Initial Commit

.gitignore

@@ -0,0 +1,2 @@
+# MacOS Stuff
+**/.DS_Store

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "SauravMaheshkar/bert-large-uncased-whole-word-masking-chaii",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "squad2",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "language": "english",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "name": "Bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e1e75bdfcdda8ed0cbf2e1b06283fc2841620088d8bbbe97678262ce9cf9ae9
+size 2673000237

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e73e8155e42ecdf23e2a2478013602233bcc7da2f23f1ae7edc9c2c861a0643d
+size 1336547639

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12798c4dcd971e843bf2d371fd4a9ac49f205ba8c65b444604de688afc08cdfe
+size 14657

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18132446c5dbcce34518f3b4224f48ebb3dfcfecc009681bece771b03cef4533
+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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "SauravMaheshkar/bert-large-uncased-whole-word-masking-chaii/special_tokens_map.json", "name_or_path": "SauravMaheshkar/bert-large-uncased-whole-word-masking-chaii", "do_basic_tokenize": true, "never_split": null}

trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998933560840354,
+  "global_step": 2344,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.7486960644855383e-05,
+      "loss": 1.208,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2745376955903272e-05,
+      "loss": 1.0337,
+      "step": 1000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.003793266951162e-06,
+      "loss": 0.9647,
+      "step": 1500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.262209577999052e-06,
+      "loss": 0.9206,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0249625444412231,
+      "eval_runtime": 13.4585,
+      "eval_samples_per_second": 23.108,
+      "step": 2344
+    }
+  ],
+  "max_steps": 2344,
+  "num_train_epochs": 1,
+  "total_flos": 2.886882981661901e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31701401ee46e3ea68a44c93099a9e042f21cb6d29da85f1dcf9cefae1b30cdd
+size 2415