Skip to content

Commit

Permalink
Merge pull request #388 from yangheng95/v3
Browse files Browse the repository at this point in the history 
Fix #386 and #387
  • Loading branch information
@yangheng95
yangheng95 committed Feb 28, 2024
2 parents 825442d + e8e0fc5 commit dcfdb7b
Show file tree
Hide file tree
Showing 154 changed files with 36,707 additions and 1,271 deletions.
1 change: 1 addition & 0 deletions checkpoints.json
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"2.3.0": {"APC": {"multilingual": {"id": "", "Training Model": "FAST-LCF-BERT-Deberta", "Training Dataset": "APCDatasetList.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "2.3.0+", "Checkpoint File": "fast_lcf_bert_Multilingual_acc_87.28_f1_81.33.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "english": {"id": "", "Training Model": "FAST-LSA-T-V2-Deberta", "Training Dataset": "APCDatasetList.English", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "2.3.0+", "Checkpoint File": "fast_lcf_bert_English_acc_84.65_f1_82.39.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "chinese": {"id": "", "Training Model": "FAST-LSA-T-V2-Deberta", "Training Dataset": "APCDatasetList.Chinese", "Language": "Chinese", "Description": "Trained on RTX3090", "Available Version": "2.3.0+", "Checkpoint File": "fast_lcf_bert_Chinese_acc_93.1_f1_86.21.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "ATEPC": {"multilingual": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ABSADatasets.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "fast_lcf_atepc_Multilingual_cdw_apcacc_85.1_apcf1_80.2_atef1_76.45.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "multilingual-original": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ABSADatasets.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "fast_lcf_atepc_Multilingual_cdw_apcacc_80.81_apcf1_73.75_atef1_76.01.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "multilingual2": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ABSADatasets.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "fast_lcf_atepc_Multilingual_cdw_apcacc_78.08_apcf1_77.81_atef1_75.41.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "english": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ATEPCDatasetList.English", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "chinese": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ATEPCDatasetList.Chinese", "Language": "Chinese", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lcf_atepc_Chinese_cdw_apcacc_96.22_apcf1_95.32_atef1_78.73.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "RNAC": {"degrad_lstm": {"id": "", "Training Model": "LSTM", "Training Dataset": "ABSADatasets.Multilingual", "Language": "RNA", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "lstm_degrad_acc_85.26_f1_84.62.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "degrad_bert": {"id": "", "Training Model": "MLP", "Training Dataset": "Degrad", "Language": "RNA", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "bert_mlp_degrad_acc_87.44_f1_86.99.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "TAD": {"tad-sst2": {"id": "", "Training Model": "TAD", "Training Dataset": "SST2", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "2.3.4+", "Checkpoint File": "TAD-SST2.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "tad-agnews10k": {"id": "", "Training Model": "TAD", "Training Dataset": "AGNews", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "2.3.4+", "Checkpoint File": "TAD-AGNews10K.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "tad-amazon": {"id": "", "Training Model": "TAD", "Training Dataset": "AGNews", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "2.3.4+", "Checkpoint File": "TAD-Amazon.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "CDD": {"promise": {"id": "", "Training Model": "CodeT5-small", "Training Dataset": "Promise", "Language": "Code", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "bert_mlp_all_cpdp_acc_75.33_f1_73.52.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "ASTE": {"english1": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "2.1.1+", "Checkpoint File": "EMCGCN_SemEval_f1_74.01.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "english": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "2.1.1+", "Checkpoint File": "ASTE-EMCGCN_SemEval_f1_74.71.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "multilingual": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval + Synthetic + Chinese_Zhang datasets", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "2.1.1+", "Checkpoint File": "EMCGCN-Multilingual-f1_51.95.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "ACOS": {"multilingual": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval + Synthetic + Chinese_Zhang datasets", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "2.1.8+", "Checkpoint File": "multilingual-acos.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "UPPERTASKCODE": {"promise": {"id": "", "Training Model": "CodeT5-small", "Training Dataset": "DatasetName", "Language": "", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "lstm_degrad_acc_85.26_f1_84.62.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}}, "2.0.0": {"APC": {"multilingual": {"id": "", "Training Model": "FAST-LSA-T-V2-Deberta", "Training Dataset": "APCDatasetList.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lcf_bert_Multilingual_acc_87.18_f1_83.11.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "multilingual2": {"id": "", "Training Model": "FAST-LSA-T-V2-Deberta", "Training Dataset": "APCDatasetList.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lcf_bert_Multilingual_acc_82.66_f1_82.06.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "english": {"id": "", "Training Model": "FAST-LSA-T-V2-Deberta", "Training Dataset": "APCDatasetList.English", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lsa_t_v2_English_acc_82.21_f1_81.81.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "chinese": {"id": "", "Training Model": "FAST-LSA-T-V2-Deberta", "Training Dataset": "APCDatasetList.Chinese", "Language": "Chinese", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lsa_t_v2_Chinese_acc_96.0_f1_95.1.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "ATEPC": {"multilingual": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ABSADatasets.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "fast_lcf_atepc_Multilingual_cdw_apcacc_85.1_apcf1_80.2_atef1_76.45.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "multilingual-original": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ABSADatasets.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "fast_lcf_atepc_Multilingual_cdw_apcacc_80.81_apcf1_73.75_atef1_76.01.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "multilingual2": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ABSADatasets.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "fast_lcf_atepc_Multilingual_cdw_apcacc_78.08_apcf1_77.81_atef1_75.41.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "english": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ATEPCDatasetList.English", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "chinese": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ATEPCDatasetList.Chinese", "Language": "Chinese", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lcf_atepc_Chinese_cdw_apcacc_96.22_apcf1_95.32_atef1_78.73.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "RNAC": {"degrad_lstm": {"id": "", "Training Model": "LSTM", "Training Dataset": "ABSADatasets.Multilingual", "Language": "RNA", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "lstm_degrad_acc_85.26_f1_84.62.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "degrad_bert": {"id": "", "Training Model": "MLP", "Training Dataset": "Degrad", "Language": "RNA", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "bert_mlp_degrad_acc_87.44_f1_86.99.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "TAD": {"tad-sst2": {"id": "", "Training Model": "TAD", "Training Dataset": "SST2", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "1.15+", "Checkpoint File": "TAD-SST2.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "tad-agnews10k": {"id": "", "Training Model": "TAD", "Training Dataset": "AGNews", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "1.15+", "Checkpoint File": "TAD-AGNews10K.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "tad-amazon": {"id": "", "Training Model": "TAD", "Training Dataset": "AGNews", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "1.15+", "Checkpoint File": "TAD-Amazon.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "CDD": {"promise": {"id": "", "Training Model": "CodeT5-small", "Training Dataset": "Promise", "Language": "Code", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "bert_mlp_all_cpdp_acc_75.33_f1_73.52.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "ASTE": {"english1": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "2.1.1+", "Checkpoint File": "EMCGCN_SemEval_f1_74.01.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "english": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "2.1.1+", "Checkpoint File": "ASTE-EMCGCN_SemEval_f1_74.71.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "multilingual": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval + Synthetic + Chinese_Zhang datasets", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "2.1.1+", "Checkpoint File": "EMCGCN-Multilingual-f1_51.95.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "ACOS": {"multilingual": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval + Synthetic + Chinese_Zhang datasets", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "2.1.8+", "Checkpoint File": "multilingual-acos.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "UPPERTASKCODE": {"promise": {"id": "", "Training Model": "CodeT5-small", "Training Dataset": "DatasetName", "Language": "", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "lstm_degrad_acc_85.26_f1_84.62.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}}}
2 changes: 1 addition & 1 deletion examples-v2/aspect_opinion_sentiment_category_extraction/checkpoints.json
View file

