Training in progress, epoch 1

config.json

@@ -1,24 +1,19 @@
 {
-  "_name_or_path": "albert-base-v2",
+  "_name_or_path": "bert-base-multilingual-cased",
   "architectures": [
-    "AlbertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0,
-  "bos_token_id": 2,
-  "classifier_dropout_prob": 0.1,
-  "down_scale_factor": 1,
-  "embedding_size": 128,
-  "eos_token_id": 3,
-  "gap_size": 0,
-  "hidden_act": "gelu_new",
-  "hidden_dropout_prob": 0,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
     "0": "negative",
     "1": "positive"
   },
   "initializer_range": 0.02,
-  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
     "negative": 0,
@@ -26,17 +21,20 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_groups": 1,
   "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
   "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",
   "torch_dtype": "float32",
   "transformers_version": "4.45.1",
   "type_vocab_size": 2,
-  "vocab_size": 30000
+  "use_cache": true,
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79fc5f043cd3fbed4f63373794507f10d3daf7c31aab1edec19e055474bb828e
-size 46743912
+oid sha256:d9130e8a80aaef7178823b318bf4ce0b78e214805182086e97642a666abd301f
+size 711443456

runs/Nov06_18-58-33_d06da987adfc/events.out.tfevents.1730919517.d06da987adfc.30.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffe279ad463b122cafa1a995b56f069d2a311aa7a9b92be15d2bece826b400e0
-size 7218
+oid sha256:6b0f2c2ff65ddb3c19081506c7f0b42296054b1110c6998fe5b910af8c2172f5
+size 7851

runs/Nov06_19-47-25_d06da987adfc/events.out.tfevents.1730922451.d06da987adfc.30.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0000314b3952dd9f17f79163c079965b40e53c4165fe306efca8aa79270df199
+size 6382

special_tokens_map.json

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

tokenizer_config.json

@@ -1,22 +1,22 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<pad>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<unk>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
+    "101": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "3": {
+    "102": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,26 +32,24 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "103": {
       "content": "[MASK]",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "eos_token": "[SEP]",
-  "keep_accents": false,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "remove_space": true,
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "tokenizer_class": "AlbertTokenizer",
-  "unk_token": "<unk>"
+  "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:d6b885508fa6a1dfde1aa6142297249713cd200d625db15d887847a7324a5bd8
+oid sha256:06509947117a151f258dfa6e923c9fb87edc41cfbc11d96b4ad738f6b4f31893
 size 5240