See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/tinyllama
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 9d6479db12ebe5de_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/9d6479db12ebe5de_train_data.json
  type:
    field_instruction: doc_text
    field_output: sentence
    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/b1635cb9-5f86-41a5-8fd9-a45c711b452a
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/9d6479db12ebe5de_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: 1024
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: 2346e438-0b42-4959-aa36-1d3d813fa606
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 2346e438-0b42-4959-aa36-1d3d813fa606
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

b1635cb9-5f86-41a5-8fd9-a45c711b452a

This model is a fine-tuned version of unsloth/tinyllama on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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	0.0118	1	nan
0.0	0.1059	9	nan
0.0	0.2118	18	nan
0.0	0.3176	27	nan
0.0	0.4235	36	nan
0.0	0.5294	45	nan
0.0	0.6353	54	nan
0.0	0.7412	63	nan
0.0	0.8471	72	nan
0.0	0.9529	81	nan
0.0	1.0588	90	nan
0.0	1.1647	99	nan

Framework versions

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