Training in progress, epoch 1

config.json

@@ -1,19 +1,20 @@
 {
-  "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
+  "_name_or_path": "bert-base-multilingual-cased",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "hidden_size": 768,
   "id2label": {
     "0": "Female",
     "1": "Male"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
+  "intermediate_size": 3072,
   "label2id": {
     "Female": 0,
     "Male": 1
@@ -24,12 +25,16 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "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",
   "problem_type": "single_label_classification",
-  "tokenizer_class": "XLMRobertaTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.26.0",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250037
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e443b1989a3ebae25bf763267bf0cac0a4c9b08e006e7bcfa5cad2a3ee5622ef
-size 470690933
+oid sha256:13a03d159d1ace0f652945036c9f90824e20af0bcca54113edc9b212e2c82825
+size 711492725

runs/Jan25_16-24-58_fee55ac23edd/1674664022.7144568/events.out.tfevents.1674664022.fee55ac23edd.1985.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c42c97236992b4e4cba69ef8d1987cc7ab4e5d23518b6469f3a8a8e84f59a65
+size 5670

runs/Jan25_16-24-58_fee55ac23edd/events.out.tfevents.1674664022.fee55ac23edd.1985.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5038365d5f2403f7c1ce8021a4c66dacfb134bb21ce2927d7435dc81521156f8
+size 4723

special_tokens_map.json

@@ -1,9 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "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 sha256:2bae0289b9bb66bfbf85d834f6313ebd8e40f484df2bd0351539e74a0e4ddeb4
-size 17098081
+oid sha256:7529a33b1945f06664a6266d6d5eff9b5545890202e86fb05702f6f01d4b8f44
+size 2919615

tokenizer_config.json

@@ -1,21 +1,14 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--microsoft--Multilingual-MiniLM-L12-H384/snapshots/6e8c1ec6b4ec4e3fc6eb7d2cd834fcd582b61daf/special_tokens_map.json",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-multilingual-cased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7159ca1fc46db0dce023cada6f0be9f6a81e740e044dcc3cbffc96ac42114f78
+oid sha256:b306338565241b3acd57495bad6a78ac89e436a5add531f0a2e9ddf4a575745c
 size 3515