mlfoundations-dev
/

code-contests-sandboxes-traces-terminus-2_seed_44

Generated from Trainer

Model card Files Files and versions

code-contests-sandboxes-traces-terminus-2_seed_44

This model is a fine-tuned version of Qwen/Qwen3-8B on the mlfoundations-dev/code-contests-sandboxes-traces-terminus-2 dataset.

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: 4e-05
train_batch_size: 1
eval_batch_size: 8
seed: 44
distributed_type: multi-GPU
num_devices: 16
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5.0

Training results

Framework versions

Transformers 4.55.0
Pytorch 2.7.0+cu128
Datasets 3.6.0
Tokenizers 0.21.1

Downloads last month: 4

Safetensors

Model size

308k params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mlfoundations-dev/code-contests-sandboxes-traces-terminus-2_seed_44

Base model

Qwen/Qwen3-8B-Base

Finetuned

Finetuned

(1642)

this model