Training in progress, epoch 1

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "bert-base-multilingual-uncased",
   "architectures": [
-    "RobertaForTokenClassification"
+    "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -58,16 +57,21 @@
     "I-PRODUCT": 16,
     "O": 0
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.12.5",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 105879
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73473e8a39e8ce3ff5a3e4cbc19748cd551574adc4d530a738c9013856539bc0
-size 496369457
+oid sha256:564c34fd9dc6c8036345e485ff87be744b4f8ee715d1ed989aab0bfca1d61202
+size 667211313

runs/Jan25_04-43-20_ip-172-31-23-147/1643085893.3787484/events.out.tfevents.1643085893.ip-172-31-23-147.4012.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42cfc4cab8edea7b053b54b019b43590aaf721088318df369677534cf5971f98
+size 4564

runs/Jan25_04-43-20_ip-172-31-23-147/events.out.tfevents.1643085893.ip-172-31-23-147.4012.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71de329e656d9d327b47d281860a728e3bfdab1ce91e39fb404b13f7bee6d163
+size 4822

special_tokens_map.json

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

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_prefix_space": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-uncased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38160c87c3396ec6cf7c0145b599d026b4ea40b2c884ee23582b9c761c3a919e
+oid sha256:c5a3f3e3ea26f6c01351d57e521e57aa44fcb2784e755b957504ff785050dd8a
 size 2863