Upload 9 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34622a95d0c0c8cf6debe03a1c6deb186dbb0e440aa475586ce4cd981f77e478
+size 540279452

pretraining_results.json

@@ -0,0 +1,28 @@
+{
+  "train_loss": 3.6125041409141696,
+  "eval_loss": NaN,
+  "perplexity": NaN,
+  "total_steps": 8637,
+  "training_time_seconds": 6911.5204,
+  "samples_per_second": 19.994,
+  "config": {
+    "model_name": "vinai/phobert-base",
+    "max_length": "256",
+    "mlm_probability": "0.15",
+    "epochs": "3",
+    "batch_size": "2",
+    "gradient_accumulation_steps": "8",
+    "learning_rate": "5e-05",
+    "warmup_steps": "500",
+    "weight_decay": "0.01",
+    "data_dir": "/kaggle/working/Dataset/processed",
+    "output_dir": "/kaggle/working/models/phobert_pretrained",
+    "logs_dir": "/kaggle/working/models/phobert_pretrained/logs",
+    "device": "cuda",
+    "fp16": "True",
+    "logging_steps": "100",
+    "save_steps": "1000",
+    "eval_steps": "1000"
+  },
+  "timestamp": "2026-01-07T18:06:17.914554"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c30448e7d9063d3f2b05e0f106d9fe369d041c72420cd3b4b4b06433e0f1fcd2
+size 433288887

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}