metadata
base_model: facebook/mbart-large-50-many-to-many-mmt
tags:
- generated_from_trainer
model-index:
- name: mbart-large-50-many-to-many-mmt-finetuned-human-to-assistant
results: []
mbart-large-50-many-to-many-mmt-finetuned-human-to-assistant
This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8285
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 16 | 0.8667 |
| No log | 2.0 | 32 | 0.7968 |
| No log | 3.0 | 48 | 0.8283 |
| No log | 4.0 | 64 | 0.8198 |
| No log | 5.0 | 80 | 0.8298 |
| No log | 6.0 | 96 | 0.8322 |
| No log | 7.0 | 112 | 0.8368 |
| No log | 8.0 | 128 | 0.8324 |
| No log | 9.0 | 144 | 0.8295 |
| No log | 10.0 | 160 | 0.8285 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1