Update model

config.json

@@ -8,6 +8,7 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
+  "gradient_checkpointing": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -18,7 +19,6 @@
   "n_layer": 12,
   "n_positions": 1024,
   "resid_pdrop": 0.1,
-  "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
@@ -29,8 +29,7 @@
       "max_length": 1000
     }
   },
-  "torch_dtype": "float32",
-  "transformers_version": "4.11.3",
+  "transformers_version": "4.5.1",
   "use_cache": true,
   "vocab_size": 50257
 }

eval_results.txt

@@ -1 +1 @@
-perplexity = tensor(23.8079)
+perplexity = tensor(29.3612)

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ec045983bc9246842a8731795ab37d5993af3de6f6b0c71bd02992f1c361b3
+oid sha256:3351b33568e477ce26c7510c209d50751cf248d2ac53d6de9294afe52b637fd5
 size 510403817

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace"}