Training in progress, step 50

config.json

@@ -1,10 +1,41 @@
 {
+  "_name_or_path": "li-jay-cs/gptj-supervised-summarize-checkpoint",
+  "activation_function": "gelu_new",
   "architectures": [
     "GPTRewardModel"
   ],
-  "model_path": "li-jay-cs/gptj-supervised-summarize-checkpoint",
-  "model_type": "reward",
-  "tokenizer_id": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "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
+    }
+  },
   "torch_dtype": "float16",
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a9c0b75a1534fe3986001cf767b51f3af0a2a84797dc5a55e1d2fbe41f278c0
+oid sha256:603ab16770a0d2f78a9d189d97e2ffa1853acf497c938ced4b2ea6fcccef49a7
 size 575049586