init

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-cased-distilled-squad",
+  "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,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "transformers_version": "4.2.2",
+  "vocab_size": 28996
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee71bbffbf08c28ea122f4fc5a7e9ea302fd01b04cc96b644b555f7f27116f50
+size 518457353

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6943d191e734ef5a2edc4309c1ca1036fa998737367f93bc6106d8431ea3399
+size 260812229

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7250c9c9a47f8798f227929b2e63d2585c09e696e0d8720b614736143df9b951
+size 623

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "distilbert-base-cased-distilled-squad"}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.635578583765112,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.8704663212435235e-05,
+      "loss": 0.195,
+      "step": 500
+    },
+    {
+      "epoch": 0.86,
+      "exact_match": 93.51079954528231,
+      "f1": 93.80762915245671,
+      "step": 500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.7409326424870466e-05,
+      "loss": 0.1077,
+      "step": 1000
+    },
+    {
+      "epoch": 1.73,
+      "exact_match": 93.50606290261463,
+      "f1": 93.65447770620185,
+      "step": 1000
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.61139896373057e-05,
+      "loss": 0.0884,
+      "step": 1500
+    },
+    {
+      "epoch": 2.59,
+      "exact_match": 93.6576354679803,
+      "f1": 93.74605279777693,
+      "step": 1500
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 2.4818652849740934e-05,
+      "loss": 0.0757,
+      "step": 2000
+    },
+    {
+      "epoch": 3.45,
+      "exact_match": 94.20234937476317,
+      "f1": 94.30971327523054,
+      "step": 2000
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 2.3523316062176165e-05,
+      "loss": 0.0682,
+      "step": 2500
+    },
+    {
+      "epoch": 4.32,
+      "exact_match": 93.98920045471769,
+      "f1": 94.03340911961604,
+      "step": 2500
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 2.22279792746114e-05,
+      "loss": 0.0636,
+      "step": 3000
+    },
+    {
+      "epoch": 5.18,
+      "exact_match": 93.88025767336111,
+      "f1": 94.01288366805606,
+      "step": 3000
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 2.0932642487046633e-05,
+      "loss": 0.0562,
+      "step": 3500
+    },
+    {
+      "epoch": 6.04,
+      "exact_match": 93.99867374005305,
+      "f1": 94.05867121384364,
+      "step": 3500
+    },
+    {
+      "epoch": 6.91,
+      "learning_rate": 1.9637305699481864e-05,
+      "loss": 0.0535,
+      "step": 4000
+    },
+    {
+      "epoch": 6.91,
+      "exact_match": 94.24024251610459,
+      "f1": 94.3255020841228,
+      "step": 4000
+    },
+    {
+      "epoch": 7.77,
+      "learning_rate": 1.8341968911917098e-05,
+      "loss": 0.0497,
+      "step": 4500
+    },
+    {
+      "epoch": 7.77,
+      "exact_match": 93.9039408866995,
+      "f1": 94.00498926361,
+      "step": 4500
+    },
+    {
+      "epoch": 8.64,
+      "learning_rate": 1.704663212435233e-05,
+      "loss": 0.0463,
+      "step": 5000
+    },
+    {
+      "epoch": 8.64,
+      "exact_match": 94.43444486547935,
+      "f1": 94.50707338638372,
+      "step": 5000
+    }
+  ],
+  "max_steps": 11580,
+  "num_train_epochs": 20,
+  "total_flos": 192130582402252800,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660f26c7987ee7b14c99cce4a32ef7e08ae10d0df5de7998ef3369de96a1d312
+size 2031