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 = 0.8122222222222222
+cls_report =               precision    recall  f1-score   support
+
+         0.0     0.8485    0.7778    0.8116       468
+         1.0     0.7792    0.8495    0.8128       432
+
+    accuracy                         0.8122       900
+   macro avg     0.8138    0.8137    0.8122       900
+weighted avg     0.8152    0.8122    0.8122       900
+
+eval_loss = 0.4493997673193614
+fn = 65
+fp = 104
+macro_f1 = 0.8122201357792864
+mcc = 0.6274964083386112
+tn = 364
+tp = 367
+weighted_f1 = 0.812195098464057
+weighted_p = 0.8138390272148235
+weighted_r = 0.8136574074074074

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_P_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": "P", "special_tags": ["<e>", "</e>"], "merge_n": 2, "merge_type": "concat"}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60cd781faba3cf254dc6444769b00ce0843a58498aba09986d34706f5a08ffc3
+size 2660516165

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:889b9de985ea55414cd11a2c4442f19317d40346757a6e7c915b83d1e1002604
+size 1334506229

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93a77a513e2e8c74a0f7643b089a6503701a057afe58a9c7890e0113b7dc464
+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     0.8643    0.8920    0.8780       500
+           T     0.8884    0.8600    0.8740       500
+
+    accuracy                         0.8760      1000
+   macro avg     0.8764    0.8760    0.8760      1000
+weighted avg     0.8764    0.8760    0.8760      1000
+
+
+ADJ
+Accuracy = 0.875
+Weighted Recall = 0.875
+Weighted Precision = 0.8750971250971252
+Weighted F1 = 0.8748788524907928
+Macro Recall = 0.8738390092879257
+Macro Precision = 0.8752913752913754
+Macro F1 = 0.8743942624539639
+ADV
+Accuracy = 0.8333333333333334
+Weighted Recall = 0.8333333333333334
+Weighted Precision = 0.8412698412698413
+Weighted F1 = 0.827838827838828
+Macro Recall = 0.8055555555555556
+Macro Precision = 0.8492063492063492
+Macro F1 = 0.8168498168498168
+NOUN
+Accuracy = 0.8674242424242424
+Weighted Recall = 0.8674242424242424
+Weighted Precision = 0.8681623467839614
+Weighted F1 = 0.8673442938002072
+Macro Recall = 0.8673362508070881
+Macro Precision = 0.8682238554806047
+Macro F1 = 0.8673309690295347
+VERB
+Accuracy = 0.8959731543624161
+Weighted Recall = 0.8959731543624161
+Weighted Precision = 0.896133741888969
+Weighted F1 = 0.8959626105073482
+Macro Recall = 0.8959731543624161
+Macro Precision = 0.896133741888969
+Macro F1 = 0.8959626105073484

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 sha256:28823c3c77f4a50d0e993c24862c6823d96d5a3a8faa57f57ba6e93a25d5dda0
+size 2811