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,
@@ -40,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.32.1",
+  "transformers_version": "4.33.1",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd336168a1f0c576cdb472d5366845266c3f7e95c472ea5062399fb324cc7371
-size 327674773
+oid sha256:b73660cddadea84f1cef78f38b8434dbac3c141999f1abfe9ab197db53539112
+size 497807197

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaf677570da6480fca12a34c8fb703edf62e2223898cc0379ad0bc21bb77bdbc
+oid sha256:917c3d60063ad243889f541f95ec1ed3d6bc7162be76afbff86747f5ed8d52a1
 size 4091