Training in progress, epoch 1

config.json

@@ -1,52 +1,160 @@
 {
-  "_name_or_path": "markussagen/xlm-roberta-longformer-base-4096",
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
   "architectures": [
-    "LongformerForTokenClassification"
+    "XLMRobertaForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "attention_window": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
-  ],
   "bos_token_id": 0,
+  "classifier_dropout": null,
   "eos_token_id": 2,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "O",
-    "1": "B-content",
-    "2": "I-content"
+    "0": "I-PERSON",
+    "1": "B-TRANSPORTATION",
+    "2": "I-ROLE",
+    "3": "B-EVENT",
+    "4": "I-TIME",
+    "5": "I-TRANSPORTATION",
+    "6": "I-COUNTRY",
+    "7": "I-LANGUAGE",
+    "8": "B-LANGUAGE",
+    "9": "I-LOCATION",
+    "10": "B-DEGREE",
+    "11": "I-DOCUMENT",
+    "12": "B-PERSON",
+    "13": "B-SOCIAL_MEDIA",
+    "14": "B-COUNTRY",
+    "15": "B-SCHOOL",
+    "16": "I-ORGANIZATION",
+    "17": "I-QUANTITY",
+    "18": "I-SONG",
+    "19": "I-NUMBER",
+    "20": "I-FOOD",
+    "21": "B-TEMPERATURE",
+    "22": "I-TOTAL_AREA",
+    "23": "I-TOTAL_VOLUME",
+    "24": "I-DISEASE",
+    "25": "B-RELATIONSHIP",
+    "26": "I-EVENT",
+    "27": "B-GENDER",
+    "28": "B-QUANTITY",
+    "29": "I-TEMPERATURE",
+    "30": "I-DEGREE",
+    "31": "B-EDUCATION",
+    "32": "B-LOCATION",
+    "33": "B-NUMBER",
+    "34": "I-RELATIONSHIP",
+    "35": "I-EDUCATION",
+    "36": "I-ORDINAL",
+    "37": "I-SCHOOL",
+    "38": "B-NATIONALITY",
+    "39": "I-AGE",
+    "40": "O",
+    "41": "B-MONEY",
+    "42": "B-FOOD",
+    "43": "I-MONEY",
+    "44": "B-SONG",
+    "45": "B-TOTAL_AREA",
+    "46": "I-NATIONALITY",
+    "47": "I-RANK",
+    "48": "B-ROLE",
+    "49": "B-ORDINAL",
+    "50": "B-PRODUCT",
+    "51": "B-TIME",
+    "52": "B-AGE",
+    "53": "B-ORGANIZATION",
+    "54": "I-DATE",
+    "55": "B-DISEASE",
+    "56": "B-SPORT",
+    "57": "B-TOTAL_VOLUME",
+    "58": "I-PRODUCT",
+    "59": "B-RANK",
+    "60": "B-DATE",
+    "61": "I-GENDER",
+    "62": "B-DOCUMENT",
+    "63": "I-SPORT"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "B-content": 1,
-    "I-content": 2,
-    "O": 0
+    "B-AGE": 52,
+    "B-COUNTRY": 14,
+    "B-DATE": 60,
+    "B-DEGREE": 10,
+    "B-DISEASE": 55,
+    "B-DOCUMENT": 62,
+    "B-EDUCATION": 31,
+    "B-EVENT": 3,
+    "B-FOOD": 42,
+    "B-GENDER": 27,
+    "B-LANGUAGE": 8,
+    "B-LOCATION": 32,
+    "B-MONEY": 41,
+    "B-NATIONALITY": 38,
+    "B-NUMBER": 33,
+    "B-ORDINAL": 49,
+    "B-ORGANIZATION": 53,
+    "B-PERSON": 12,
+    "B-PRODUCT": 50,
+    "B-QUANTITY": 28,
+    "B-RANK": 59,
+    "B-RELATIONSHIP": 25,
+    "B-ROLE": 48,
+    "B-SCHOOL": 15,
+    "B-SOCIAL_MEDIA": 13,
+    "B-SONG": 44,
+    "B-SPORT": 56,
+    "B-TEMPERATURE": 21,
+    "B-TIME": 51,
+    "B-TOTAL_AREA": 45,
+    "B-TOTAL_VOLUME": 57,
+    "B-TRANSPORTATION": 1,
+    "I-AGE": 39,
+    "I-COUNTRY": 6,
+    "I-DATE": 54,
+    "I-DEGREE": 30,
+    "I-DISEASE": 24,
+    "I-DOCUMENT": 11,
+    "I-EDUCATION": 35,
+    "I-EVENT": 26,
+    "I-FOOD": 20,
+    "I-GENDER": 61,
+    "I-LANGUAGE": 7,
+    "I-LOCATION": 9,
+    "I-MONEY": 43,
+    "I-NATIONALITY": 46,
+    "I-NUMBER": 19,
+    "I-ORDINAL": 36,
+    "I-ORGANIZATION": 16,
+    "I-PERSON": 0,
+    "I-PRODUCT": 58,
+    "I-QUANTITY": 17,
+    "I-RANK": 47,
+    "I-RELATIONSHIP": 34,
+    "I-ROLE": 2,
+    "I-SCHOOL": 37,
+    "I-SONG": 18,
+    "I-SPORT": 63,
+    "I-TEMPERATURE": 29,
+    "I-TIME": 4,
+    "I-TOTAL_AREA": 22,
+    "I-TOTAL_VOLUME": 23,
+    "I-TRANSPORTATION": 5,
+    "O": 40
   },
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 4098,
-  "model_type": "longformer",
+  "max_position_embeddings": 1024,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "onnx_export": false,
   "output_past": true,
   "pad_token_id": 1,
-  "sep_token_id": 2,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
   "type_vocab_size": 1,
+  "use_cache": true,
   "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af1826976de6ef4c8bd227cbc881848dab7e09528e776a24661bb227d5a3235
-size 602972630
+oid sha256:74edb2bcc1e7f35835570d6293e95c5ea40ae9d04a708f51e6d3841758566e63
+size 1111599872

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69564b696052886ed0ac63fa393e928384e0f8caada38c1f4864a9bfbf379c15
-size 17098273
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -46,10 +46,9 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "model_max_length": 4096,
+  "model_max_length": 1024,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "sp_model_kwargs": {},
   "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cebb45392ada4e096b7de83626f6af596c7812a19186c5e2a5f56a1918c95ff
-size 4984
+oid sha256:0f66ddaffcc2cba5568017fc2c01a206d4ca9a797c9721dad0fc518c3fa4520b
+size 5176