3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.7469

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=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0020	1	11.7637
11.7637	0.0101	5	11.7636
11.7642	0.0202	10	11.7634
11.7617	0.0303	15	11.7630
11.7625	0.0404	20	11.7624
11.7625	0.0505	25	11.7616
11.761	0.0606	30	11.7605
11.7599	0.0707	35	11.7588
11.7583	0.0808	40	11.7562
11.7544	0.0910	45	11.7522
11.7519	0.1011	50	11.7469

Framework versions

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