Grogros-dmWM-llama-3.2-1B-In-OWTWM-DW-Al4-wmToken-d4-a0.1-v2-meta-OWT-LA-ext
This model is a fine-tuned version of Grogros/dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-Al4-wmToken-d4-a0.1-v2-meta-OWT on the openwebtext 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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 10000
Training results
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1.post303
- Datasets 3.2.0
- Tokenizers 0.20.3
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Grogros/Grogros-dmWM-llama-3.2-1B-In-OWTWM-DW-Al4-wmToken-d4-a0.1-v2-meta-OWT-LA-ext
Base model
meta-llama/Llama-3.2-1B-Instruct