Training in progress epoch 0

config.json

@@ -0,0 +1,164 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-large-bne",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Faa",
+    "1": "pp",
+    "2": "vmp",
+    "3": "da",
+    "4": "rg",
+    "5": "vsp",
+    "6": "Z",
+    "7": "Fat",
+    "8": "aq",
+    "9": "dd",
+    "10": "ao",
+    "11": "vmn",
+    "12": "Fx",
+    "13": "Fpa",
+    "14": "vsn",
+    "15": "px",
+    "16": "Fpt",
+    "17": "Fp",
+    "18": "Fh",
+    "19": "Fc",
+    "20": "sp",
+    "21": "pt",
+    "22": "pd",
+    "23": "vsg",
+    "24": "Fe",
+    "25": "p0",
+    "26": "vai",
+    "27": "de",
+    "28": "nc",
+    "29": "W",
+    "30": "vss",
+    "31": "Fia",
+    "32": "vms",
+    "33": "di",
+    "34": "rn",
+    "35": "vap",
+    "36": "Fd",
+    "37": "vmg",
+    "38": "vsm",
+    "39": "vmi",
+    "40": "Zm",
+    "41": "dn",
+    "42": "van",
+    "43": "vag",
+    "44": "Fs",
+    "45": "I",
+    "46": "pn",
+    "47": "vsi",
+    "48": "Zp",
+    "49": "pe",
+    "50": "Fz",
+    "51": "pi",
+    "52": "vas",
+    "53": "dt",
+    "54": "cs",
+    "55": "pr",
+    "56": "np",
+    "57": "vam",
+    "58": "Fg",
+    "59": "vmm",
+    "60": "i",
+    "61": "X",
+    "62": "dp",
+    "63": "Fit",
+    "64": "Y",
+    "65": "cc"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Faa": 0,
+    "Fat": 7,
+    "Fc": 19,
+    "Fd": 36,
+    "Fe": 24,
+    "Fg": 58,
+    "Fh": 18,
+    "Fia": 31,
+    "Fit": 63,
+    "Fp": 17,
+    "Fpa": 13,
+    "Fpt": 16,
+    "Fs": 44,
+    "Fx": 12,
+    "Fz": 50,
+    "I": 45,
+    "W": 29,
+    "X": 61,
+    "Y": 64,
+    "Z": 6,
+    "Zm": 40,
+    "Zp": 48,
+    "ao": 10,
+    "aq": 8,
+    "cc": 65,
+    "cs": 54,
+    "da": 3,
+    "dd": 9,
+    "de": 27,
+    "di": 33,
+    "dn": 41,
+    "dp": 62,
+    "dt": 53,
+    "i": 60,
+    "nc": 28,
+    "np": 56,
+    "p0": 25,
+    "pd": 22,
+    "pe": 49,
+    "pi": 51,
+    "pn": 46,
+    "pp": 1,
+    "pr": 55,
+    "pt": 21,
+    "px": 15,
+    "rg": 4,
+    "rn": 34,
+    "sp": 20,
+    "vag": 43,
+    "vai": 26,
+    "vam": 57,
+    "van": 42,
+    "vap": 35,
+    "vas": 52,
+    "vmg": 37,
+    "vmi": 39,
+    "vmm": 59,
+    "vmn": 11,
+    "vmp": 2,
+    "vms": 32,
+    "vsg": 23,
+    "vsi": 47,
+    "vsm": 38,
+    "vsn": 14,
+    "vsp": 5,
+    "vss": 30
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14488294d6eee3e0bc192cb1dc25c76de5f086b66903a1fd74515a412eb87c37
+size 1417546912

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}