Upload folder using huggingface_hub

OneM-enar-ar-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,50 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-enar-ar-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,ar",
+ "partial_langs": "ar",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_file": "data/preprocessed_data/train_spider_seq2seq_english.json",
+ "valid_file": "data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "dataset_type": "spider",
+ "dataset_lang": "en",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "result_prefix": ""
+}

OneM-enar-ar-mean_eng-32.1e-4.1000/enar_ar_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd3777b7f46d175ac81049e24ab65879b643fc102aee43ddbeea1090c05bfbc
+size 100923736

OneM-ende-de-mean_eng-32.1e-4.1000/OneM_ende_de_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f74dc3665b4009b44545a3ae6630a639c010bbdecc234a17bcc6c9da23d09b
+size 100923736

OneM-ende-de-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,53 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-ende-de-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,de",
+ "partial_langs": "de",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_spider_seq2seq_prefix": "data/preprocessed_data/train_spider_seq2seq",
+ "dev_spider_seq2seq_prefix": "data/preprocessed_data/dev_spider_seq2seq",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "induced_code_switch": false,
+ "gt_code_switch": false,
+ "switch_prob": 1.0,
+ "muse_dict_path": "/home1/deokhk_1/research/ZX-seq2seq/data/muse_dict.txt",
+ "induced_dict_path": "/home/deokhk/research/XLang-NL2SQL/bilingual_dictionary/ko_to_en_token_dict_csls.json",
+ "result_prefix": ""
+}

OneM-enes-es-mean_eng-32.1e-4.1000/OneM_enes_es_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6be92b951b75ac0c59e528981cd1c4d5df37bf7484f58363a43fe3784d85c95
+size 100923736

OneM-enes-es-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,53 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-enes-es-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,es",
+ "partial_langs": "es",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_spider_seq2seq_prefix": "data/preprocessed_data/train_spider_seq2seq",
+ "dev_spider_seq2seq_prefix": "data/preprocessed_data/dev_spider_seq2seq",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "induced_code_switch": false,
+ "gt_code_switch": false,
+ "switch_prob": 1.0,
+ "muse_dict_path": "/home1/deokhk_1/research/ZX-seq2seq/data/muse_dict.txt",
+ "induced_dict_path": "/home/deokhk/research/XLang-NL2SQL/bilingual_dictionary/ko_to_en_token_dict_csls.json",
+ "result_prefix": ""
+}

OneM-enfa-fa-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,50 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-enfa-fa-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,fa",
+ "partial_langs": "fa",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_file": "data/preprocessed_data/train_spider_seq2seq_english.json",
+ "valid_file": "data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "dataset_type": "spider",
+ "dataset_lang": "en",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "result_prefix": ""
+}

OneM-enfa-fa-mean_eng-32.1e-4.1000/enfa_fa_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105478f6ab0e86ceb1a228797be6e2b8a99c387c7c0fa17d4beb08ce7924039d
+size 100923736

OneM-enfi-fi-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,50 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-enfi-fi-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,fi",
+ "partial_langs": "fi",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_file": "data/preprocessed_data/train_spider_seq2seq_english.json",
+ "valid_file": "data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "dataset_type": "spider",
+ "dataset_lang": "en",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "result_prefix": ""
+}

OneM-enfi-fi-mean_eng-32.1e-4.1000/enfi_fi_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a029ceac2487f455856f4768eb80ed8ed1cd2e695e055732486f29dcf22558ed
+size 100923736

OneM-enfr-fr-mean_eng-32.1e-4.1000/OneM_enfr_fr_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f562e3b6e0ee32c771401a2d95071b88397b7427e33fc3fdde01e1c9eb83f253
+size 100923736

OneM-enfr-fr-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,53 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-enfr-fr-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,fr",
+ "partial_langs": "fr",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_spider_seq2seq_prefix": "data/preprocessed_data/train_spider_seq2seq",
+ "dev_spider_seq2seq_prefix": "data/preprocessed_data/dev_spider_seq2seq",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "induced_code_switch": false,
+ "gt_code_switch": false,
+ "switch_prob": 1.0,
+ "muse_dict_path": "/home1/deokhk_1/research/ZX-seq2seq/data/muse_dict.txt",
+ "induced_dict_path": "/home/deokhk/research/XLang-NL2SQL/bilingual_dictionary/ko_to_en_token_dict_csls.json",
+ "result_prefix": ""
+}

OneM-enit-it-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,50 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-enit-it-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,it",
+ "partial_langs": "it",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_file": "data/preprocessed_data/train_spider_seq2seq_english.json",
+ "valid_file": "data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "dataset_type": "spider",
+ "dataset_lang": "en",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "result_prefix": ""
+}

OneM-enit-it-mean_eng-32.1e-4.1000/enit_it_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878646dc7d4f13a65ff75e6e84c9cd819cc4373181075cab27acfa935efb2439
+size 100923736

OneM-enja-ja-mean_eng-32.1e-4.1000/OneM_enja_ja_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad04e416ed902842260ed84d11865610aa343af63746c4323b2452e49fc84e9d
+size 100923736

OneM-enja-ja-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,53 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-enja-ja-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,ja",
+ "partial_langs": "ja",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_spider_seq2seq_prefix": "data/preprocessed_data/train_spider_seq2seq",
+ "dev_spider_seq2seq_prefix": "data/preprocessed_data/dev_spider_seq2seq",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "induced_code_switch": false,
+ "gt_code_switch": false,
+ "switch_prob": 1.0,
+ "muse_dict_path": "/home1/deokhk_1/research/ZX-seq2seq/data/muse_dict.txt",
+ "induced_dict_path": "/home/deokhk/research/XLang-NL2SQL/bilingual_dictionary/ko_to_en_token_dict_csls.json",
+ "result_prefix": ""
+}

