Training in progress, step 10000

.gitignore

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

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_72",
+  "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": "4.30.1",
+  "vocab_size": 30522
+}

logs/events.out.tfevents.1686341683.serv-9225.1283119.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a993f3899c626b971066512f7a5430443cc998fcd28348c38845dafc1d4ee367
+size 7526

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ffb33acee883eb3688d0ccabc3abfb6dfdbf83b2aba496fe32d5cdba7ecbbe
+size 481170113

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 sha256:8ff6a3cdee20763cdbce4b008ae4a9674da89da98b213d7cbb62da3af2b4957d
+size 5051