pythia-410m-tulu-v2-mix
This model is a fine-tuned version of EleutherAI/pythia-410m on the allenai/tulu-v2-sft-mixture dataset. It achieves the following results on the evaluation set:
- Loss: 1.2142
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: 16
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6351 | 0.9999 | 2548 | 1.4234 |
| 1.3173 | 1.9998 | 5096 | 1.2321 |
| 1.1209 | 2.9997 | 7644 | 1.2142 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.19.1