Large diffs are not rendered by default.

5 changes: 3 additions & 2 deletions examples-v2/aspect_opinion_sentiment_category_extraction/multitask_train.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@

import findfile
from pyabsa import ABSAInstruction as absa_instruction

warnings.filterwarnings("ignore")
import pandas as pd

Expand All @@ -35,8 +36,8 @@
# id_test_file_path = './integrated_datasets'
# id_train_file_path = "./integrated_datasets/acos_datasets/"
# id_test_file_path = "./integrated_datasets/acos_datasets"
id_train_file_path = './integrated_datasets/acos_datasets/501.Laptop14'
id_test_file_path = './integrated_datasets/acos_datasets/501.Laptop14'
id_train_file_path = "./integrated_datasets/acos_datasets/501.Laptop14"
id_test_file_path = "./integrated_datasets/acos_datasets/501.Laptop14"
# id_train_file_path = './integrated_datasets/acos_datasets/504.Restaurant16'
# id_test_file_path = './integrated_datasets/acos_datasets/504.Restaurant16'

Expand Down
2 changes: 1 addition & 1 deletion examples-v2/aspect_polarity_classification/ensemble_inference.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ def ensemble_performance(dataset, print_result=False):
APC.APCDatasetList.Restaurant14,
APC.APCDatasetList.Restaurant15,
APC.APCDatasetList.Restaurant16,
APC.APCDatasetList.MAMS
APC.APCDatasetList.MAMS,
]:
# Training
pass
Expand Down
12 changes: 7 additions & 5 deletions examples-v2/aspect_polarity_classification/train_apc.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -31,23 +31,25 @@
APC.APCDatasetList.MAMS,
]:
for model in [
# APC.APCModelList.FAST_LSA_T_V2,
APC.APCModelList.FAST_LSA_T_V2,
# APC.APCModelList.FAST_LSA_S_V2,
APC.APCModelList.BERT_SPC_V2,
# APC.APCModelList.BERT_SPC_V2,
# APC.APCModelList.BERT_SPC
]:
for pretrained_bert in [
# "microsoft/deberta-v3-base",
"bert-base-uncased",
# "bert-base-uncased",
# 'roberta-base',
# 'microsoft/deberta-v3-large',
"microsoft/deberta-v2-xlarge",
]:
config = APC.APCConfigManager.get_apc_config_english()
config.model = model
config.pretrained_bert = pretrained_bert
# config.pretrained_bert = 'roberta-base'
config.evaluate_begin = 0
config.max_seq_len = 80
config.batch_size = 8
config.max_seq_len = 70
config.num_epoch = 30
# config.log_step = 5
config.log_step = -1
Expand All @@ -59,9 +61,9 @@
config.cache_dataset = False
config.l2reg = 1e-8
config.learning_rate = 2e-5
config.use_amp = False
config.use_bert_spc = True
config.lsa = True
# config.use_amp = True
config.use_torch_compile = False
config.seed = [random.randint(0, 10000) for _ in range(3)]

Expand Down
Loading

0 comments on commit dcfdb7b

Please sign in to comment.