Training in progress, epoch 1

config.json

@@ -11,15 +11,15 @@
   "eos_token_id": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "is_decoder": false,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
   "pooler_fc_size": 768,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7359dfece60eea8387d874b6cb69665b9baae3f40236d32fad306b602f1e2edf
-size 409100240
+oid sha256:0f06c2d90b2f0872e345c905231585bf9bc0180ed36815814463d9b5195ffc0c
+size 1302144896

tokenizer.json

@@ -6,14 +6,7 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,