Upload 12 files

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.9254441857337952,
+    "eval_runtime": 20.0857,
+    "eval_samples": 90,
+    "eval_samples_per_second": 4.481,
+    "eval_steps_per_second": 2.24,
+    "perplexity": 2.5229886870822713,
+    "train_loss": 0.8416486935253584,
+    "train_runtime": 1747.7023,
+    "train_samples": 807,
+    "train_samples_per_second": 1.385,
+    "train_steps_per_second": 0.693
+}

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": 0.9254441857337952,
+    "eval_runtime": 20.0857,
+    "eval_samples": 90,
+    "eval_samples_per_second": 4.481,
+    "eval_steps_per_second": 2.24,
+    "perplexity": 2.5229886870822713
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50296ac55dce918f5a57e04ee96ce2e4fa89a179d1035276d1233f74a639b1b
+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": 0.8416486935253584,
+    "train_runtime": 1747.7023,
+    "train_samples": 807,
+    "train_samples_per_second": 1.385,
+    "train_steps_per_second": 0.693
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1212,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.24,
+      "learning_rate": 2.9372937293729375e-05,
+      "loss": 1.061,
+      "step": 500
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 8.745874587458746e-06,
+      "loss": 0.7091,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "step": 1212,
+      "total_flos": 1.151340640468992e+16,
+      "train_loss": 0.8416486935253584,
+      "train_runtime": 1747.7023,
+      "train_samples_per_second": 1.385,
+      "train_steps_per_second": 0.693
+    }
+  ],
+  "max_steps": 1212,
+  "num_train_epochs": 3,
+  "total_flos": 1.151340640468992e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ea77a47c485b68fa3556ff51c6fee5156e972815c87fa5ea4bb3f4023326b0
+size 2543