update

config.json

@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "finetuning_task": null,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "num_labels": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pruned_heads": {},
+  "resid_pdrop": 0.1,
+  "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
+    }
+  },
+  "torchscript": false,
+  "vocab_size": 50257
+}

metrics.json

@@ -0,0 +1 @@
+{"2000.perplexity": 1.7814306020736694, "4000.perplexity": 1.7171242237091064, "6000.perplexity": 1.7327085733413696, "8000.perplexity": 1.6859264373779297, "10000.perplexity": 1.6911686658859253, "12000.perplexity": 1.7163463830947876, "best_perp": 1.6859264373779297, "best_perp_step": 8000}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4da5a849f9d5ef2a993e9645afec4690b6e21e8e15cc93dabf6db2b47d06e2
+size 548125486

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "max_len": 1024, "init_inputs": []}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35440027d6241389eb596b90f63548ea8bbdad1971ddfb22b8883dbfbc86f82d
+size 1264