FEAT: New model

model/6a62f122a90e090b285f0344a1d79e753f2000bb/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "OwnBertForNextSentencePrediction"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model/6a62f122a90e090b285f0344a1d79e753f2000bb/info.json

@@ -0,0 +1,4 @@
+{
+  "model": "BERT-NSP-v6",
+  "description": "Model trained on DailyDialogue and CommonDialogues. Using [unused1] token to divide sentences in context. Improved training arguments (warmup, smaller learning rate). Using frozen test set to better compare models and therefore trained longer time (about 60 epochs). The model also have bigger classification head (from one layer liner as classical). Added method for **Data Augmentation**. More info can be found at https://wandb.ai/alquist/next-sentence-prediction/runs/xvzhhw2r/overview?workspace=user-petr-lorenc"
+}

model/6a62f122a90e090b285f0344a1d79e753f2000bb/meta-info.json

@@ -0,0 +1 @@
+{"args": [], "kwargs": {"model_package": "models", "model_class": "OwnBertForNextSentencePrediction", "data_root": "/home/lorenpe2/project/data", "data_sources": [["COMMON_DIALOGUES", "common_dialogues/train.json", "common_dialogues/valid_frozen.json", "common_dialogues/test_frozen.json"], ["DAILY_DIALOGUES", "daily_dialogues/dialogues_text.train.txt", "daily_dialogues/dev_frozen.json", "daily_dialogues/test_frozen.json"]], "pretrained_model": "bert-base-uncased", "tokenizer": "bert-base-uncased", "approach": "IGNORE_DUPLICITIES", "data_augmentation": ["ADD_PARTLY_BROKEN_CONTEXT"], "special_token": "[unused1]", "learning_rate": 5e-07, "warmup_ratio": 0.1, "freeze_prefinetuning": true, "prefinenuting_epoch": 10, "finetuning_epochs": 75}, "tokenizer_args": {"padding": "max_length", "max_length_ctx": 256, "max_length_res": 40, "truncation": "only_first", "return_tensors": "np", "is_split_into_words": true, "approach": "IGNORE_DUPLICITIES", "special_token": "[unused1]"}}

model/6a62f122a90e090b285f0344a1d79e753f2000bb/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb065d01ae7e4e255d81ca3fdafadb21c42daea7cafdaaac3c21923f11827641
+size 438871109

model/6a62f122a90e090b285f0344a1d79e753f2000bb/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[unused1]"]}

model/6a62f122a90e090b285f0344a1d79e753f2000bb/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "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, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

model/6a62f122a90e090b285f0344a1d79e753f2000bb/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0032b55f2a68888f89b97e84498c69d4a7a65403f1a209c41da390a1762f76fc
+size 3195