Initial Commit

.gitignore

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

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "SauravMaheshkar/distilbert-multi-finetuned-for-xqua-on-chaii",
+  "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": false,
+  "tie_weights_": true,
+  "transformers_version": "4.6.1",
+  "vocab_size": 119547
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ee00a0bfa56445482a8e15da7de6d511bd78579f9ae197fb0c12555d6796b1
+size 1077949019

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83181f6dbde897a7045ac9f4ea3a2d1ea9489a9f6ac354aca314534526ed85fc
+size 538984901

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f96a1a48c84a8d72b517ec18721c78494702e09f5ad8253bd98ae7c7c4025a7
+size 14657

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f1afe4a33f68808776494f2d52851453a5102d021cfde6cbc15324a5d070db
+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, "max_len": 512, "special_tokens_map_file": "SauravMaheshkar/distilbert-multi-finetuned-for-xqua-on-chaii/special_tokens_map.json", "name_or_path": "SauravMaheshkar/distilbert-multi-finetuned-for-xqua-on-chaii", "do_basic_tokenize": true, "never_split": null}

trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9997158283603297,
+  "global_step": 1759,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.5906506632975366e-05,
+      "loss": 1.0597,
+      "step": 500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.589387239418826e-06,
+      "loss": 0.8341,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.272267845862287e-06,
+      "loss": 0.7827,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.892806351184845,
+      "eval_runtime": 1.8448,
+      "eval_samples_per_second": 121.42,
+      "step": 1759
+    }
+  ],
+  "max_steps": 1759,
+  "num_train_epochs": 1,
+  "total_flos": 8736766232813568.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d17737b17672a4e32ef6214d37b54116fa93cb1fb983477810bfaa4e1fc548c
+size 2415