See axolotl config

axolotl version: 0.4.1

\base_model: NousResearch/Meta-Llama-3-8B-Instruct
adapter: lora
base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 5a6e8b9ebf7c1456_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/5a6e8b9ebf7c1456_train_data.json
  type:
    field_instruction: context
    field_output: question
    format: '{instruction}'
    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/d93c3772-eb60-43d0-8b31-1bd004c89ab0
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.00015
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 5
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/5a6e8b9ebf7c1456_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 2.0e-05
optimizer: adamw_torch
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: 2048
special_tokens:
  pad_token: </s>
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: 2acd1e4e-b7c7-430d-9d44-d9ef33c12168
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 2acd1e4e-b7c7-430d-9d44-d9ef33c12168
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

d93c3772-eb60-43d0-8b31-1bd004c89ab0

This model is a fine-tuned version of HuggingFaceH4/tiny-random-LlamaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.3268

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: 0.00015
• 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=0.95,adam_epsilon=2e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0005	1	10.3723
10.3731	0.0043	9	10.3706
10.369	0.0086	18	10.3637
10.3575	0.0129	27	10.3481
10.3406	0.0172	36	10.3401
10.3382	0.0215	45	10.3376
10.3358	0.0258	54	10.3354
10.3349	0.0301	63	10.3326
10.3312	0.0344	72	10.3297
10.3303	0.0387	81	10.3277
10.3274	0.0430	90	10.3269
10.3262	0.0473	99	10.3268

Framework versions

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