Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "gokuls/bert_12_layer_model_v1_complete_training_new_wt_init",
+  "activation": "relu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.05,
+  "cache_dir": null,
+  "dim": 768,
+  "dropout": 0.05,
+  "finetuning_task": "wnli",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "not_entailment",
+    "1": "entailment"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "entailment": 1,
+    "not_entailment": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "hybridbert",
+  "n_heads": 12,
+  "n_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "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/1685552112.193103/events.out.tfevents.1685552112.serv-9223.3032138.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f28e7d01244695543e9d857b8b36dd0d343aac1ca506a8c531ef2b2d73a0d8e
+size 5930

logs/events.out.tfevents.1685552112.serv-9223.3032138.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c27e465102b9733ba69b7fd29847539aea60b4541628a4f3825e56c67af4e8a
+size 4579

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6396c11d40f5912418dc9d6d31777dad4eae2786e3e94d3e775a8cca9b3d6d3
+size 481099229

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:d0b4048d68cc126b657917f129495dd8bde23a94e1677e9c1e22554074344841
+size 3963