chatml-test-no-pad
This model is a fine-tuned version of EleutherAI/pythia-1b-deduped on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1270
- Accuracy: 0.2976
- Entropy: 1.0400
- Samples: 715
- Perplexity: 3.0862
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 99
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Entropy |
|---|---|---|---|---|---|
| 0.8981 | 1.0 | 1730 | 1.1270 | 0.2976 | 1.0400 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0-rc1
- Datasets 2.11.0
- Tokenizers 0.13.3