Initial Commit

.gitignore

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

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "SauravMaheshkar/distilbert-base-uncased-distilled-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,
+  "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": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7543991fd9f57c6a02edae448c87fe76739fba1cc8bc23d28c1af9ca8c9b1fa9
+size 530979419

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63242105f9523b3cf3835386d7f72871a5fd2aa2284fa090e0edfc4718925dc6
+size 265500101

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2563e3e24007c57efddd36843ab3bd7c9bc2167831ac8715bb770b46dd36ca
+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": null, "name_or_path": "SauravMaheshkar/distilbert-base-uncased-distilled-chaii"}

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": 1.4078,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2745376955903272e-05,
+      "loss": 1.1637,
+      "step": 1000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.003793266951162e-06,
+      "loss": 1.0799,
+      "step": 1500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.262209577999052e-06,
+      "loss": 1.0642,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.197797417640686,
+      "eval_runtime": 2.2647,
+      "eval_samples_per_second": 137.328,
+      "step": 2344
+    }
+  ],
+  "max_steps": 2344,
+  "num_train_epochs": 1,
+  "total_flos": 5734497329676288.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dbeb59108bb5692a34bf4e36cc0a916ac4a9f6587864a935a40e9e7c4e3f126
+size 2415