Training in progress, epoch 1

config.json

@@ -11,7 +11,7 @@
   "hidden_act": "gelu",
   "hidden_dim": 3072,
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "hidden_size": 256,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
@@ -19,8 +19,8 @@
   "model_type": "bert",
   "n_heads": 12,
   "n_layers": 6,
-  "num_attention_heads": 8,
-  "num_hidden_layers": 8,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:120433dbb8bd67a52be5b8bda423d0c1c5d1543038196937d5c1f8fdf4a5166d
-size 199130417
+oid sha256:fe9655ceaaeee1d419228cf250be3c4dd991ebec18f2f8d37217aaac351c8663
+size 61518732

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,