|
--- |
|
{} |
|
--- |
|
## Run info |
|
- complete_hash: b97998c098e0d34fa00d918d670b8f9b |
|
- short_hash: b9799b8f9b |
|
|
|
### Configuration |
|
```yaml |
|
data: |
|
batch_size: 32 |
|
data_seed: 42 |
|
drop_last: false |
|
eval_batch_size: 128 |
|
max_length: 512 |
|
multiprocessing_context: null |
|
num_workers: 8 |
|
persistent_workers: false |
|
pin_memory: true |
|
replacement: false |
|
shuffle: true |
|
dataset: mnli |
|
estimator: |
|
accelerator: gpu |
|
convert_to_bettertransformer: false |
|
deterministic: true |
|
precision: bf16-true |
|
tf32_mode: high |
|
fit: |
|
enable_progress_bar: true |
|
limit_train_batches: null |
|
log_interval: 100 |
|
max_epochs: 20 |
|
min_epochs: null |
|
optimizer_kwargs: |
|
init_kwargs: |
|
fused: true |
|
lr: 3.0e-05 |
|
name: adamw |
|
scheduler_kwargs: |
|
name: constant_schedule_with_warmup |
|
num_warmup_steps: 2000 |
|
model: |
|
base_model: roberta-base |
|
name: roberta-base |
|
revision: null |
|
seed: 42 |
|
seed: 42 |
|
``` |
