library_name, license, base_model, tags, model-index
| library_name | license | base_model | tags | model-index | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| transformers | other | Qwen/Qwen2.5-7B |
|
|
qwen25-7b-sft-temporal_grounding_real_6k_base
This model is a fine-tuned version of Qwen/Qwen2.5-7B on the deepseek_real_video_marathon_temporal_grounding_6k 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: 1e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Use paged_adamw_8bit 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: 8
Training results
Framework versions
- Transformers 4.53.3
- Pytorch 2.7.1+cu126
- Datasets 3.4.1
- Tokenizers 0.21.4