Pushing model.

added_tokens.json

@@ -0,0 +1 @@
+{"<bos>": 50257, "<eos>": 50258, "<pad>": 50259, "<context>": 50260, "<clue>": 50261, "<ans>": 50262, "<style>": 50263, "<ques>": 50264}

config.json

@@ -0,0 +1,31 @@
+{
+  "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": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "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
+    }
+  },
+  "vocab_size": 50265
+}

events.out.tfevents.1598920989.ip-172-31-34-164

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c626a17ae2fc20393564a47c0ada6699863d755490c9faeca04a27dabb8e24
+size 1106252

model_training_args.json

@@ -0,0 +1,21 @@
+{
+  "model_type": "gpt2",
+  "model_checkpoint": "gpt2",
+  "device": "cuda:0",
+  "use_amp": true,
+  "train_batch_size": 3,
+  "valid_batch_size": 3,
+  "gradient_accumulation_steps": 10,
+  "lr": 6.25e-05,
+  "max_norm": 1.0,
+  "n_epochs": 3,
+  "eval_before_start": false,
+  "dataset_cache_dir": "/home/ubuntu/question-generation/caches/datasets",
+  "dataset_dir": "datasets/SQuAD/qg",
+  "local_rank": 0,
+  "output_dir": "/home/ubuntu/question-generation/outputs/train",
+  "save_interval_epoch": 1,
+  "iterations_before_checking": 0,
+  "n_saved_epoch": 3,
+  "distributed": true
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458a55f8f8fe32a199245d77ce38acd0224d37c2f1ce78037fa8bfad32d5ce07
+size 510432891

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<bos>", "eos_token": "<eos>", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<pad>", "additional_special_tokens": ["<context>", "<clue>", "<ans>", "<style>", "<ques>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}