print("Train Model")
model = Model(binaryClassification=args["binaryClassification"],
model_str=tokenizer_model[1],
doLower=args["doLower"],
train_batchSize=args["train_batchSize"],
testval_batchSize=args["testval_batchSize"],
learningRate=args["learningRate"],
doLearningRateScheduler=args["doLearningRateScheduler"],
labelSentences=labelSentencesDict,
max_label_len=max_label_len,
device=device)
model.run(train_data=train_df[data_column],
train_target=train_df[args["targets"]],
val_data=val_df[data_column],
val_target=val_df[args["targets"]],
test_data=test_df[data_column],
test_target=test_df[args["targets"]],
epochs=args["numEpochs"])
wandb.log({'finished': True})
run_infos = wandb_summarizer.download.get_results(wandb_project_name)
names = []
scores = []
for run_info in run_infos:
try:
scores.append(run_info["end_test_macroAuc"])
names.append(run_info["name"])
except:
pass
max_label_len = max(
[len(word_tokenize(x)) for x in labelSentencesDict.values()])
print("Train Model")
model = Model(args=tokenizer_model,
doLower=args["doLower"],
train_batchSize=args["train_batchSize"],
testval_batchSize=args["testval_batchSize"],
learningRate=args["learningRate"],
doLearningRateScheduler=args["doLearningRateScheduler"],
labelSentences=labelSentencesDict,
smartBatching=args["smartBatching"],
max_label_len=max_label_len,
device=device,
target_columns=args["targets"])
# train and test the model
model.run(train_data=train_data,
train_target=train_target,
val_data=val_data,
val_target=val_target,
test_data=test_data,
test_target=test_target,
epochs=args["numEpochs"])
# close the logging
wandb.log({'finished': True})
# save the model
#model.save(os.path.join(args["model_path"], "{}".format(wandb.run.name)))