End of training

config.json

@@ -1,31 +1,24 @@
 {
-  "activation_function": "gelu_new",
   "architectures": [
-    "GPT2LMHeadModel"
+    "BertLMHeadModel"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 6,
-  "n_positions": 514,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.32.0",
+  "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 52000
 }

generation_config.json

@@ -1,6 +1,5 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "pad_token_id": 0,
   "transformers_version": "4.32.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a54da3a79c5d622a28985f4a3fddee954251b7b458fad654901499e7d50842
-size 331462549
+oid sha256:9bf1f3dc55bc2205f00a7f8d0691e0f402de989aa5100ca8f6997ff294bb2fcd
+size 334056757

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd9f37f3003f669d389650c4c24378a2e3a556924b4b5b2887c369f0a38e840d
+oid sha256:2fcdcbcdc06580cc4d992a218697fd3ef45dcb0c4572cc8f290ae3c4acb1468c
 size 4091