iter_count = 400

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2-medium",
+  "_name_or_path": "li-jay-cs/gptj-supervised-summarize-checkpoint",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -7,18 +7,18 @@
   "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_embd": 768,
+  "n_head": 12,
   "n_inner": null,
-  "n_layer": 24,
+  "n_layer": 12,
   "n_positions": 1024,
-  "n_special": 0,
-  "predict_special_tokens": true,
+  "pad_token_id": 50256,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -36,6 +36,6 @@
   },
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,7 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.35.2"
+  "pad_token_id": 50256,
+  "transformers_version": "4.35.2",
+  "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:349a976f266e671388c85be4bb8781fb727c4cceac4bd19e55acaab3a090e1fd
-size 1419322880
+oid sha256:348442616096d063f910b18e3d8fd2a7dc95fdd104cd173b9a02fc4e879e5317
+size 497774208