Initial Commit

.gitignore

@@ -0,0 +1,2 @@
+# MacOS Stuff
+**/.DS_Store

checkpoint-fold-0/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google/rembert",
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 312,
+  "classifier_dropout_prob": 0.1,
+  "embedding_dropout_prob": 0,
+  "embedding_size": 256,
+  "eos_token_id": 313,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "input_embedding_size": 256,
+  "intermediate_size": 4608,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "rembert",
+  "num_attention_heads": 18,
+  "num_hidden_layers": 32,
+  "output_embedding_size": 1664,
+  "pad_token_id": 0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250300
+}

checkpoint-fold-0/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f557117dc2d9456600767f89484e9c3c513ad34cc7675aafba96ce572af474a4
+size 2303917083

checkpoint-fold-0/result_dict.json

@@ -0,0 +1,12 @@
+{
+    "best_val_loss": 0.3669051616245515,
+    "epoch": [
+        0
+    ],
+    "train_loss": [
+        0.6209910749581079
+    ],
+    "val_loss": [
+        0.3669051616245515
+    ]
+}

checkpoint-fold-0/sentencepiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
+size 4697711

checkpoint-fold-0/special_tokens_map.json

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

checkpoint-fold-0/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 256, "special_tokens_map_file": "SauravMaheshkar/rembert-maxseq-384-docstride-128-chaii/checkpoint-fold-0/special_tokens_map.json", "name_or_path": "google/rembert", "tokenizer_class": "RemBertTokenizer"}

checkpoint-fold-1/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google/rembert",
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 312,
+  "classifier_dropout_prob": 0.1,
+  "embedding_dropout_prob": 0,
+  "embedding_size": 256,
+  "eos_token_id": 313,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "input_embedding_size": 256,
+  "intermediate_size": 4608,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "rembert",
+  "num_attention_heads": 18,
+  "num_hidden_layers": 32,
+  "output_embedding_size": 1664,
+  "pad_token_id": 0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250300
+}

checkpoint-fold-1/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf90effc3f23c83dcb11397febd97be5a623fb075ae199c1dd725f984c6885a4
+size 2303917083

checkpoint-fold-1/result_dict.json

@@ -0,0 +1,12 @@
+{
+    "best_val_loss": 0.38460480150028975,
+    "epoch": [
+        0
+    ],
+    "train_loss": [
+        0.6068687927800378
+    ],
+    "val_loss": [
+        0.38460480150028975
+    ]
+}

checkpoint-fold-1/sentencepiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
+size 4697711

checkpoint-fold-1/special_tokens_map.json

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

checkpoint-fold-1/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 256, "special_tokens_map_file": "SauravMaheshkar/rembert-maxseq-384-docstride-128-chaii/checkpoint-fold-1/special_tokens_map.json", "name_or_path": "google/rembert", "tokenizer_class": "RemBertTokenizer"}

checkpoint-fold-2/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google/rembert",
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 312,
+  "classifier_dropout_prob": 0.1,
+  "embedding_dropout_prob": 0,
+  "embedding_size": 256,
+  "eos_token_id": 313,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "input_embedding_size": 256,
+  "intermediate_size": 4608,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "rembert",
+  "num_attention_heads": 18,
+  "num_hidden_layers": 32,
+  "output_embedding_size": 1664,
+  "pad_token_id": 0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250300
+}

checkpoint-fold-2/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc48f240be46a2824a28e6060ffc06a560e9d028f292a34a0d89a57935c72c3
+size 2303917083

checkpoint-fold-2/result_dict.json

@@ -0,0 +1,12 @@
+{
+    "best_val_loss": 0.37014211892720533,
+    "epoch": [
+        0
+    ],
+    "train_loss": [
+        0.6895470289407112
+    ],
+    "val_loss": [
+        0.37014211892720533
+    ]
+}

checkpoint-fold-2/sentencepiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
+size 4697711

checkpoint-fold-2/special_tokens_map.json

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

checkpoint-fold-2/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 256, "special_tokens_map_file": "SauravMaheshkar/rembert-maxseq-384-docstride-128-chaii/checkpoint-fold-2/special_tokens_map.json", "name_or_path": "google/rembert", "tokenizer_class": "RemBertTokenizer"}

checkpoint-fold-3/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google/rembert",
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 312,
+  "classifier_dropout_prob": 0.1,
+  "embedding_dropout_prob": 0,
+  "embedding_size": 256,
+  "eos_token_id": 313,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "input_embedding_size": 256,
+  "intermediate_size": 4608,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "rembert",
+  "num_attention_heads": 18,
+  "num_hidden_layers": 32,
+  "output_embedding_size": 1664,
+  "pad_token_id": 0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250300
+}

checkpoint-fold-3/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dec3c34977219501b558c0306273564c6fcf862f15ffdcd33c3a3ba2f67110a
+size 2303917083

checkpoint-fold-3/result_dict.json

@@ -0,0 +1,12 @@
+{
+    "best_val_loss": 0.3932758030970136,
+    "epoch": [
+        0
+    ],
+    "train_loss": [
+        0.6031655376991026
+    ],
+    "val_loss": [
+        0.3932758030970136
+    ]
+}

checkpoint-fold-3/sentencepiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
+size 4697711

checkpoint-fold-3/special_tokens_map.json

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

checkpoint-fold-3/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 256, "special_tokens_map_file": "SauravMaheshkar/rembert-maxseq-384-docstride-128-chaii/checkpoint-fold-3/special_tokens_map.json", "name_or_path": "google/rembert", "tokenizer_class": "RemBertTokenizer"}