|
[2024-03-04 17:34:08,795][hydra][INFO] - |
|
estimator: |
|
accelerator: gpu |
|
precision: bf16-true |
|
deterministic: true |
|
tf32_mode: high |
|
convert_to_bettertransformer: false |
|
callbacks: |
|
timer: |
|
_target_: energizer.active_learning.callbacks.Timer |
|
lr_monitor: |
|
_target_: energizer.callbacks.lr_monitor.LearningRateMonitor |
|
model_checkpoint: |
|
_target_: energizer.callbacks.model_checkpoint.ModelCheckpoint |
|
dirpath: .checkpoints |
|
stage: train |
|
frequency: 1:epoch |
|
loggers: |
|
tensorboard: |
|
_target_: energizer.loggers.TensorBoardLogger |
|
root_dir: ./ |
|
name: tb_logs |
|
version: null |
|
data: |
|
batch_size: 32 |
|
eval_batch_size: 128 |
|
shuffle: true |
|
replacement: false |
|
data_seed: 42 |
|
drop_last: false |
|
num_workers: 8 |
|
pin_memory: true |
|
persistent_workers: false |
|
multiprocessing_context: null |
|
max_length: 512 |
|
fit: |
|
max_epochs: 20 |
|
optimizer_kwargs: |
|
name: adamw |
|
lr: 3.0e-05 |
|
init_kwargs: |
|
fused: true |
|
scheduler_kwargs: |
|
name: constant_schedule_with_warmup |
|
num_warmup_steps: 2000 |
|
log_interval: 100 |
|
enable_progress_bar: true |
|
limit_train_batches: null |
|
limit_validation_batches: null |
|
model: |
|
name: bert-tiny |
|
revision: null |
|
seed: 42 |
|
log_interval: 100 |
|
enable_progress_bar: true |
|
limit_batches: null |
|
seed: 42 |
|
experiment_group: training |
|
run_name: bert-tiny_2024-03-04T17-34-08 |
|
data_path: /home/pl487/coreset-project/data/processed |
|
dataset: mnli |
|
|
|
====================================================================== |
|
[2024-03-04 17:34:08,796][hydra][INFO] - Seed enabled: 42 |
|
[2024-03-04 17:34:09,910][hydra][INFO] - Label distribution: |
|
{<RunningStage.TRAIN: 'train'>: {'0-(entailment)': 130899, '1-(neutral)': 130900, '2-(contradiction)': 130903}} |
|
[2024-03-04 17:34:21,700][hydra][INFO] - Loggers: [<energizer.loggers.tensorboard.TensorBoardLogger object at 0x7f79509062f0>] |
|
[2024-03-04 17:34:21,700][hydra][INFO] - Callbacks: [<energizer.active_learning.callbacks.Timer object at 0x7f792e9ecfd0>, <energizer.callbacks.lr_monitor.LearningRateMonitor object at 0x7f792e9ed030>, <energizer.callbacks.model_checkpoint.ModelCheckpoint object at 0x7f792e9ed540>] |
|
[2024-03-04 17:34:21,702][hydra][INFO] - Model summary: |
|
Total num params: 4.4M |
|
Of which trainable: 4.4M |
|
With a memory footprint of 0.01GB |
|
Total memory allocated 0.03GB |
|
[2024-03-04 17:34:21,702][hydra][INFO] - Dataloading params: |
|
SequenceClassificationDataloaderArgs(batch_size=32, eval_batch_size=128, num_workers=8, pin_memory=True, drop_last=False, persistent_workers=False, shuffle=True, replacement=False, data_seed=42, multiprocessing_context=None, max_length=512) |
|
[2024-03-04 17:34:21,737][hydra][INFO] - Batch: |
|
{<InputKeys.INPUT_IDS: 'input_ids'>: tensor([[ 101, 2092, 7910, 2008, 1005, 1055, 2785, 1997, 5793, 1045, |
|
2812, 2027, 1005, 2128, 2130, 4755, 2009, 2000, 2000, 2073, |
|
