8b62df5c9e
Model: penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k Source: Original Platform
1.5 KiB
1.5 KiB
library_name, license, base_model, tags, model-index
| library_name | license | base_model | tags | model-index | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| transformers | apache-2.0 | Qwen/Qwen3-8B |
|
|
kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k
This model is a fine-tuned version of Qwen/Qwen3-8B on the penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k 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: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7.0
Training results
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1