|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imdb |
|
model-index: |
|
- name: distilbert-base-uncased-finetuned-imdb-mlm-accelerate |
|
results: [] |
|
metrics: |
|
- perplexity |
|
pipeline_tag: fill-mask |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# distilbert-base-uncased-finetuned-imdb-mlm-acclerate |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset. |
|
It achieves the following results on the evaluation set: |
|
- Perplexity: 11.0482 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
Accelerate |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: AdamW with lr=5e-5 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Validation Loss | Perplexity | |
|
|:-------------------:|:-----:|:------------------:|:------------------:| |
|
| 2.657470791203201 | 1.0 | 2.462477684020996 | 11.733848321632662 | |
|
| 2.5095403741119773 | 2.0 | 2.4211950302124023 | 11.259306489817392 | |
|
| 2.4733242700054388 | 3.0 | 2.4022672176361084 | 11.048196673044224 | |
|
|
|
|
|
|
|
|
|
|
|
Run history: |
|
|
|
Perplexity █▃▁ |
|
eval/loss █▂▁▁▁ |
|
eval/runtime █▁▁▁▁ |
|
eval/samples_per_second ▁▇█▇█ |
|
eval/steps_per_second ▁▇█▇█ |
|
train/epoch ▁▁▄▅████ |
|
train/global_step ▁▃▃▆▆███████ |
|
train/learning_rate █▄▁ |
|
train/loss █▃▁ |
|
train/total_flos ▁ |
|
train/train_loss ▁ |
|
train/train_runtime ▁ |
|
train/train_samples_per_second ▁ |
|
train/train_steps_per_second ▁ |
|
|
|
Run summary: |
|
|
|
Perplexity 11.0482 |
|
eval/loss 2.41189 |
|
eval/runtime 1.923 |
|
eval/samples_per_second 520.03 |
|
eval/steps_per_second 8.32 |
|
train/epoch 3.0 |
|
train/global_step 471 |
|
train/learning_rate 0.0 |
|
train/loss 2.5354 |
|
train/total_flos 994208670720000.0 |
|
train/train_loss 2.60498 |
|
train/train_runtime 159.5259 |
|
train/train_samples_per_second 188.057 |
|
train/train_steps_per_second 2.952 |
|
|
|
|
|
View run classic-pond-2 at: https://wandb.ai/tchoud8/distilbert-base-uncased-finetuned-imdb-accelerate/runs/a7hw7i1u |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
