Upload 12 files

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.124106764793396,
+    "eval_runtime": 85.8692,
+    "eval_samples": 393,
+    "eval_samples_per_second": 4.577,
+    "eval_steps_per_second": 2.294,
+    "perplexity": 3.0774667192237892,
+    "train_loss": 1.1233460162319033,
+    "train_runtime": 7598.915,
+    "train_samples": 3540,
+    "train_samples_per_second": 1.398,
+    "train_steps_per_second": 0.699
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_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,
+  "gradient_checkpointing": false,
+  "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,
+  "resid_pdrop": 0.1,
+  "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
+    }
+  },
+  "transformers_version": "4.8.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.124106764793396,
+    "eval_runtime": 85.8692,
+    "eval_samples": 393,
+    "eval_samples_per_second": 4.577,
+    "eval_steps_per_second": 2.294,
+    "perplexity": 3.0774667192237892
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d351f4584a1bc653f5ea678b7c27f9c074dd8dc74f875b73d32227cdd43004b3
+size 3134053001

special_tokens_map.json

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

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-large", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.1233460162319033,
+    "train_runtime": 7598.915,
+    "train_samples": 3540,
+    "train_samples_per_second": 1.398,
+    "train_steps_per_second": 0.699
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 5310,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.5291902071563094e-05,
+      "loss": 1.6091,
+      "step": 500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.058380414312618e-05,
+      "loss": 1.3109,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.587570621468927e-05,
+      "loss": 1.2431,
+      "step": 1500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.116760828625235e-05,
+      "loss": 1.1485,
+      "step": 2000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.6459510357815442e-05,
+      "loss": 1.0738,
+      "step": 2500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.175141242937853e-05,
+      "loss": 1.0668,
+      "step": 3000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.704331450094162e-05,
+      "loss": 1.0542,
+      "step": 3500
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.2335216572504708e-05,
+      "loss": 0.9543,
+      "step": 4000
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.627118644067798e-06,
+      "loss": 0.9464,
+      "step": 4500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.919020715630885e-06,
+      "loss": 0.9416,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "step": 5310,
+      "total_flos": 5.05049054183424e+16,
+      "train_loss": 1.1233460162319033,
+      "train_runtime": 7598.915,
+      "train_samples_per_second": 1.398,
+      "train_steps_per_second": 0.699
+    }
+  ],
+  "max_steps": 5310,
+  "num_train_epochs": 3,
+  "total_flos": 5.05049054183424e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe8b27204b58d49752a90bbbed284c708c809e2684dc28baf320b4d8d44ec69
+size 2543