Upload 12 files

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "deepset/electra-base-squad2",
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "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:f5231ac38131c00b7e2aec0b645f73a60a2eeda43e12f562ca2400e29a631baf
+size 871262021

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:989da9bbce4e1785256dbccfa51ef0fd33b5215897f74ada03d15702b970e399
+size 435645485

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c82356e85ed9e77a699c118a6c0944df0b432faf675ffb5fb5c2a162f4d836b
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b6fea68b198450145ec317f1beb9b8d30d0d70e357ddd6fababef1f050d113
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8274d2b7d27457e92000da3fc294b62c925282ca5353b31a67f689aeed649014
+size 627

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 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 5,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2e-05,
+      "loss": 5.6896,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_runtime": 0.0225,
+      "eval_samples_per_second": 355.07,
+      "eval_steps_per_second": 44.384,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2e-05,
+      "loss": 5.5077,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_runtime": 0.0204,
+      "eval_samples_per_second": 392.596,
+      "eval_steps_per_second": 49.075,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 5.5731,
+      "step": 3
+    },
+    {
+      "epoch": 3.0,
+      "eval_runtime": 0.033,
+      "eval_samples_per_second": 242.139,
+      "eval_steps_per_second": 30.267,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.2e-05,
+      "loss": 3.2841,
+      "step": 4
+    },
+    {
+      "epoch": 4.0,
+      "eval_runtime": 0.0377,
+      "eval_samples_per_second": 212.053,
+      "eval_steps_per_second": 26.507,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.5314,
+      "step": 5
+    },
+    {
+      "epoch": 5.0,
+      "eval_runtime": 0.0526,
+      "eval_samples_per_second": 151.97,
+      "eval_steps_per_second": 18.996,
+      "step": 5
+    }
+  ],
+  "max_steps": 5,
+  "num_train_epochs": 5,
+  "total_flos": 7838902702080.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235ba8e115049415bea248f4fb84c6c9ad804c0cf210b2f0d39264b8d1cee295
+size 3643