metadata

library_name: transformers
license: mit
base_model: nisten/Biggie-SmoLlm-0.15B-Base
tags:
  - generated_from_trainer
model-index:
  - name: capybara_finetuned_results
    results: []

qwq_CoT_finetuned_results

This model is a fine-tuned version of nisten/Biggie-SmoLlm-0.15B-Base on an unknown dataset. It achieves the following results on the evaluation set:

eval_loss: 0.9331
eval_runtime: 274.7295
eval_samples_per_second: 3.64
eval_steps_per_second: 0.455
epoch: 0.1826
step: 2100

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: 6
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 12
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 30
training_steps: 3000

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.2.0
Tokenizers 0.19.1