Upload 15 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,53 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+model-index:
+- name: bert-lr3-seed36
+  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. -->
+
+# bert-lr3-seed36
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the squad_v2 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: 12
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.20.1
+- Pytorch 1.12.0+cu116
+- Datasets 2.3.2
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 2.0,
+    "eval_HasAns_exact": 72.58771929824562,
+    "eval_HasAns_f1": 79.39651959521703,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 72.8847771236333,
+    "eval_NoAns_f1": 72.8847771236333,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 72.7364608776215,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 76.13598653755962,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 72.7364608776215,
+    "eval_f1": 76.13598653755975,
+    "eval_samples": 12134,
+    "eval_total": 11873,
+    "train_loss": 0.9679226359383004,
+    "train_runtime": 5136.3695,
+    "train_samples": 131754,
+    "train_samples_per_second": 51.302,
+    "train_steps_per_second": 4.275
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad32d66444d65c3bb0c184288a206c88f5d543d1f326cffbd862afda1df2417a
+size 56562475

eval_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 2.0,
+    "eval_HasAns_exact": 72.58771929824562,
+    "eval_HasAns_f1": 79.39651959521703,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 72.8847771236333,
+    "eval_NoAns_f1": 72.8847771236333,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 72.7364608776215,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 76.13598653755962,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 72.7364608776215,
+    "eval_f1": 76.13598653755975,
+    "eval_samples": 12134,
+    "eval_total": 11873
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97078fe93ad949cb9852413f8c04375b3ed4ea85bc8825c3ff3a083e83f84f08
+size 435643185

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 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.9679226359383004,
+    "train_runtime": 5136.3695,
+    "train_samples": 131754,
+    "train_samples_per_second": 51.302,
+    "train_steps_per_second": 4.275
+}

trainer_state.json

@@ -0,0 +1,283 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 21960,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9316939890710385e-05,
+      "loss": 2.4099,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.8633879781420765e-05,
+      "loss": 1.6744,
+      "step": 1000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.795081967213115e-05,
+      "loss": 1.5233,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.7267759562841533e-05,
+      "loss": 1.402,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.6584699453551913e-05,
+      "loss": 1.3482,
+      "step": 2500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.5901639344262294e-05,
+      "loss": 1.2935,
+      "step": 3000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.5218579234972678e-05,
+      "loss": 1.2617,
+      "step": 3500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.453551912568306e-05,
+      "loss": 1.2702,
+      "step": 4000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3852459016393442e-05,
+      "loss": 1.1879,
+      "step": 4500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.3169398907103826e-05,
+      "loss": 1.1748,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.248633879781421e-05,
+      "loss": 1.1447,
+      "step": 5500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.180327868852459e-05,
+      "loss": 1.1318,
+      "step": 6000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.1120218579234974e-05,
+      "loss": 1.1303,
+      "step": 6500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.0437158469945358e-05,
+      "loss": 1.0937,
+      "step": 7000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.975409836065574e-05,
+      "loss": 1.0495,
+      "step": 7500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.907103825136612e-05,
+      "loss": 1.0518,
+      "step": 8000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.8387978142076503e-05,
+      "loss": 1.0632,
+      "step": 8500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7704918032786887e-05,
+      "loss": 1.0331,
+      "step": 9000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.7021857923497267e-05,
+      "loss": 1.0486,
+      "step": 9500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.633879781420765e-05,
+      "loss": 1.0162,
+      "step": 10000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5655737704918035e-05,
+      "loss": 1.0093,
+      "step": 10500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.4972677595628415e-05,
+      "loss": 0.9826,
+      "step": 11000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.4289617486338798e-05,
+      "loss": 0.7505,
+      "step": 11500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.3606557377049181e-05,
+      "loss": 0.716,
+      "step": 12000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.2923497267759564e-05,
+      "loss": 0.7136,
+      "step": 12500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.2240437158469946e-05,
+      "loss": 0.7486,
+      "step": 13000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.1557377049180328e-05,
+      "loss": 0.7063,
+      "step": 13500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.087431693989071e-05,
+      "loss": 0.6988,
+      "step": 14000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.0191256830601094e-05,
+      "loss": 0.7327,
+      "step": 14500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 9.508196721311476e-06,
+      "loss": 0.7099,
+      "step": 15000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 8.825136612021857e-06,
+      "loss": 0.6963,
+      "step": 15500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 8.14207650273224e-06,
+      "loss": 0.7096,
+      "step": 16000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.459016393442623e-06,
+      "loss": 0.6755,
+      "step": 16500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.775956284153006e-06,
+      "loss": 0.6778,
+      "step": 17000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 6.092896174863388e-06,
+      "loss": 0.7141,
+      "step": 17500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 5.409836065573771e-06,
+      "loss": 0.6712,
+      "step": 18000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 4.726775956284153e-06,
+      "loss": 0.6862,
+      "step": 18500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 4.043715846994535e-06,
+      "loss": 0.66,
+      "step": 19000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.3606557377049183e-06,
+      "loss": 0.652,
+      "step": 19500
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 2.6775956284153005e-06,
+      "loss": 0.694,
+      "step": 20000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.994535519125683e-06,
+      "loss": 0.6673,
+      "step": 20500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.3114754098360657e-06,
+      "loss": 0.6625,
+      "step": 21000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 6.284153005464482e-07,
+      "loss": 0.6728,
+      "step": 21500
+    },
+    {
+      "epoch": 2.0,
+      "step": 21960,
+      "total_flos": 5.164033933049242e+16,
+      "train_loss": 0.9679226359383004,
+      "train_runtime": 5136.3695,
+      "train_samples_per_second": 51.302,
+      "train_steps_per_second": 4.275
+    }
+  ],
+  "max_steps": 21960,
+  "num_train_epochs": 2,
+  "total_flos": 5.164033933049242e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:779b21da8049387bf25dba124e7952b43b8dcaa5c8135bea0b6ff646ec35a23a
+size 3311