Add best model

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "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",
+  "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",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

eval_results.txt

@@ -0,0 +1,5 @@
+ans_f1 = 72.7162551492616
+correct = 559
+eval_loss = -8.96630859375
+incorrect = 51
+similar = 154

model_args.json

@@ -0,0 +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_epsilon": 1e-08, "best_model_dir": "/mnt/ssd1/kikiputri/QGen/outputs/idk-mrc/bert/mbert_idk/99/best_model/", "cache_dir": "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": "ans_f1", "early_stopping_metric_minimize": false, "early_stopping_patience": 3, "encoding": "utf-8", "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": 99, "max_grad_norm": 1.0, "max_seq_length": 512, "model_name": "bert-base-multilingual-cased", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": true, "no_save": false, "not_saved_args": [], "num_train_epochs": 10, "optimizer": "AdamW", "output_dir": "/mnt/ssd1/kikiputri/QGen/outputs/idk-mrc/bert/mbert_idk/99/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 38, "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_steps": -1, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": "idk-mrc", "warmup_ratio": 0.06, "warmup_steps": 716, "weight_decay": 0.0, "model_class": "QuestionAnsweringModel", "doc_stride": 128, "lazy_loading": false, "max_answer_length": 100, "max_query_length": 128, "n_best_size": 20, "null_score_diff_threshold": 0.0, "special_tokens_list": []}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21fec8f6387eb540cfbe684817857137015cb2f4d3c8be55ef4b1528c88eebb
+size 1418239981

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e271368be438bcd4be8d14e41d3d11c55c0c54ae34b2223db4a37371ea521ad1
+size 709146103

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412315de04cd4e3ccce58e50ad381b669d14c707d57a0a91256479620fadb172
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "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, "tokenizer_file": "/home/kikiputri/.cache/huggingface/transformers/46880f3b0081fda494a4e15b05787692aa4c1e21e0ff2428ba8b14d4eda0784d.b33e51591f94f17c238ee9b1fac75b96ff2678cbaed6e108feadb3449d18dc24", "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c0804e7731e5d70fd5d22e1fe7da4a9c2fbfe586986bed405bca01637d1a64
+size 3119