Training in progress, step 500

config.json

@@ -1,7 +1,7 @@
 {
   "activation": "gelu",
   "architectures": [
-    "DistilBertModel"
+    "DistilBertForMaskedLM"
   ],
   "attention_dropout": 0.1,
   "dim": 768,
@@ -18,5 +18,5 @@
   "sinusoidal_pos_embds": false,
   "torch_dtype": "float32",
   "transformers_version": "4.26.0",
-  "vocab_size": 20000
+  "vocab_size": 2000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92811d548c5911d9cd9ea803ac49b02def8d8c5c3b900d6b45018a03382919df
-size 233161117
+oid sha256:d1499b6bcb275ebe2fd7139931dcc03846161b92c998785973b247d0d1059867
+size 180244401

tokenizer_config.json

@@ -5,7 +5,7 @@
   "eos_token": "<|EOS|>",
   "mask_token": "<|MASK|>",
   "model_max_length": 1024,
-  "name_or_path": "gpt2",
+  "name_or_path": "alvarodt/geocoding",
   "pad_token": "<|PAD|>",
   "sep_token": "<|SEP|>",
   "special_tokens_map_file": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d204d38b1f742ed37a5851f0bf0a8b10855574b347998fe0577392c27ae1be11
+oid sha256:d2c3120c107c23e73082af191fc9aa6b292c8fa3ca7b00995e7bf8913c4653b7
 size 3515