upload final best orig model

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "BioM-ELECTRA-Large-SQuAD2-finetune-127-1/checkpoint-10565",
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28895
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12915f0e00bd9d16cecb714593fc6a3c602324a9a95c0fe2b35b57adb3f09fa
+size 2659653861

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34f6a88d4b1101e489636c23141760285744d693520518ec861423c8d8ab148
+size 1329849649

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49220eddcceec1d3dea2859cd418ba71f78be030b120fb84d6f51388ada0312
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3682473d4b1ed9440be1eaff0ca0d909753fe593d5e07cffe8d07e73dba3dc
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5abd4139a12ea51bd0adb84fd844d980a1c9427a66e0bd0e9073f92f047b911
+size 623

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "BioM-ELECTRA-Large-SQuAD2-finetune-127-1/checkpoint-10565",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 8452,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9059157595835306e-05,
+      "loss": 0.0116,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8118315191670613e-05,
+      "loss": 0.0759,
+      "step": 1000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.717557974443919e-05,
+      "loss": 0.2127,
+      "step": 1500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6229058211074304e-05,
+      "loss": 0.0926,
+      "step": 2000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.5282536677709418e-05,
+      "loss": 0.1933,
+      "step": 2500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.4336015144344535e-05,
+      "loss": 0.0232,
+      "step": 3000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.3389493610979651e-05,
+      "loss": 0.0176,
+      "step": 3500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.2442972077614768e-05,
+      "loss": 0.0192,
+      "step": 4000
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.1496450544249882e-05,
+      "loss": 0.0148,
+      "step": 4500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.0551822053951728e-05,
+      "loss": 0.013,
+      "step": 5000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.605300520586845e-06,
+      "loss": 0.019,
+      "step": 5500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.65877898722196e-06,
+      "loss": 0.0361,
+      "step": 6000
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 7.714150496923806e-06,
+      "loss": 0.021,
+      "step": 6500
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 6.767628963558922e-06,
+      "loss": 0.0146,
+      "step": 7000
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 5.8211074301940376e-06,
+      "loss": 0.0071,
+      "step": 7500
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 4.874585896829153e-06,
+      "loss": 0.0093,
+      "step": 8000
+    }
+  ],
+  "max_steps": 10565,
+  "num_train_epochs": 5,
+  "total_flos": 4.709658898479514e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:225a74f94dabc2a8cafc665441d4f0ed24428e6dd3d87eed4ca1029568e43afb
+size 3503