Training in progress, step 10000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48",
+  "activation": "relu",
+  "architectures": [
+    "DistilBertForMaskedLM"
+  ],
+  "attention_dropout": 0.05,
+  "dim": 768,
+  "dropout": 0.05,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "hybridbert",
+  "n_heads": 12,
+  "n_layers": 12,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.1,
+  "sinusoidal_pos_embds": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "vocab_size": 30522
+}

logs/1686221811.2517877/events.out.tfevents.1686221811.serv-9219.2885075.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df82859b27c279dfbb146acc0d5fb9096bbd024e92d55df8f5be4a1d350e37e
+size 6030

logs/events.out.tfevents.1686221811.serv-9219.2885075.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0656ca9b21543bbd6c50e3d35b01b673032960b3585bf6f07f2f497eb4888e3a
+size 7526

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7892070586832402911be0208d0c5cbc6a3be15f45c8bfc0da7c03e7899b969
+size 476593729

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26361705300b9566d8ed7673e98abbb29656ce6e373588a8361e70d55e5d3002
+size 4603