Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1 @@
+{"<e>": 28996, "</e>": 28997}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bert-large-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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": "4.16.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28998
+}

eval_results.txt

@@ -0,0 +1,20 @@
+accuracy = 0.7811111111111111
+cls_report =               precision    recall  f1-score   support
+
+         0.0     0.7652    0.8355    0.7988       468
+         1.0     0.8021    0.7222    0.7600       432
+
+    accuracy                         0.7811       900
+   macro avg     0.7836    0.7788    0.7794       900
+weighted avg     0.7829    0.7811    0.7802       900
+
+eval_loss = 0.5005695144335429
+fn = 120
+fp = 77
+macro_f1 = 0.7794114902601401
+mcc = 0.5624374149385448
+tn = 391
+tp = 312
+weighted_f1 = 0.7801860010276712
+weighted_p = 0.7836114478893645
+weighted_r = 0.7788461538461539

model_args.json

@@ -0,0 +1 @@
+{"adam_epsilon": 1e-08, "begin_tag": "<e>", "best_model_dir": "temp/outputs/best_model", "cache_dir": "temp/cache_dir/", "config": {}, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 70, "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, "end_tag": "</e>", "eval_batch_size": 64, "evaluate_during_training": true, "evaluate_during_training_silent": false, "evaluate_during_training_steps": 100, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 100, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 120, "model_name": "bert-large-cased", "model_type": "bert", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "num_train_epochs": 3, "output_dir": "temp/outputs/", "overwrite_output_dir": true, "process_count": 70, "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": 100, "save_recent_only": true, "silent": false, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": true, "wandb_kwargs": {"group": "en-en_bert-large-cased_CLS-B_concat", "job_type": "2"}, "wandb_project": "TransWiC-groups", "warmup_ratio": 0.1, "warmup_steps": 304, "weight_decay": 0, "skip_special_tokens": true, "model_class": "ClassificationModel", "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, "stride": 0.8, "tie_value": 1, "tagging": true, "strategy": "CLS-B", "special_tags": ["[CLS]", "<e>"], "merge_n": 3, "merge_type": "concat"}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62052a2c62d0dd2b9f868be1f4eb71859e1e8dd8524de6ee1a180463600cdc59
+size 2660532549

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:273495400adebec39210e2045cc842bf59e90fdd3e95e8faa19e9f2f7594663e
+size 1334514421

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:603e994655cf3ec4d6084c28df34193c3cf6ad356dd7b152e73720eae863d034
+size 627

special_tokens_map.json

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

test_eval.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.8515    0.9060    0.8779       500
+           T     0.8996    0.8420    0.8698       500
+
+    accuracy                         0.8740      1000
+   macro avg     0.8755    0.8740    0.8739      1000
+weighted avg     0.8755    0.8740    0.8739      1000
+
+
+ADJ
+Accuracy = 0.8541666666666666
+Weighted Recall = 0.8541666666666666
+Weighted Precision = 0.8637617656605
+Weighted F1 = 0.8539344815940562
+Macro Recall = 0.8579721362229102
+Macro Precision = 0.8602726387536515
+Macro F1 = 0.8541033434650457
+ADV
+Accuracy = 0.7666666666666667
+Weighted Recall = 0.7666666666666667
+Weighted Precision = 0.7682539682539683
+Weighted F1 = 0.7589743589743588
+Macro Recall = 0.7361111111111112
+Macro Precision = 0.7698412698412698
+Macro F1 = 0.7435897435897436
+NOUN
+Accuracy = 0.875
+Weighted Recall = 0.875
+Weighted Precision = 0.8757551023343448
+Weighted F1 = 0.8749246198687668
+Macro Recall = 0.8749121170815697
+Macro Precision = 0.8758180275288736
+Macro F1 = 0.8749120565135613
+VERB
+Accuracy = 0.8926174496644296
+Weighted Recall = 0.8926174496644296
+Weighted Precision = 0.8932551319648093
+Weighted F1 = 0.8925739005046864
+Macro Recall = 0.8926174496644295
+Macro Precision = 0.8932551319648094
+Macro F1 = 0.8925739005046864

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/hh2/.cache/huggingface/transformers/75be22d7750034989358861e325977feda47740e1c3f8a4dc1cb73570aad843e.2b9a196704f2f183fe3f4b48d6e662dba8203fdcb3346bfa896831378edf6f97", "name_or_path": "bert-large-cased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aef620af9dc323d460035f21adf09d622e29f6318e2d4e8a295dba21903b850
+size 2875