|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- kanishka/counterfactual-babylm-random_removal |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: smolm-autoreg-bpe-counterfactual-babylm-random_removal-1e-4 |
|
results: |
|
- task: |
|
name: Causal Language Modeling |
|
type: text-generation |
|
dataset: |
|
name: kanishka/counterfactual-babylm-random_removal |
|
type: kanishka/counterfactual-babylm-random_removal |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.40612524722144594 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# smolm-autoreg-bpe-counterfactual-babylm-random_removal-1e-4 |
|
|
|
This model was trained from scratch on the kanishka/counterfactual-babylm-random_removal dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.4340 |
|
- Accuracy: 0.4061 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 32000 |
|
- num_epochs: 20.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:------:|:---------------:|:--------:| |
|
| 4.0553 | 1.0 | 18586 | 4.2477 | 0.3104 | |
|
| 3.572 | 2.0 | 37172 | 3.7583 | 0.3622 | |
|
| 3.394 | 3.0 | 55758 | 3.5857 | 0.3796 | |
|
| 3.2886 | 4.0 | 74344 | 3.4992 | 0.3883 | |
|
| 3.2289 | 5.0 | 92930 | 3.4729 | 0.3932 | |
|
| 3.176 | 6.0 | 111516 | 3.4186 | 0.3977 | |
|
| 3.1344 | 7.0 | 130102 | 3.4150 | 0.3990 | |
|
| 3.0979 | 8.0 | 148688 | 3.4191 | 0.4009 | |
|
| 3.0701 | 9.0 | 167274 | 3.4137 | 0.4016 | |
|
| 3.0392 | 10.0 | 185860 | 3.4201 | 0.4029 | |
|
| 3.0154 | 11.0 | 204446 | 3.4057 | 0.4039 | |
|
| 2.9892 | 12.0 | 223032 | 3.4152 | 0.4046 | |
|
| 2.9688 | 13.0 | 241618 | 3.4149 | 0.4047 | |
|
| 2.9542 | 14.0 | 260204 | 3.4117 | 0.4051 | |
|
| 2.9338 | 15.0 | 278790 | 3.4235 | 0.4052 | |
|
| 2.9143 | 16.0 | 297376 | 3.4130 | 0.4059 | |
|
| 2.8967 | 17.0 | 315962 | 3.4165 | 0.4059 | |
|
| 2.8824 | 18.0 | 334548 | 3.4299 | 0.4059 | |
|
| 2.863 | 19.0 | 353134 | 3.4312 | 0.4061 | |
|
| 2.8521 | 20.0 | 371720 | 3.4340 | 0.4061 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
