Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/xtremedistil-l6-h256-uncased",
+  "_name_or_path": "google-bert/bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -8,13 +8,13 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 256,
+  "hidden_size": 768,
   "id2label": {
     "0": "NON-TOXIC",
     "1": "TOXIC"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1024,
+  "intermediate_size": 3072,
   "label2id": {
     "NON-TOXIC": 0,
     "TOXIC": 1
@@ -22,8 +22,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 6,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc9db100d46403947e2bcfb4873dead7956f29d25bd2e0028314c6653f867da0
-size 51014384
+oid sha256:8ad82ee2b55282fbbf5d317dfcb980b19d99c77d05aebb50a4b07f6b4b1eeded
+size 437958648

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -43,11 +43,9 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:718efc7b443f95173c376a317e2dc463120527b731cfe1c7721356c6d22fcfa7
+oid sha256:3e5f00d9cf9acf59b80ccb2a75c91a2f8fe93df2a733db26c23749af2fd68d02
 size 5176