Training in progress, step 500

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-NAME_STUDENT",
+    "2": "B-URL_PERSONAL",
+    "3": "B-ID_NUM",
+    "4": "B-STREET_ADDRESS",
+    "5": "B-PHONE_NUM",
+    "6": "B-EMAIL",
+    "7": "B-USERNAME",
+    "8": "I-NAME_STUDENT",
+    "9": "I-URL_PERSONAL",
+    "10": "I-ID_NUM",
+    "11": "I-STREET_ADDRESS",
+    "12": "I-PHONE_NUM"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EMAIL": 6,
+    "B-ID_NUM": 3,
+    "B-NAME_STUDENT": 1,
+    "B-PHONE_NUM": 5,
+    "B-STREET_ADDRESS": 4,
+    "B-URL_PERSONAL": 2,
+    "B-USERNAME": 7,
+    "I-ID_NUM": 10,
+    "I-NAME_STUDENT": 8,
+    "I-PHONE_NUM": 12,
+    "I-STREET_ADDRESS": 11,
+    "I-URL_PERSONAL": 9,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a1444d5c060c08d8aed7a6e510dff93394297fb0f9e18488e3ca8e019a903e
+size 1109876260

runs/Jan29_08-18-55_9e411f035124/events.out.tfevents.1706516345.9e411f035124.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe8e643878929614184fce9e8409fa9d39c7c968dd7aa6270496bcb6794cbfa
+size 5084

runs/Jan29_08-18-55_9e411f035124/events.out.tfevents.1706516456.9e411f035124.26.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5bbb3455481ef3413bca5d94b4da8354ff6dcd8a5b6de3f568ab07d804523b
+size 5392

runs/Jan29_08-18-55_9e411f035124/events.out.tfevents.1706516564.9e411f035124.26.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f69d93f375edce4699c9e2feb6ccf36be16ed00e71b8287ddb557f6c64908d1d
+size 5084

runs/Jan29_08-23-08_9e411f035124/events.out.tfevents.1706516594.9e411f035124.26.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ffe24feb918e9bc8f47dde54cb7a40bebf1bb44f87a0765568f9a059d9c03f0
+size 8992

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
+size 17082854

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "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": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "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>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d451eb1aa8a16a791281871c6d91322e8267a7b2f36f0b5ffc4298ced45c9e
+size 4283