riddle me this gpt2

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2-large",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "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": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76930fca9a5a89fb7aa3cf5bb2dd43b669166fc1d293309c90c475f9a3151866
+size 3134035005

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2-large",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.2636232214458918,
+    "train_runtime": 272.594,
+    "train_samples": 354,
+    "train_samples_per_second": 3.896,
+    "train_steps_per_second": 3.896
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1062,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.772218773524804e-05,
+      "loss": 1.6278,
+      "step": 500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 4.280991068959739e-07,
+      "loss": 0.9544,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "step": 1062,
+      "total_flos": 2311098177945600.0,
+      "train_loss": 1.2636232214458918,
+      "train_runtime": 272.594,
+      "train_samples_per_second": 3.896,
+      "train_steps_per_second": 3.896
+    }
+  ],
+  "max_steps": 1062,
+  "num_train_epochs": 3,
+  "total_flos": 2311098177945600.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dccc3a590aac4004c4a17f3f18978616be66f053af43759527770eac0f1c1f4
+size 3387