File size: 869 Bytes
bcc84fc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
from __gin__ import dynamic_registration
import tasks

import __main__ as train_script
from t5.data import mixtures
from t5x import models
from t5x import partitioning
from t5x import utils

include "t5x/examples/t5/t5_1_1/large.gin"
include "t5x/configs/runs/finetune.gin"

MIXTURE_OR_TASK_NAME = %gin.REQUIRED
TASK_FEATURE_LENGTHS = {"inputs": 512, "targets": 512}
INITIAL_CHECKPOINT_PATH = %gin.REQUIRED
TRAIN_STEPS = %gin.REQUIRED  # 1000000 pre-trained steps + 10000 fine-tuning steps.
USE_CACHED_TASKS = False
DROPOUT_RATE = 0.1
RANDOM_SEED = 0

#Fixing a small error
infer_eval/utils.DatasetConfig:
  task_feature_lengths = %TASK_FEATURE_LENGTHS

#Saving every 1000 steps
utils.SaveCheckpointConfig:
  period = 1000
  keep = 1  # number of checkpoints to keep

# Might have to ba changed based on architecture
# partitioning.PjitPartitioner.num_partitions = 1