Add files using upload-large-folder tool

config.json

@@ -0,0 +1,31 @@
+{
+  "model_type": "gpt2",
+  "architecture": "GPT2LMHeadModel",
+  "vocab_size": 32000,
+  "n_positions": 1024,
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_layer": 12,
+  "n_head": 12,
+  "activation_function": "gelu_new",
+  "resid_pdrop": 0.1,
+  "embd_pdrop": 0.1,
+  "attn_pdrop": 0.1,
+  "layer_norm_epsilon": 1e-5,
+  "initializer_range": 0.02,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "summary_activation": null,
+  "summary_proj_to_labels": true,
+  "summary_first_dropout": 0.1,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 512,
+      "temperature": 0.8,
+      "top_p": 0.9
+    }
+  }
+}

training_args.json

@@ -0,0 +1,22 @@
+{
+  "output_dir": "./models/literary-lm",
+  "overwrite_output_dir": true,
+  "num_train_epochs": 10,
+  "per_device_train_batch_size": 8,
+  "per_device_eval_batch_size": 8,
+  "gradient_accumulation_steps": 4,
+  "learning_rate": 5e-5,
+  "weight_decay": 0.01,
+  "warmup_steps": 500,
+  "logging_steps": 100,
+  "save_steps": 1000,
+  "eval_steps": 500,
+  "save_total_limit": 3,
+  "fp16": true,
+  "dataloader_num_workers": 4,
+  "load_best_model_at_end": true,
+  "metric_for_best_model": "perplexity",
+  "greater_is_better": false,
+  "evaluation_strategy": "steps",
+  "save_strategy": "steps"
+}