2085, 7910, 2008, 2027, 4748, 16874, 5562, 2006, 2694, 2017, |
|
2113, 2065, 2115, 2065, 2017, 7910, 2017, 2113, 2031, 2589, |
|
2023, 2030, 2065, 2017, 2342, 2023, 7910, 7910, 2057, 1005, |
|
2222, 9790, 2005, 2017, 1998, 2017, 2123, 1005, 1056, 2031, |
|
2000, 3477, 2149, 4983, 2017, 2021, 2059, 2054, 2027, 2123, |
|
1005, 1056, 2425, 2017, 2003, 2008, 2065, 2017, 2065, 2027, |
|
2663, 2017, 2507, 2068, 2012, 2560, 1037, 2353, 1997, 1996, |
|
1997, 1996, 2518, 2008, 2027, 2663, 2061, 1045, 2123, 1005, |
|
1056, 2113, 2009, 2003, 7910, 2009, 1005, 1055, 2893, 2000, |
|
2022, 2062, 2449, 2085, 2738, 2084, 7910, 2941, 7910, 7149, |
|
2007, 1996, 4126, 2084, 2007, 7910, 8529, 1996, 7910, 7750, |
|
2027, 1996, 1996, 9559, 2024, 2074, 1999, 2009, 2005, 1996, |
|
2769, 1045, 1005, 1049, 1045, 1005, 1049, 6427, 1045, 2113, |
|
1045, 1045, 5993, 2007, 2017, 1045, 2228, 2017, 1005, 2128, |
|
2613, 2017, 1005, 2128, 2200, 2157, 2008, 1996, 8801, 2323, |
|
1045, 2228, 2027, 2323, 2031, 2019, 5020, 3815, 1997, 2017, |
|
2113, 2672, 2027, 2064, 2031, 1037, 2261, 2021, 1045, 2228, |
|
2087, 1997, 2068, 2323, 2022, 2025, 7910, 9559, 1999, 1996, |
|
2755, 1998, 2008, 1005, 1055, 2126, 2126, 2027, 1005, 2310, |
|
5407, 2046, 4331, 2009, 1005, 1055, 2138, 1997, 1996, 1996, |
|
2375, 2477, 2017, 2113, 1996, 15932, 1998, 2673, 2021, 7910, |
|
2021, 2053, 1045, 2113, 2057, 2009, 8529, 2057, 1005, 2128, |
|
1999, 5374, 1998, 7910, 2057, 2031, 1996, 2168, 2518, 2058, |
|
24375, 4667, 1998, 1998, 7910, 2027, 2024, 5599, 2068, 2041, |
|
1045, 2812, 2074, 1996, 3180, 7173, 6251, 2518, 2027, 2292, |
|
2068, 2041, 2138, 1997, 2027, 2123, 1005, 1056, 2031, 2151, |
|
2173, 2000, 2562, 2000, 2404, 2068, 2061, 8307, 2008, 2071, |
|
2017, 2113, 7910, 4983, 7910, 2042, 1037, 2350, 10048, 2021, |
|
7910, 7910, 2130, 1996, 14255, 14141, 2135, 2210, 4933, 1045, |
|
2812, 1996, 1996, 4364, 2008, 12386, 2651, 1999, 2637, 2003, |
|
1996, 6778, 1998, 9444, 2008, 2089, 2022, 3251, 2009, 1005, |
|
1055, 1037, 13742, 2030, 5850, 2030, 3649, 2842, 8529, 2027, |
|
2024, 1996, 3924, 2008, 2024, 2183, 2000, 3477, 1998, 2027, |
|
2024, 1996, 2028, 2008, 2024, 2183, 2000, 9015, 1998, 1996, |
|
2060, 2711, 2017, 2113, 2065, 2027, 3477, 2065, 2027, 2065, |
|
2027, 7910, 6545, 2068, 7910, 1998, 7910, 2059, 1996, 2017, |
|
2113, 2051, 1996, 2375, 3138, 2058, 7910, 2431, 1996, 2051, |
|
7910, 2027, 2593, 2292, 2068, 2175, 2030, 2027, 2131, 2125, |
|
2007, 1037, 1037, 6251, 2138, 2027, 1005, 2310, 2018, 1037, |
|
5160, 2008, 2017, 2113, 5683, 2008, 2008, 2027, 4694, 1005, |
|
1056, 2035, 2362, 2043, 2027, 2106, 2009, 102, 1045, 2228, |
|
2008, 2045, 2323, 2022, 2019, 5020, 6630, 1997, 15406, 1999, |
|
2256, 8801, 1012, 102]]), <InputKeys.ATT_MASK: 'attention_mask'>: tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
|
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]), <InputKeys.LABELS: 'labels'>: tensor([0]), <InputKeys.ON_CPU: 'on_cpu'>: {<SpecialKeys.ID: 'uid'>: [221950]}} |
|
|