petite-difference-challenge.../3-train.py

32 lines
1.4 KiB
Python
Executable File

#!/usr/bin/env bash
TOTAL_NUM_UPDATES=1000000000000000 # 10 epochs through IMDB for bsz 32
WARMUP_UPDATES=216085 # 6 percent of the number of updates
LR=1e-05 # Peak LR for polynomial LR scheduler.
HEAD_NAME=hesaid # Custom name for the classification head.
NUM_CLASSES=2 # Number of classes for the classification task.
MAX_SENTENCES=35 # Batch size.
ROBERTA_PATH="roberta_base_fairseq/model.pt"
fairseq-train data-bin/ \
--restore-file $ROBERTA_PATH \
--max-positions 512 \
--max-sentences $MAX_SENTENCES \
--max-tokens 8192 \
--task sentence_prediction \
--reset-optimizer --reset-dataloader --reset-meters \
--required-batch-size-multiple 2 \
--init-token 0 --separator-token 2 \
--arch roberta_base \
--criterion sentence_prediction \
--classification-head-name $HEAD_NAME \
--num-classes $NUM_CLASSES \
--dropout 0.1 --attention-dropout 0.1 \
--weight-decay 0.1 --optimizer adam --adam-betas "(0.9, 0.98)" --adam-eps 1e-06 \
--clip-norm 0.0 \
--lr-scheduler polynomial_decay --lr $LR --total-num-update $TOTAL_NUM_UPDATES --warmup-updates $WARMUP_UPDATES \
--max-epoch 5 --log-format tqdm --log-interval 1 --save-interval-updates 15000 --keep-interval-updates 5 --skip-invalid-size-inputs-valid-test \
--best-checkpoint-metric accuracy --maximize-best-checkpoint-metric \
--find-unused-parameters \
--update-freq 1