iter_count = 1

config.json

@@ -1,43 +1,9 @@
 {
-  "_name_or_path": "li-jay-cs/gpt2-medium-supervised-summarize-checkpoint",
-  "activation_function": "gelu_new",
   "architectures": [
-    "GPT2LMHeadModel"
+    "PPOModel"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "end_token_id": 50256,
-  "eos_token_id": 50256,
-  "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
-  "n_inner": null,
-  "n_layer": 24,
-  "n_positions": 1024,
-  "n_special": 0,
-  "pad_token_id": 50256,
-  "predict_special_tokens": true,
-  "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,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
+  "model_type": "ppo",
+  "sft_model_path": "li-jay-cs/gpt2-medium-supervised-summarize-checkpoint",
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
-  "use_cache": false,
-  "vocab_size": 50257
+  "transformers_version": "4.36.2"
 }

generation_config.json

@@ -1,8 +1,4 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
-  "pad_token_id": 50256,
-  "transformers_version": "4.36.2",
-  "use_cache": false
+  "transformers_version": "4.36.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1527fc4813712eb58687816a98f31ed9931a6629773833907a5d340871e6285
-size 1419322880
+oid sha256:ebabca746e91a47a964cf7faa724d78cf074674eeb567d6b9f58ef29fab9fa3b
+size 2838660960