OneM-enko-en-mean_eng-32.1e-4.1000/1M.enko.en_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2345fa23d78590ae81c3d9f141502cef02149a2fadd11bb3dc5b6bab189908dc
+size 100923736

OneM-enko-en-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,53 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.2,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-enko-en-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,ko",
+ "partial_langs": "en",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_spider_seq2seq_prefix": "data/preprocessed_data/train_spider_seq2seq",
+ "dev_spider_seq2seq_prefix": "data/preprocessed_data/dev_spider_seq2seq",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "induced_code_switch": false,
+ "gt_code_switch": false,
+ "switch_prob": 1.0,
+ "muse_dict_path": "/home1/deokhk_1/research/ZX-seq2seq/data/muse_dict.txt",
+ "induced_dict_path": "/home/deokhk/research/XLang-NL2SQL/bilingual_dictionary/ko_to_en_token_dict_csls.json",
+ "result_prefix": ""
+}

OneM-enpl-pl-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,50 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-enpl-pl-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,pl",
+ "partial_langs": "pl",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_file": "data/preprocessed_data/train_spider_seq2seq_english.json",
+ "valid_file": "data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "dataset_type": "spider",
+ "dataset_lang": "en",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "result_prefix": ""
+}

OneM-enpl-pl-mean_eng-32.1e-4.1000/enpl_pl_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6119db125d680fd18818cdf86e8fd8faab3e6346450312a8701c0375913e246
+size 100923736

OneM-enpt-pt-mean_eng-32.1e-4.1000/1M_enpt_pt_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d403da8766d5bb4d4f697acc580edb905b8d2be29b5e701d912981a062d568b
+size 100923736

OneM-enpt-pt-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,50 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-enpt-pt-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,pt",
+ "partial_langs": "pt",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_file": "data/preprocessed_data/train_spider_seq2seq_english.json",
+ "valid_file": "data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "dataset_type": "spider",
+ "dataset_lang": "en",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "result_prefix": ""
+}

OneM-entr-tr-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,50 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-entr-tr-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,tr",
+ "partial_langs": "tr",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_file": "data/preprocessed_data/train_spider_seq2seq_english.json",
+ "valid_file": "data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "dataset_type": "spider",
+ "dataset_lang": "en",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "result_prefix": ""
+}

OneM-entr-tr-mean_eng-32.1e-4.1000/entr_tr_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6defc00cf6db05aac0afb8f0c5372fd5dc6cccb4e8b51a740c83cfbfa8a560fe
+size 100923736

OneM-envi-vi-mean_eng-32.1e-4.1000/1M_envi_vi_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfa548f638e9dd704e790ec7239da340befa152f639b61552b99a267c579305
+size 100923736

OneM-envi-vi-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,50 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-envi-vi-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,vi",
+ "partial_langs": "vi",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_file": "data/preprocessed_data/train_spider_seq2seq_english.json",
+ "valid_file": "data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "dataset_type": "spider",
+ "dataset_lang": "en",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "result_prefix": ""
+}

OneM-enzh-zh-mean_eng-32.1e-4.1000/1M_enzh_zh_mean_eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fbe0e283a930f1c9262a00da6cbd5f389c9c8828b7a2d3ed34d3105cd3dddf3
+size 100923736

OneM-enzh-zh-mean_eng-32.1e-4.1000/config.json

@@ -0,0 +1,50 @@
+{
+ "epochs": 50,
+ "batch_size": 8,
+ "valid_batch_size": 16,
+ "gradient_accumulation_steps": 1,
+ "learning_rate": 0.0001,
+ "warmup_steps": 1000,
+ "early_stop": 3,
+ "mask_rate": 0.25,
+ "seed": 2023,
+ "training_steps": 100000,
+ "eval_steps": 5000,
+ "do_adapter_train": true,
+ "do_task_finetune": false,
+ "do_predict": false,
+ "do_synthesize": false,
+ "output_dir": "output",
+ "exp_tag": "OneM-enzh-zh-mean_eng-32.1e-4.1000",
+ "use_checkpoint": false,
+ "adapter_training_checkpoint": null,
+ "pretrained_adapter_dir": null,
+ "model_name_or_path": "google/mt5-large",
+ "max_seq_length": 512,
+ "local_rank": -1,
+ "adapter_types": "decoder-lang",
+ "langs": "en,zh",
+ "partial_langs": "zh",
+ "tasks": null,
+ "task_lang": null,
+ "adapter_layer_norm": true,
+ "adapter_reduction_factor": 2,
+ "adapter_hidden_act": "gelu",
+ "frozen_list": "all",
+ "freeze_option": "dec_cross_attention_only",
+ "train_file": "data/preprocessed_data/train_spider_seq2seq_english.json",
+ "valid_file": "data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "without_schema": false,
+ "inference_data_file": "/home1/deokhk_1/research/ZX-seq2seq/data/preprocessed_data/dev_spider_seq2seq_english.json",
+ "dataset_type": "spider",
+ "dataset_lang": "en",
+ "generation_max_length": 64,
+ "generation_num_beams": 8,
+ "contrastive_generation": false,
+ "repetition_penalty": 1.0,
+ "without_language_identity": true,
+ "removal_type": "mean_eng",
+ "language_identity_path": "/home1/deokhk_1/research/XLang-NL2SQL/language_identity_wiki_token_1M",
+ "remove_prob": 1.0,
+ "result_prefix": ""
+}