Training in progress, step 500

config.json

@@ -1,6 +1,5 @@
 {
-  "_name_or_path": "distilgpt2",
-  "_num_labels": 1,
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -9,20 +8,14 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "id2label": {
-    "0": "LABEL_0"
-  },
   "initializer_range": 0.02,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 6,
+  "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d57ae9a1cc33e21fb93b0a90b7b87ee86f6c4d57f2f1ee7fc5a1bf207ce2177
-size 327674773
+oid sha256:422402454b6dd7f0adfac90bbcf6d3460ef1cd469a15901a3081759c90d66cd0
+size 497807197

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad9344fbec9061dc47dc600ce3a649710d6b618f2fe716b56d3b03f716ba8f16
+oid sha256:70a337c77fb5d7dd9b98604123a7c13d5eb289d52867d7626d95b30152dda55b
 size 4027