Training in progress, step 160

config.json

@@ -1,23 +1,24 @@
 {
-  "_name_or_path": "FacebookAI/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,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "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",
@@ -25,5 +26,5 @@
   "transformers_version": "4.44.2",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 25005
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66509c3ec9e04260525daff1420e0a356e62fc89e975c3b5f2a462249da19e3f
-size 1112205008
+oid sha256:ff208e415728bfe566dbc98e8ce0f9839d242c8a613d7f5d13a57d10118ea2a3
+size 421007928

sentencepiece.bpe.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
-size 5069051
+oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
+size 904693

special_tokens_map.json

@@ -1,4 +1,9 @@
 {
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a514807cffabd8abaf028cfaffe7ff0c4f60b97ea2db80c41f14172ae6b018ca
-size 17082987
+oid sha256:72628f274f21abc796b20544930636121fe0a9c2cd9d7fb0732d3aed558d6824
+size 2179643

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "<s>NOTUSED",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "</s>NOTUSED",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -32,7 +32,31 @@
       "single_word": false,
       "special": true
     },
-    "250001": {
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<_>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25004": {
       "content": "<mask>",
       "lstrip": true,
       "normalized": false,
@@ -41,14 +65,20 @@
       "special": true
     }
   },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
   "unk_token": "<unk>"
 }