Training in progress, epoch 1

config.json

@@ -1,18 +1,15 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "vietgpt/bert-30M-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "dim": 768,
-  "dropout": 0.1,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
-  "hidden_dim": 3072,
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 512,
   "id2label": {
     "0": 0,
     "1": 1,
@@ -193,7 +190,7 @@
     "176": 176
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1024,
   "label2id": {
     "0": 0,
     "1": 1,
@@ -373,23 +370,18 @@
     "175": 175,
     "176": 176
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
   "model_type": "bert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "tokenizer_class": "BartphoTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.37.1",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 50001
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c130907e71d640b7522ec8f93123c7c12a43029cc31249c10e930d83c64c157
-size 438496948
+oid sha256:9e5f97cdf749d94ea1d5590b1c780f34c602d9ca463a371b1304f4554a09bb35
+size 138527692

runs/Jan26_07-36-30_9533dac6c070/events.out.tfevents.1706254592.9533dac6c070.2896.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54caf2d281bd8cc135aeb1b620380fec697690c67671934d03ff2dd1f0244ddf
+size 10068

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63e0e8f2d912f8ebf14402e66c2afef07b078099b953efb690d18c6c00af23a
+size 1027111

special_tokens_map.json

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

tokenizer_config.json

@@ -1,55 +1,55 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
+    "50000": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BartphoTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7047f50dbd21ea1978181102ffd71486ba18eb5e48f9bcb474210f31905dda
+oid sha256:d2f9eccc3448f3efb92df68c6f7f0bdb64758addb2976e0f7dffe8d74f247b4f
 size 4728