Training in progress, step 500

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForMaskedLM"
@@ -13,12 +12,11 @@
   "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.26.0",
-  "vocab_size": 30522
+  "vocab_size": 20000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e496d48edd743d1a0cb91a33e5f71b5ae574ca4a6ec1d69f69f6f11d89b06426
-size 267978033
+oid sha256:4731a16c43aa6c9d3a35e4b55f8a49a70dc84223483f1213cc2982f7220c9a54
+size 235612401

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 sha256:5d7e2476801831ff09f6e9407f893227bf3c6fe4829ae426044ef5d4ba56de38
+oid sha256:896911aad1017ed476ddc3d99e0ab5ac16a6dda3e0974b7d1298164cf0362c15
 size 3515