Aaron Renfroe
Upload 7 files
7b174a1 verified
metadata
license: apache-2.0
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
tags:
  - generated_from_trainer
model-index:
  - name: OrcaMathTinyllama3
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0

model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

max_steps: 0

datasets:
  - path: /home/renfroe/Dev/datasets/orcamath/orcamath-input-output.json
    type:
      system_prompt: ""
      field_system: system
      field_instruction: input
      field_output: output
      format: "<|user|>\n{instruction}</s>\n<|assistant|>\n"
      no_input_format: "<|user|>\n{instruction}</s>\n<|assistant|>\n"


dataset_prepared_path:
val_set_size: 0.05
output_dir: ./OrcaMathTinyllama3

sequence_len: 2048
sample_packing: true

wandb_project: axolotl_tinyllama_orcamath
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 10
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0001

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch:
eval_table_size:
saves_per_epoch: 10
debug:
deepspeed:
weight_decay: 0.0001
fsdp:
fsdp_config:
special_tokens:

OrcaMathTinyllama3

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2366

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: 10
  • eval_batch_size: 10
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.2464 1.0 3773 0.2366

Framework versions

  • Transformers 4.40.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.18.0
  • Tokenizers 0.15.0