Large version

config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "gpt2-medium",
+  "_name_or_path": "gpt2-large",
+  "_num_labels": 1,
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -9,17 +10,21 @@
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
+  "n_embd": 1280,
+  "n_head": 20,
   "n_inner": null,
-  "n_layer": 24,
+  "n_layer": 36,
   "n_positions": 1024,
-  "n_special": 0,
-  "predict_special_tokens": true,
   "resid_pdrop": 0.1,
   "summary_activation": null,
   "summary_first_dropout": 0.1,

eval_results.txt

@@ -0,0 +1 @@
+perplexity = tensor(1.4023)

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9715692bc39de529ffbc531552d3caed9d7a279668561b54466cf2b531391a
-size 1444586106
+oid sha256:f0b6c2a4b7220946b85287fca8fd4216196b65ff95aa4a7990845f99ff23c74c
+size 3134059791

tokenizer_config.json

@@ -1 +1 @@
-{"errors": "replace", "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, "do_lower_case": false, "model_max_length": 1024, "name_or_path": "gpt2-medium"}
+{"errors": "replace", "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, "do_lower_case": false, "model_max_length": 1024, "name_or_path": "gpt2-large"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41b24f51d44b4f45df060ae252d06bde46dac4bdcd7c662d0b6d618ff4e57b30
+oid sha256:14033e81fade7a78b5d99882645fb288752db52662c846829d9bed5d297c99fd
 size 1455