Upload 12 files

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.9309731721878052,
+    "eval_runtime": 14.5067,
+    "eval_samples": 66,
+    "eval_samples_per_second": 4.55,
+    "eval_steps_per_second": 2.275,
+    "perplexity": 2.536976892020004,
+    "train_loss": 0.791101954004786,
+    "train_runtime": 1264.5393,
+    "train_samples": 592,
+    "train_samples_per_second": 1.404,
+    "train_steps_per_second": 0.702
+}

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": 0.9309731721878052,
+    "eval_runtime": 14.5067,
+    "eval_samples": 66,
+    "eval_samples_per_second": 4.55,
+    "eval_steps_per_second": 2.275,
+    "perplexity": 2.536976892020004
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9d2f4128d834777b878eaa86ac2200b214fdea47a9b4b68444092f703b96bf
+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": 0.791101954004786,
+    "train_runtime": 1264.5393,
+    "train_samples": 592,
+    "train_samples_per_second": 1.404,
+    "train_steps_per_second": 0.702
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 888,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.1846846846846845e-05,
+      "loss": 0.9229,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 888,
+      "total_flos": 8446018081259520.0,
+      "train_loss": 0.791101954004786,
+      "train_runtime": 1264.5393,
+      "train_samples_per_second": 1.404,
+      "train_steps_per_second": 0.702
+    }
+  ],
+  "max_steps": 888,
+  "num_train_epochs": 3,
+  "total_flos": 8446018081259520.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40f2664e47b19d418af3b274392e304d93922acaaba62329a8e9d928d48bd87
+size 2543