add files

added_tokens.json

@@ -0,0 +1 @@
+{"<|UNK|>": 50259, "<|PAD|>": 50260, "<|EOS|>": 50258, "<|SEP|>": 50261, "<|BOS|>": 50257}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50257,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50258,
+  "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": 50260,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "sep_token_id": 50261,
+  "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": "4.15.0",
+  "use_cache": true,
+  "vocab_size": 50262
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8fa7be8bce0bfb68827ab656078f7f4e5cb1345da3200e93f31f3bccfd4ee0
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05479fbfc9c9bc3741ca2919cf3c632ce2aed2455c8e5e39af8e5f7159ec32d
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:580839809af279bd2c9627ea4cd6738840ec3fa38a69ec17d67c36413858655b
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|BOS|>", "eos_token": "<|EOS|>", "unk_token": "<|UNK|>", "sep_token": "<|SEP|>", "pad_token": "<|PAD|>"}

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": 0.745124876499176,
+  "best_model_checkpoint": "/content/checkpoint-250",
+  "epoch": 2.0,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7531784772872925,
+      "eval_runtime": 102.2998,
+      "eval_samples_per_second": 19.55,
+      "eval_steps_per_second": 4.888,
+      "step": 125
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.745124876499176,
+      "eval_runtime": 102.2807,
+      "eval_samples_per_second": 19.554,
+      "eval_steps_per_second": 4.889,
+      "step": 250
+    }
+  ],
+  "max_steps": 500,
+  "num_train_epochs": 4,
+  "total_flos": 6271008768000000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7adcec3b454fb39ac4704da32c94295547cc32577bfc0e0c007012a73d8f0b48
+size 2927