Qna First commit

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.2",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5a58fce8b98f508392fa297fc13ea7fe61ca13aaaffc197227ffe8ac3cd290
+size 530974121

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f248cee4868379a386a23a1fc9364cb0173a2537af26646543eca2b6e112968c
+size 265491317

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a41e665458f179be422920f1f8b88383451e48a92c15aaf2b60b7d2f147face
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a0e0f6ba69eae521e6753c4adb0bb2c9333d8e467287f60f6f4b393d188a6e
+size 623

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9940357852882704,
+  "global_step": 5500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.819266220856678e-05,
+      "loss": 3.0844,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.6385324417133565e-05,
+      "loss": 1.8306,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.4577986625700345e-05,
+      "loss": 1.6551,
+      "step": 1500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.2770648834267125e-05,
+      "loss": 1.5101,
+      "step": 2000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.0963311042833906e-05,
+      "loss": 1.4381,
+      "step": 2500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.155973251400688e-06,
+      "loss": 1.3683,
+      "step": 3000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.348635459967468e-06,
+      "loss": 1.2983,
+      "step": 3500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.541297668534249e-06,
+      "loss": 1.3465,
+      "step": 4000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.7339598771010305e-06,
+      "loss": 1.3036,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.9266220856678112e-06,
+      "loss": 1.2562,
+      "step": 5000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.1928429423459245e-07,
+      "loss": 1.2602,
+      "step": 5500
+    }
+  ],
+  "max_steps": 5533,
+  "num_train_epochs": 1,
+  "total_flos": 8623104602112000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a23b901c523ac1ed9cf37e35d74292a94f945c1b8a9e094f5f4561b0625e0d
+size 3439