Training in progress, epoch 0

config.json

@@ -1,15 +1,13 @@
 {
-  "_name_or_path": "distilroberta-base",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "RobertaForTokenClassification"
+    "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": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "B-forenames",
     "1": "I-forenames",
@@ -17,23 +15,22 @@
     "3": "I-surnames"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "B-forenames": 0,
     "B-surnames": 2,
     "I-forenames": 1,
     "I-surnames": 3
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "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": "4.31.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c84174970c74575a9a41ee15132b8cacaaa53db1ada5fa43a6f4b5f363d2555
-size 326158569
+oid sha256:af22976c7d931fd59e96f3ceb39203fd731ba8e0164453334e11109da219d615
+size 265498661

runs/Aug17_05-53-53_1307412cf5c4/events.out.tfevents.1692251636.1307412cf5c4.14228.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6930d15d0495e3bad28b02e3ecd8991e1a44148d14f3c3fee832d6838cff18
+size 4184

runs/Aug17_05-55-09_1307412cf5c4/events.out.tfevents.1692251714.1307412cf5c4.25486.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86d0a716261fa9476a3967e85e033d124eea6ed8db9d6960fea32eb6c137162
+size 4205

runs/Aug17_05-58-14_1307412cf5c4/events.out.tfevents.1692251899.1307412cf5c4.26617.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:644e00f2a65e02ca12ec8e088c5a60994adc004261db708b9d2a13abee03f79c
+size 4205

runs/Aug17_06-05-00_1307412cf5c4/events.out.tfevents.1692252305.1307412cf5c4.28683.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8644d6a1ccb462c0765d421522a9ca7b2628d905ba4ef304e41b22de2289fbe5
+size 4642

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_config.json

@@ -1,15 +1,13 @@
 {
-  "add_prefix_space": false,
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "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 sha256:34f490f2becda0f5c3dce0e5e3677a1ef31793dad06733c601485de7bf42e6b9
+oid sha256:c33d5cfe4d0bf7a8500615a597b1f6a2a0c8860bb344d9ee2d8e5fca57dadbc5
 size 3963