Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/tinyllama
batch_size: 8
bf16: true
chat_template: tokenizer_default_fallback_alpaca
datasets:
- data_files:
  - fced0da711a452c4_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/fced0da711a452c4_train_data.json
  type:
    field_instruction: question_body
    field_output: question_title
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
early_stopping_patience: 3
eval_steps: 50
flash_attention: true
gpu_memory_limit: 80GiB
gradient_checkpointing: true
group_by_length: true
hub_model_id: willtensora/dc78143d-f969-489f-b5a3-33391bf2b1e6
hub_strategy: checkpoint
learning_rate: 0.0002
logging_steps: 10
lora_alpha: 256
lora_dropout: 0.1
lora_r: 128
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 1
model_type: AutoModelForCausalLM
num_epochs: 100
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resize_token_embeddings_to_32x: false
sample_packing: false
save_steps: 50
sequence_len: 2048
tokenizer_type: LlamaTokenizerFast
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.1
wandb_entity: ''
wandb_mode: online
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: default
warmup_ratio: 0.05
xformers_attention: true

dc78143d-f969-489f-b5a3-33391bf2b1e6

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

  • Loss: 1.3469

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: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • total_train_batch_size: 8
  • total_eval_batch_size: 8
  • 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: 335
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss
No log 0.0019 1 3.1687
1.4763 0.0931 50 1.4450
1.3149 0.1862 100 1.3312
1.3618 0.2793 150 1.3268
1.396 0.3724 200 1.3320
1.4143 0.4655 250 1.3690
1.3715 0.5587 300 1.3469

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1
Downloads last month
8
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for willtensora/dc78143d-f969-489f-b5a3-33391bf2b1e6

Base model

unsloth/tinyllama
Adapter
(165)
this model