Retrain model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "dialogpt-twitter-ubuntu-finetuned/checkpoint-4000",
+  "_name_or_path": "microsoft/DialoGPT-medium",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,7 +8,6 @@
   "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 +17,9 @@
   "n_inner": null,
   "n_layer": 24,
   "n_positions": 1024,
+  "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,
@@ -31,7 +32,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.2",
+  "transformers_version": "4.12.0",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bac0798dd83629403f08769c97764934583bb21d83dd35ba9b874d4236a606e
-size 1444586120
+oid sha256:28e212af58364a2dfb8a790b7a9f5fbf30925185159394029bf43a3d3d07b243
+size 1444581337

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d03349ac6933826c80971b9eb2582744858f835d60469deb0160e74961431e3
+size 2799