metadata
tags:
- generated_from_trainer
datasets:
- kanishka/babylm2-subset
metrics:
- accuracy
model-index:
- name: opt-babylm2-subset-default-3e-4
results:
- task:
name: Causal Language Modeling
type: text-generation
dataset:
name: kanishka/babylm2-subset
type: kanishka/babylm2-subset
metrics:
- name: Accuracy
type: accuracy
value: 0.5327396962492645
opt-babylm2-subset-default-3e-4
This model was trained from scratch on the kanishka/babylm2-subset dataset. It achieves the following results on the evaluation set:
- Loss: 2.3776
- Accuracy: 0.5327
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: 0.0003
- 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: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.6575 | 1.0 | 14169 | 2.8571 | 0.4750 |
| 2.4179 | 2.0 | 28338 | 2.6258 | 0.4990 |
| 2.286 | 3.0 | 42507 | 2.5088 | 0.5123 |
| 2.2124 | 4.0 | 56676 | 2.4448 | 0.5203 |
| 2.1307 | 5.0 | 70845 | 2.4099 | 0.5251 |
| 2.0706 | 6.0 | 85014 | 2.3887 | 0.5281 |
| 2.0233 | 7.0 | 99183 | 2.3779 | 0.5304 |
| 1.9727 | 8.0 | 113352 | 2.3731 | 0.5315 |
| 1.9311 | 9.0 | 127521 | 2.3728 | 0.5324 |
| 1.8943 | 10.0 | 141690 | 2.3776 | 0.5327 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.19.1