init commit

all_results.json

@@ -0,0 +1 @@
+{"F1": 88.34753277550725, "EM": 80.4635761589404}

args.txt

@@ -0,0 +1,32 @@
+model_name_or_path: gpt2-xl
+config_name: None
+tokenizer_name: None
+use_slow_tokenizer: False
+per_device_train_batch_size: 1
+per_device_eval_batch_size: 1
+learning_rate: 5e-06
+weight_decay: 0.1
+num_train_epochs: 5
+patience: 2
+max_train_steps: None
+gradient_accumulation_steps: 1
+lr_scheduler_type: SchedulerType.LINEAR
+num_warmup_steps: 0
+output_dir: gpt_xl_squad_decay_0.1
+seed: None
+finetune_type: vanilla
+beta: 0.1
+model_type: None
+max_seq_length: 600
+max_context_length: 600
+num_beams: 1
+preprocessing_num_workers: 16
+overwrite_cache: False
+no_keep_linebreaks: False
+push_to_hub: False
+hub_model_id: None
+hub_token: None
+checkpointing_steps: epoch
+resume_from_checkpoint: None
+with_tracking: False
+local_rank: -1

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "gpt2-xl",
+  "activation_function": "gelu_new",
+  "adapters": {
+    "adapters": {},
+    "config_map": {},
+    "fusion_config_map": {},
+    "fusions": {}
+  },
+  "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": 1600,
+  "n_head": 25,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "output_past": true,
+  "pad_token": "<|endoftext|>",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b184e03b36ff0fff68cf6b7a280bbe02675a19f5ed1d890ecb684a3ffc079bde
+size 6281056077

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_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-xl", "tokenizer_class": "GPT2Tokenizer"}