First model version

config.json

@@ -1,32 +1,29 @@
 {
-  "_name_or_path": "bert-base-multilingual-cased",
+  "_name_or_path": "xlm-roberta-base",
   "architectures": [
-    "BertForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "directionality": "bidi",
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.16.2",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 119547
+  "vocab_size": 250002
 }

eval_results.txt

@@ -1,11 +1,11 @@
-accuracy = 0.9122422114962703
-auprc = 0.8306318579767767
-auroc = 0.9438948821801457
-eval_loss = 0.2500895470380783
-fn = 107
-fp = 93
-macro_f1 = 0.8526940379543927
-mcc = 0.7055567705337081
-tn = 1764
-tp = 315
-weighted_f1 = 0.9116668668243681
+accuracy = 0.9240895129442738
+auprc = 0.8611675773330013
+auroc = 0.9568999839214756
+eval_loss = 0.21043916642665864
+fn = 73
+fp = 100
+macro_f1 = 0.8772280551302447
+mcc = 0.7550662217302937
+tn = 1757
+tp = 349
+weighted_f1 = 0.9249881346495145

model_args.json

@@ -1 +1 @@
-{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "temp_mbert_en_es/outputs/best_model", "cache_dir": "temp_mbert_en_es/cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 10, "encoding": null, "eval_batch_size": 512, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 200, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 0.0001, "local_rank": -1, "logging_steps": 200, "loss_type": null, "loss_args": {}, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "bert-base-multilingual-cased", "model_type": "bert", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 3, "optimizer": "AdamW", "output_dir": "temp_mbert_en_es/outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 78, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_recent_only": true, "save_steps": 200, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "bert-base-multilingual-cased", "tokenizer_type": null, "train_batch_size": 32, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {}, "wandb_project": "Xeventminer", "warmup_ratio": 0.06, "warmup_steps": 116, "weight_decay": 0, "model_class": "TextClassificationModel", "labels_list": [0, 1], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "temp_xlmr_en_es/outputs/best_model", "cache_dir": "temp_xlmr_en_es/cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 10, "encoding": null, "eval_batch_size": 512, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 200, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 200, "loss_type": null, "loss_args": {}, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "xlm-roberta-base", "model_type": "xlmroberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 3, "optimizer": "AdamW", "output_dir": "temp_xlmr_en_es/outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 78, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_recent_only": true, "save_steps": 200, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "xlm-roberta-base", "tokenizer_type": null, "train_batch_size": 32, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {}, "wandb_project": "Xeventminer", "warmup_ratio": 0.06, "warmup_steps": 116, "weight_decay": 0, "model_class": "TextClassificationModel", "labels_list": [0, 1], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:374987a6b7efff4ee798f8ef2fc4f9706cb67af0223b3a73704634933b656442
-size 1423007429
+oid sha256:0afb642255caf244480cd326aacc1be93d085f73ce9b004547ae92318cbec8f3
+size 2224529093

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94934cfe1985e464134f558b89f5dd0b6285e97fc1d8a16203b894bfe4ccedc6
-size 711505845
+oid sha256:a4a1a6314d396649089a71043ffda72e98f184b727f5f735c11cb112fd1d419e
+size 1112267893

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:637fb90ef6f33f623985ffd2349e0024fd92fec9acb9ac7d333df9ff95f6cdf0
+oid sha256:0a178fe0d4f5740c916bb95d666f189f27f88814ebec35559a4be3b31b1e105c
 size 627

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -1 +1 @@
-{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6098407db450b43d7111054e1d9c9385c9b9ffefd0ebc56de420e8a2848930b
+oid sha256:fbdb12bb8ac7c516b58d782a4638179c0be476073d3d6faddb90c79b0d1263e9
 size 3323