add files

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: google_electra-small-discriminator_squad
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# google_electra-small-discriminator_squad
+
+This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on the squad dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.14.1
+- Pytorch 1.9.0
+- Datasets 1.16.1
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 76.95364238410596,
+    "eval_f1": 84.98869246841396,
+    "eval_samples": 10784,
+    "train_loss": 1.262162847499961,
+    "train_runtime": 2635.5654,
+    "train_samples": 88524,
+    "train_samples_per_second": 100.765,
+    "train_steps_per_second": 6.298
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "google/electra-small-discriminator",
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "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": "4.14.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 76.95364238410596,
+    "eval_f1": 84.98869246841396,
+    "eval_samples": 10784
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a664650162a084e5a48dfee5c525a8b1e54dac575cccf38dfd8e4a6effef9e69
+size 54019309

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": null, "name_or_path": "google/electra-small-discriminator", "tokenizer_class": "ElectraTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.262162847499961,
+    "train_runtime": 2635.5654,
+    "train_samples": 88524,
+    "train_samples_per_second": 100.765,
+    "train_steps_per_second": 6.298
+}

trainer_state.json

@@ -0,0 +1,223 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 16599,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.9096331104283392e-05,
+      "loss": 3.2794,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.819266220856678e-05,
+      "loss": 2.2324,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.7288993312850172e-05,
+      "loss": 1.9171,
+      "step": 1500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.6385324417133564e-05,
+      "loss": 1.6619,
+      "step": 2000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.5481655521416952e-05,
+      "loss": 1.5888,
+      "step": 2500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.4577986625700344e-05,
+      "loss": 1.4678,
+      "step": 3000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.3674317729983735e-05,
+      "loss": 1.3724,
+      "step": 3500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.2770648834267124e-05,
+      "loss": 1.4076,
+      "step": 4000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.1866979938550515e-05,
+      "loss": 1.3559,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.0963311042833907e-05,
+      "loss": 1.2931,
+      "step": 5000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.0059642147117295e-05,
+      "loss": 1.3135,
+      "step": 5500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.9155973251400687e-05,
+      "loss": 1.1764,
+      "step": 6000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.825230435568408e-05,
+      "loss": 1.1188,
+      "step": 6500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.7348635459967467e-05,
+      "loss": 1.1272,
+      "step": 7000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.644496656425086e-05,
+      "loss": 1.1424,
+      "step": 7500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.554129766853425e-05,
+      "loss": 1.1509,
+      "step": 8000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.463762877281764e-05,
+      "loss": 1.0994,
+      "step": 8500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.373395987710103e-05,
+      "loss": 1.1085,
+      "step": 9000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.283029098138442e-05,
+      "loss": 1.0516,
+      "step": 9500
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.1926622085667812e-05,
+      "loss": 1.1125,
+      "step": 10000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.1022953189951202e-05,
+      "loss": 1.0775,
+      "step": 10500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.0119284294234592e-05,
+      "loss": 1.0903,
+      "step": 11000
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.215615398517983e-06,
+      "loss": 0.9665,
+      "step": 11500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 8.311946502801373e-06,
+      "loss": 0.958,
+      "step": 12000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 7.408277607084765e-06,
+      "loss": 0.9539,
+      "step": 12500
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 6.504608711368155e-06,
+      "loss": 0.9495,
+      "step": 13000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 5.6009398156515455e-06,
+      "loss": 0.9543,
+      "step": 13500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.697270919934936e-06,
+      "loss": 0.9697,
+      "step": 14000
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 3.7936020242183263e-06,
+      "loss": 0.973,
+      "step": 14500
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.889933128501717e-06,
+      "loss": 0.9563,
+      "step": 15000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.9862642327851074e-06,
+      "loss": 0.9312,
+      "step": 15500
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.0825953370684982e-06,
+      "loss": 0.9779,
+      "step": 16000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.7892644135188868e-07,
+      "loss": 0.966,
+      "step": 16500
+    },
+    {
+      "epoch": 3.0,
+      "step": 16599,
+      "total_flos": 5819517971269632.0,
+      "train_loss": 1.262162847499961,
+      "train_runtime": 2635.5654,
+      "train_samples_per_second": 100.765,
+      "train_steps_per_second": 6.298
+    }
+  ],
+  "max_steps": 16599,
+  "num_train_epochs": 3,
+  "total_flos": 5819517971269632.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01fa2b63a20382a2e83ea2e70ee67ed26f54ce5784699186a8ae62657e14e182
+size 2991