Training in progress, epoch 1

config.json

@@ -0,0 +1,119 @@
+{
+  "_name_or_path": "DeepMount00/Italian-ModernBERT-base",
+  "architectures": [
+    "ModernBertForTokenClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 2,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 3,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-LOC",
+    "4": "I-LOC",
+    "5": "B-ORG",
+    "6": "I-ORG",
+    "7": "B-ANIM",
+    "8": "I-ANIM",
+    "9": "B-BIO",
+    "10": "I-BIO",
+    "11": "B-CEL",
+    "12": "I-CEL",
+    "13": "B-DIS",
+    "14": "I-DIS",
+    "15": "B-EVE",
+    "16": "I-EVE",
+    "17": "B-FOOD",
+    "18": "I-FOOD",
+    "19": "B-INST",
+    "20": "I-INST",
+    "21": "B-MEDIA",
+    "22": "I-MEDIA",
+    "23": "B-PLANT",
+    "24": "I-PLANT",
+    "25": "B-MYTH",
+    "26": "I-MYTH",
+    "27": "B-TIME",
+    "28": "I-TIME",
+    "29": "B-VEHI",
+    "30": "I-VEHI",
+    "31": "B-MISC",
+    "32": "I-MISC"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "B-ANIM": 7,
+    "B-BIO": 9,
+    "B-CEL": 11,
+    "B-DIS": 13,
+    "B-EVE": 15,
+    "B-FOOD": 17,
+    "B-INST": 19,
+    "B-LOC": 3,
+    "B-MEDIA": 21,
+    "B-MISC": 31,
+    "B-MYTH": 25,
+    "B-ORG": 5,
+    "B-PER": 1,
+    "B-PLANT": 23,
+    "B-TIME": 27,
+    "B-VEHI": 29,
+    "I-ANIM": 8,
+    "I-BIO": 10,
+    "I-CEL": 12,
+    "I-DIS": 14,
+    "I-EVE": 16,
+    "I-FOOD": 18,
+    "I-INST": 20,
+    "I-LOC": 4,
+    "I-MEDIA": 22,
+    "I-MISC": 32,
+    "I-MYTH": 26,
+    "I-ORG": 6,
+    "I-PER": 2,
+    "I-PLANT": 24,
+    "I-TIME": 28,
+    "I-VEHI": 30,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "mask_token_id": 4,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "reference_compile": false,
+  "repad_logits_with_grad": false,
+  "sep_token_id": 3,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "unk_token_id": 0,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8eaf2552b495faac161c97200cfc4c098baae8d315c2fd7e2099bd8ad6aff2
+size 542108652

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "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]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens": {
+    "cls_token": "[CLS]",
+    "mask_token": "[MASK]",
+    "pad_token": "[PAD]",
+    "sep_token": "[SEP]",
+    "unk_token": "[UNK]"
+  },
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb74ab57d875b2fad8534a34bdadee966a6260c19a29765c1a6b25aceaf4fb05
+size 5304