Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48",
+  "activation": "relu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.05,
+  "cache_dir": null,
+  "dim": 768,
+  "dropout": 0.05,
+  "finetuning_task": "stsb",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "hybridbert",
+  "n_heads": 12,
+  "n_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "revision": "main",
+  "seq_classif_dropout": 0.1,
+  "sinusoidal_pos_embds": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_auth_token": null,
+  "vocab_size": 30522
+}

logs/1686059404.678693/events.out.tfevents.1686059404.serv-9207.2390652.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d616266f731d8d237fb560d227108246b0d9d4cea8ebd99d59d3fbd10d81ee
+size 5938

logs/events.out.tfevents.1686059404.serv-9207.2390652.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21dc74fbbd1c97b156aa6c7d45235016f7f0edbe9724623f1e6d2e06c8c235b2
+size 4639

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeca1d265666851ae29aa61289c4005e58ff8d989870819df94280231c6f85d0
+size 476520365

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 sha256:3385fe96c97f133cbc0d3606dd71e56579530cc78f387a6f0e53736451ea385c
+size 3963