Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "wukevin/tcr-bert",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 64,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 21,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 26
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18b1ad44520d63444d1ddd465f394c0b42e6cc08d4b17ea5f4fb9f792e2c3b6
+size 229621365

runs/Apr07_03-24-21_e79bc52ba879/1680837887.4074097/events.out.tfevents.1680837887.e79bc52ba879.155.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dfdb0e0ea4ebb54291c47bca7c5b80dd32789b859efe51bf97b5aab490954e1
+size 5861

runs/Apr07_03-24-21_e79bc52ba879/events.out.tfevents.1680837887.e79bc52ba879.155.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a9ed7fd7928242863027a29130f87e8ded19ed0473ced389068210d7e8dbad
+size 4397

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "*",
+  "mask_token": ".",
+  "pad_token": "$",
+  "sep_token": "|",
+  "unk_token": "?"
+}

tokenizer.json

@@ -0,0 +1,176 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 21,
+      "content": "$",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 22,
+      "content": ".",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 23,
+      "content": "?",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 24,
+      "content": "|",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 25,
+      "content": "*",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "BertNormalizer",
+    "clean_text": true,
+    "handle_chinese_chars": false,
+    "strip_accents": null,
+    "lowercase": false
+  },
+  "pre_tokenizer": {
+    "type": "BertPreTokenizer"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "*",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "|",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "*",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "|",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "|",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "*": {
+        "id": "*",
+        "ids": [
+          25
+        ],
+        "tokens": [
+          "*"
+        ]
+      },
+      "|": {
+        "id": "|",
+        "ids": [
+          24
+        ],
+        "tokens": [
+          "|"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "WordPiece",
+    "prefix": "##",
+    "cleanup": true
+  },
+  "model": {
+    "type": "WordPiece",
+    "unk_token": "?",
+    "continuing_subword_prefix": "##",
+    "max_input_chars_per_word": 100,
+    "vocab": {
+      "R": 0,
+      "H": 1,
+      "K": 2,
+      "D": 3,
+      "E": 4,
+      "S": 5,
+      "T": 6,
+      "N": 7,
+      "Q": 8,
+      "C": 9,
+      "U": 10,
+      "G": 11,
+      "P": 12,
+      "A": 13,
+      "V": 14,
+      "I": 15,
+      "L": 16,
+      "M": 17,
+      "F": 18,
+      "Y": 19,
+      "W": 20,
+      "$": 21,
+      ".": 22,
+      "?": 23,
+      "|": 24,
+      "*": 25
+    }
+  }
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "cls_token": "*",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": ".",
+  "model_max_len": 45,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "$",
+  "padding_side": "right",
+  "sep_token": "|",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--wukevin--tcr-bert/snapshots/ef65ddcb4e549990e584680e27f9ae2618c884ff/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": false,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "?"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1649313dd16468ef88e2614194b37b71ecbc2890bf75467ca4a56a198e657a5
+size 3579

vocab.txt

@@ -0,0 +1,26 @@
+R
+H
+K
+D
+E
+S
+T
+N
+Q
+C
+U
+G
+P
+A
+V
+I
+L
+M
+F
+Y
+W
+$
+.
+?
+|
+*