Training in progress, step 500

config.json

@@ -0,0 +1,216 @@
+{
+  "_name_or_path": "UWB-AIR/Czert-B-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.15,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-ah",
+    "2": "I-ah",
+    "3": "B-at",
+    "4": "I-at",
+    "5": "B-az",
+    "6": "I-az",
+    "7": "B-g_",
+    "8": "I-g_",
+    "9": "B-gc",
+    "10": "I-gc",
+    "11": "B-gh",
+    "12": "I-gh",
+    "13": "B-gl",
+    "14": "I-gl",
+    "15": "B-gq",
+    "16": "I-gq",
+    "17": "B-gr",
+    "18": "I-gr",
+    "19": "B-gs",
+    "20": "I-gs",
+    "21": "B-gt",
+    "22": "I-gt",
+    "23": "B-gu",
+    "24": "I-gu",
+    "25": "B-i_",
+    "26": "I-i_",
+    "27": "B-ia",
+    "28": "I-ia",
+    "29": "B-ic",
+    "30": "I-ic",
+    "31": "B-if",
+    "32": "I-if",
+    "33": "B-io",
+    "34": "I-io",
+    "35": "B-me",
+    "36": "I-me",
+    "37": "B-mi",
+    "38": "I-mi",
+    "39": "B-mn",
+    "40": "I-mn",
+    "41": "B-ms",
+    "42": "I-ms",
+    "43": "B-n_",
+    "44": "I-n_",
+    "45": "B-na",
+    "46": "I-na",
+    "47": "B-nb",
+    "48": "I-nb",
+    "49": "B-nc",
+    "50": "I-nc",
+    "51": "B-ni",
+    "52": "I-ni",
+    "53": "B-no",
+    "54": "I-no",
+    "55": "B-ns",
+    "56": "I-ns",
+    "57": "B-o_",
+    "58": "I-o_",
+    "59": "B-oa",
+    "60": "I-oa",
+    "61": "B-oe",
+    "62": "I-oe",
+    "63": "B-om",
+    "64": "I-om",
+    "65": "B-op",
+    "66": "I-op",
+    "67": "B-or",
+    "68": "I-or",
+    "69": "B-p_",
+    "70": "I-p_",
+    "71": "B-pc",
+    "72": "I-pc",
+    "73": "B-pd",
+    "74": "I-pd",
+    "75": "B-pf",
+    "76": "I-pf",
+    "77": "B-pm",
+    "78": "I-pm",
+    "79": "B-pp",
+    "80": "I-pp",
+    "81": "B-ps",
+    "82": "I-ps",
+    "83": "B-td",
+    "84": "I-td",
+    "85": "B-tf",
+    "86": "I-tf",
+    "87": "B-th",
+    "88": "I-th",
+    "89": "B-tm",
+    "90": "I-tm",
+    "91": "B-ty",
+    "92": "I-ty"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ah": 1,
+    "B-at": 3,
+    "B-az": 5,
+    "B-g_": 7,
+    "B-gc": 9,
+    "B-gh": 11,
+    "B-gl": 13,
+    "B-gq": 15,
+    "B-gr": 17,
+    "B-gs": 19,
+    "B-gt": 21,
+    "B-gu": 23,
+    "B-i_": 25,
+    "B-ia": 27,
+    "B-ic": 29,
+    "B-if": 31,
+    "B-io": 33,
+    "B-me": 35,
+    "B-mi": 37,
+    "B-mn": 39,
+    "B-ms": 41,
+    "B-n_": 43,
+    "B-na": 45,
+    "B-nb": 47,
+    "B-nc": 49,
+    "B-ni": 51,
+    "B-no": 53,
+    "B-ns": 55,
+    "B-o_": 57,
+    "B-oa": 59,
+    "B-oe": 61,
+    "B-om": 63,
+    "B-op": 65,
+    "B-or": 67,
+    "B-p_": 69,
+    "B-pc": 71,
+    "B-pd": 73,
+    "B-pf": 75,
+    "B-pm": 77,
+    "B-pp": 79,
+    "B-ps": 81,
+    "B-td": 83,
+    "B-tf": 85,
+    "B-th": 87,
+    "B-tm": 89,
+    "B-ty": 91,
+    "I-ah": 2,
+    "I-at": 4,
+    "I-az": 6,
+    "I-g_": 8,
+    "I-gc": 10,
+    "I-gh": 12,
+    "I-gl": 14,
+    "I-gq": 16,
+    "I-gr": 18,
+    "I-gs": 20,
+    "I-gt": 22,
+    "I-gu": 24,
+    "I-i_": 26,
+    "I-ia": 28,
+    "I-ic": 30,
+    "I-if": 32,
+    "I-io": 34,
+    "I-me": 36,
+    "I-mi": 38,
+    "I-mn": 40,
+    "I-ms": 42,
+    "I-n_": 44,
+    "I-na": 46,
+    "I-nb": 48,
+    "I-nc": 50,
+    "I-ni": 52,
+    "I-no": 54,
+    "I-ns": 56,
+    "I-o_": 58,
+    "I-oa": 60,
+    "I-oe": 62,
+    "I-om": 64,
+    "I-op": 66,
+    "I-or": 68,
+    "I-p_": 70,
+    "I-pc": 72,
+    "I-pd": 74,
+    "I-pf": 76,
+    "I-pm": 78,
+    "I-pp": 80,
+    "I-ps": 82,
+    "I-td": 84,
+    "I-tf": 86,
+    "I-th": 88,
+    "I-tm": 90,
+    "I-ty": 92,
+    "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:d04fa004e2aed79d0032a41f1901e4bb554b15cfc0bb62c5a7e4fec138492805
+size 435876004

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:a3bb42167f3c492c1d1589f7ee66b49d159bfe572ac25f2546fd27d1cde94894
+size 4728