Training in progress, epoch 1

added_tokens.json

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

config.json

@@ -1,31 +1,29 @@
 {
-  "_name_or_path": "bert-base-multilingual-cased",
+  "_name_or_path": "vinai/phobert-large",
   "architectures": [
-    "BertForMultipleChoice"
+    "RobertaForMultipleChoice"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "directionality": "bidi",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "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",
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.35.0",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 119547
+  "vocab_size": 64001
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4deef8b05ffb67fb758fc33c3eaaf8196bc9e0dfe1d9dd0d97f0c1793e8ecdf4
-size 711440380
+oid sha256:b66330d75d1ea11a10753137ddbce3152fded8af6ccef1d78b4cc2c91acced38
+size 1476705404

runs/Dec04_04-30-11_e5dd265fdcc1/events.out.tfevents.1701664217.e5dd265fdcc1.47.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a696f4ac14cdcb6ea4810cb2687341c1f69683d03686f40cf56531280ee1e7c
+size 4765

special_tokens_map.json

@@ -1,7 +1,9 @@
 {
-  "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": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,39 +1,39 @@
 {
   "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]",
+    "64000": {
+      "content": "<mask>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,15 +41,14 @@
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4037839c09e7ad5d0cc1d113d2cf643fa6575062a2bf153f037510ef75825423
+oid sha256:b589890c6b3f997f604558dd652533bdc3ec1519a4139da547b05f973d6b335c
 size 4155