Training in progress, step 500

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "UWB-AIR/Czert-B-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.25,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.25,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-A",
+    "2": "I-A",
+    "3": "B-C",
+    "4": "I-C",
+    "5": "B-G",
+    "6": "I-G",
+    "7": "B-I",
+    "8": "I-I",
+    "9": "B-M",
+    "10": "I-M",
+    "11": "B-N",
+    "12": "I-N",
+    "13": "B-O",
+    "14": "I-O",
+    "15": "B-P",
+    "16": "I-P",
+    "17": "B-Q",
+    "18": "I-Q",
+    "19": "B-T",
+    "20": "I-T"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-A": 1,
+    "B-C": 3,
+    "B-G": 5,
+    "B-I": 7,
+    "B-M": 9,
+    "B-N": 11,
+    "B-O": 13,
+    "B-P": 15,
+    "B-Q": 17,
+    "B-T": 19,
+    "I-A": 2,
+    "I-C": 4,
+    "I-G": 6,
+    "I-I": 8,
+    "I-M": 10,
+    "I-N": 12,
+    "I-O": 14,
+    "I-P": 16,
+    "I-Q": 18,
+    "I-T": 20,
+    "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": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b72bd76a21ea0907ee34054c86315bd7ad86593142169688773501c8c6d033
+size 435654532

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "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 sha256:26bdaf35138b71d6b716be5359733e452e31978337ac7c9ad69cf966e8ab8d79
+size 4728