Training in progress, step 500

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bhavikardeshna/xlm-roberta-base-vietnamese",
+  "architectures": [
+    "XLMRobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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,
+  "language": "english",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "name": "XLMRoberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd392aa129262e0001b90e27bd2be5b46a0288d77bb9027be78ce96dea7abcd3
+size 1109891117

runs/Mar14_02-48-53_97715992196b/1678762141.8601477/events.out.tfevents.1678762141.97715992196b.1141.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83fb9f6bff6671cb07956c3296dfb7c60cefbc56ad884313e076d8a07fd01779
+size 5677

runs/Mar14_02-48-53_97715992196b/events.out.tfevents.1678762141.97715992196b.1141.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e3693ac690b876b8821d5ec0e27c2ea67b94d516b4f7f7bf4e77fc05bb9bbd3
+size 3979

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad94b16898f50c1c065e4bad0b52add2ebd067a544182538c331a1726ef14360
+size 17082994

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "full_tokenizer_file": null,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "bhavikardeshna/xlm-roberta-base-vietnamese",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/transformers/b285d730ad6193f7e96b41152fbc5fb05620f0961f6f513e2d36868dfb1eb2a7.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dbab29cb83c4d9ccdc5e3e0624607914391ee0584ee324d2cbbd721260e02b2
+size 3515