kanishka's picture
End of training
1008ee7
---
tags:
- generated_from_trainer
datasets:
- kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal
metrics:
- accuracy
model-index:
- name: smolm-autoreg-bpe-counterfactual-babylm-indef_articles_with_pl_nouns-removal-1e-4
results:
- task:
name: Causal Language Modeling
type: text-generation
dataset:
name: kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal
type: kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal
metrics:
- name: Accuracy
type: accuracy
value: 0.40685132585936323
---
<!-- 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-indef_articles_with_pl_nouns-removal-1e-4
This model was trained from scratch on the kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal dataset.
It achieves the following results on the evaluation set:
- Loss: 3.4203
- Accuracy: 0.4069
## 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 |
|:-------------:|:-----:|:------:|:---------------:|:--------:|
| 4.0459 | 1.0 | 18601 | 4.2512 | 0.3119 |
| 3.5647 | 2.0 | 37202 | 3.7353 | 0.3623 |
| 3.3872 | 3.0 | 55803 | 3.5881 | 0.3793 |
| 3.2888 | 4.0 | 74404 | 3.5327 | 0.3882 |
| 3.2221 | 5.0 | 93005 | 3.4746 | 0.3931 |
| 3.1699 | 6.0 | 111606 | 3.4427 | 0.3965 |
| 3.1314 | 7.0 | 130207 | 3.4235 | 0.3991 |
| 3.0928 | 8.0 | 148808 | 3.4092 | 0.4010 |
| 3.0595 | 9.0 | 167409 | 3.4074 | 0.4025 |
| 3.0344 | 10.0 | 186010 | 3.4222 | 0.4023 |
| 3.0028 | 11.0 | 204611 | 3.4034 | 0.4043 |
| 2.9831 | 12.0 | 223212 | 3.4022 | 0.4043 |
| 2.9626 | 13.0 | 241813 | 3.4060 | 0.4054 |
| 2.9442 | 14.0 | 260414 | 3.4008 | 0.4060 |
| 2.9257 | 15.0 | 279015 | 3.4016 | 0.4065 |
| 2.909 | 16.0 | 297616 | 3.4037 | 0.4065 |
| 2.8892 | 17.0 | 316217 | 3.4125 | 0.4063 |
| 2.872 | 18.0 | 334818 | 3.4132 | 0.4066 |
| 2.8568 | 19.0 | 353419 | 3.4158 | 0.4069 |
| 2.8385 | 20.0 | 372020 | 3.4203 | 0.4069 |
### Framework versions
- Transformers 4.36.0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0