Update to best checkpoint (epoch=85, val_loss=0.3335)

config.json

@@ -2,6 +2,7 @@
   "architectures": [
     "HELMBertForMaskedLM"
   ],
+  "attention_probs_dropout_prob": 0.1,
   "auto_map": {
     "AutoConfig": "configuration_helmbert.HELMBertConfig",
     "AutoModel": "modeling_helmbert.HELMBertModel",
@@ -9,8 +10,9 @@
     "AutoModelForSequenceClassification": "modeling_helmbert.HELMBertForSequenceClassification",
     "AutoTokenizer": "tokenization_helmbert.HELMBertTokenizer"
   },
-  "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 1,
+  "classifier_dropout": 0.1,
+  "classifier_num_layers": 0,
   "dtype": "float32",
   "eos_token_id": 2,
   "hidden_dropout_prob": 0.1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c735315218d2e8864e4ea93f2c76d8eef58f78989f007b6a2bf446af6657a194
+oid sha256:6e05d977e54557fd1703afc5c053dd625bb1473621df3fc913a3c8547826b9fe
 size 219166144

special_tokens_map.json

@@ -1,9 +1,51 @@
 {
-  "bos_token": "@",
-  "cls_token": "@",
-  "eos_token": "\n",
-  "mask_token": "¶",
-  "pad_token": " ",
-  "sep_token": "\n",
-  "unk_token": "§"
+  "bos_token": {
+    "content": "@",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "@",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "\n",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "¶",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": " ",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "\n",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "§",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,7 +1,4 @@
 {
-  "auto_map": {
-    "AutoTokenizer": ["tokenization_helmbert.HELMBertTokenizer", null]
-  },
   "added_tokens_decoder": {
     "0": {
       "content": " ",
@@ -44,6 +41,12 @@
       "special": true
     }
   },
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_helmbert.HELMBertTokenizer",
+      null
+    ]
+  },
   "bos_token": "@",
   "clean_up_tokenization_spaces": false,
   "cls_token": "@",