|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: facebook/blenderbot-400M-distill |
|
model-index: |
|
- name: BlenderBot_400M_distill_falcon_redefined_first10krows |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# BlenderBot_400M_distill_falcon_redefined_first10krows |
|
|
|
This model is a fine-tuned version of [facebook/blenderbot-400M-distill](https://huggingface.co/facebook/blenderbot-400M-distill) on the first 10000 rows of the tiiuae/falcon-refinedweb dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.4093 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 3.4693 | 1.0 | 1000 | 3.4126 | |
|
| 3.4552 | 2.0 | 2000 | 3.4046 | |
|
| 3.4393 | 3.0 | 3000 | 3.4076 | |
|
| 3.4455 | 4.0 | 4000 | 3.4096 | |
|
| 3.4495 | 5.0 | 5000 | 3.4007 | |
|
| 3.4521 | 6.0 | 6000 | 3.4099 | |
|
| 3.446 | 7.0 | 7000 | 3.4107 | |
|
| 3.4383 | 8.0 | 8000 | 3.4114 | |
|
| 3.4502 | 9.0 | 9000 | 3.4115 | |
|
| 3.4472 | 10.0 | 10000 | 3.4093 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.13.0 |
|
- Tokenizers 0.13.3 |
|
|
