Training in progress, epoch 1

config.json

@@ -1,62 +1,55 @@
 {
-  "_name_or_path": "xlm-roberta-large",
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
   "architectures": [
-    "XLMRobertaForTokenClassification"
+    "DistilBertForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "O",
-    "1": "B-GCNUM",
-    "2": "I-GCNUM",
-    "3": "B-BGNUM",
-    "4": "I-BGNUM",
-    "5": "B-DATE",
-    "6": "I-DATE",
-    "7": "B-ORG",
-    "8": "I-ORG",
+    "1": "B-ORG",
+    "2": "I-ORG",
+    "3": "B-GCNUMBER",
+    "4": "I-GCNUMBER",
+    "5": "B-BGNUMBER",
+    "6": "I-BGNUMBER",
+    "7": "B-NAME",
+    "8": "I-NAME",
     "9": "B-LOCATION",
     "10": "I-LOCATION",
-    "11": "B-NAME",
-    "12": "I-NAME",
-    "13": "B-BARCODE",
-    "14": "I-BARCODE"
+    "11": "B-COUNTRY",
+    "12": "I-COUNTRY"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
   "label2id": {
-    "B-BARCODE": 13,
-    "B-BGNUM": 3,
-    "B-DATE": 5,
-    "B-GCNUM": 1,
+    "B-BGNUMBER": 5,
+    "B-COUNTRY": 11,
+    "B-GCNUMBER": 3,
     "B-LOCATION": 9,
-    "B-NAME": 11,
-    "B-ORG": 7,
-    "I-BARCODE": 14,
-    "I-BGNUM": 4,
-    "I-DATE": 6,
-    "I-GCNUM": 2,
+    "B-NAME": 7,
+    "B-ORG": 1,
+    "I-BGNUMBER": 6,
+    "I-COUNTRY": 12,
+    "I-GCNUMBER": 4,
     "I-LOCATION": 10,
-    "I-NAME": 12,
-    "I-ORG": 8,
+    "I-NAME": 8,
+    "I-ORG": 2,
     "O": 0
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.39.1",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ed4e8eaa451e94485ba892e8553dca04ba675f5a4002b607a9b8419c0b36623
-size 2235473356
+oid sha256:bc48b79aa22f8d405344b4b84be18703be0c91b08a4469d0190befecc6fee07c
+size 260815972

runs/Mar27_05-22-59_4912d2a8deb3/events.out.tfevents.1711516984.4912d2a8deb3.761.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3dd9319afb0e303dd235e8937de30130f9cb2b7516dacf601b2e6c59a0f6d1
+size 5974

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
-size 17082854
+oid sha256:cb26b43c98e8266ae3e99c2a583cf8315d73b33a17e6b20b4df7ff1f22392d34
+size 669021

tokenizer_config.json

@@ -1,54 +1,55 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
-      "content": "<mask>",
-      "lstrip": true,
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80aa69e3833c673c739daa7dd9edac9864e00a653bb6392fa3021a21901a2813
+oid sha256:ad9161d8770180991aa7b1b25e04dd570f1f8c61cfc32d52b3387bd2b0e45920
 size 4920