Training in progress, step 500

config.json

@@ -1,34 +1,22 @@
 {
-  "_name_or_path": "NeverLearn/gpt2-wikitext2",
+  "_name_or_path": "openai-community/gpt2",
   "activation_function": "gelu_new",
   "architectures": [
-    "BertForMaskedLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
-  "classifier_dropout": null,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
   "layer_norm_epsilon": 1e-05,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -46,7 +34,6 @@
   },
   "torch_dtype": "float32",
   "transformers_version": "4.40.0",
-  "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 50257
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c829845c9837772684bddeca7d32d8b0a4172cb0b8382c4ce9a8cedfd971583f
-size 498785764
+oid sha256:781696faa4767e8e3c880daef349ff82f4817eb73b77f1f6c2cbe6d9c6af75ae
+size 497774208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8016abe50aa5f911d6aa79bfce87a115b93cf85fe553553bdf84e6aa86490df
+oid sha256:e1084752d82de5d3be258a37d82b895e4a218fc40d4156f7b87e8cd7c2794ddc
 size 4984