Training in progress, step 500

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "jonas-luehrs/chembert_cased-MLM-chemistry",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-ADDITIVE",
+    "2": "I-ADDITIVE",
+    "3": "B-OLEFIN",
+    "4": "I-OLEFIN",
+    "5": "B-PRE_CATALYST",
+    "6": "I-PRE_CATALYST",
+    "7": "B-SOLVENT",
+    "8": "I-SOLVENT",
+    "9": "B-SUPPORT",
+    "10": "I-SUPPORT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ADDITIVE": 1,
+    "B-OLEFIN": 3,
+    "B-PRE_CATALYST": 5,
+    "B-SOLVENT": 7,
+    "B-SUPPORT": 9,
+    "I-ADDITIVE": 2,
+    "I-OLEFIN": 4,
+    "I-PRE_CATALYST": 6,
+    "I-SOLVENT": 8,
+    "I-SUPPORT": 10,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38688eaaa9c65bd4f3f0e3c73bedbf05ade388fd410028776f78047f8303a991
+size 430980265

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 +1,16 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "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:b10778763884656c0b9c3e0a8d41b2fb78a096f2f44f7032ce4ace6dfaa0464c
+size 4091