Initial Commit

.gitignore

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "SauravMaheshkar/electra-base-chaii",
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "language": "english",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "name": "Electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2878f4e885e99b9a79e760d5415c195c87e3a0ecb7677a239f26b5af5bb89e8
+size 871270381

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66d444b772d19717f1fab022cb28bf7c5d87861b1da1e48f3708d357beb3fea
+size 435662519

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b26311388d0c1884f6a59b6f115214213fdb52b64723e29da12421ca37a7f897
+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, "model_max_length": 512, "special_tokens_map_file": "SauravMaheshkar/electra-base-chaii/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "SauravMaheshkar/electra-base-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": 2.394,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2745376955903272e-05,
+      "loss": 2.0721,
+      "step": 1000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.003793266951162e-06,
+      "loss": 2.0167,
+      "step": 1500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.262209577999052e-06,
+      "loss": 1.9823,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.2713022232055664,
+      "eval_runtime": 4.3454,
+      "eval_samples_per_second": 71.57,
+      "step": 2344
+    }
+  ],
+  "max_steps": 2344,
+  "num_train_epochs": 1,
+  "total_flos": 9409374830002176.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51880f21200da3b3040ae10951cb340d7bc543c7460ca4e7b7209723fb52e613
+size 2415