See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 840c2df7b5557273_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/840c2df7b5557273_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    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/1807746b-c659-440c-b48c-ee5406dfff85
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: 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/840c2df7b5557273_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: </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: 0a371ad5-8fec-4245-9546-c878119ebad5
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 0a371ad5-8fec-4245-9546-c878119ebad5
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

1807746b-c659-440c-b48c-ee5406dfff85

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: 10.3552

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: 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: 20
• training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0036	1	10.3784
10.3783	0.0181	5	10.3782
10.3787	0.0363	10	10.3773
10.3763	0.0544	15	10.3756
10.3747	0.0725	20	10.3722
10.3699	0.0907	25	10.3655
10.3617	0.1088	30	10.3591
10.3586	0.1269	35	10.3564
10.356	0.1451	40	10.3555
10.3555	0.1632	45	10.3553
10.3563	0.1813	50	10.3552

Framework versions

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