Training in progress, epoch 1

config.json

@@ -1,12 +1,13 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "CamembertForSequenceClassification"
   ],
   "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,
@@ -24,12 +25,12 @@
     "LABEL_2": 2,
     "LABEL_3": 3
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "camembert",
+  "num_attention_head": 12,
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
@@ -37,5 +38,5 @@
   "transformers_version": "4.25.1",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 25005
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac76ec9e39bb116391f667a8eefeb79e45bb0df5fdf72af8cd6aedf2b7839bd0
-size 1112257461
+oid sha256:d3267161ae54a89b44f0fa79206215719ad91397a2c2cafdd25955d10119d5e6
+size 421060533

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
+size 904693

special_tokens_map.json

@@ -1,11 +1,16 @@
 {
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
-size 17082660
+oid sha256:98a9a1aab83c245fe4a62898eaa94e4782ccafa043d53be646a62b1887a02597
+size 2179217

tokenizer_config.json

@@ -1,4 +1,9 @@
 {
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
@@ -10,11 +15,12 @@
     "rstrip": false,
     "single_word": false
   },
-  "model_max_length": 512,
-  "name_or_path": "xlm-roberta-base",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "sp_model_kwargs": {},
   "special_tokens_map_file": null,
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "tokenizer_class": "CamembertTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:091c60b06d39055cad3b62266cbdbd12ca8b5a9947178e0510554aa205b20d2a
+oid sha256:5a5fd828deca4f7e226481be1581298215c8badbeadf5e5aa902fbd98f945ea0
 size 3451