Upload folder using huggingface_hub

.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

.gitignore

@@ -0,0 +1,2 @@
+checkpoint-*/
+

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,86 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: debug_squad
+  results: []
+---
+
+# bert-base-uncased-finetuned-squad
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the SQuAD dataset.
+
+## Model description
+
+- **Model Type:** BERT for Question Answering
+- **Base Model:** bert-base-uncased
+- **Language:** English
+- **Task:** Question Answering
+- **Dataset:** [SQuAD v1.1](https://rajpurkar.github.io/SQuAD-explorer/)
+
+## 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: AdamW_TORCH with beta=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+- training_loss: 0.6077
+- eval_exact_match: 79.508
+- eval_f1: 87.7293
+- train_runtime: 1:09:34.90
+- train_samples_per_second: 106.019
+- train_steps_per_second: 8.835
+
+## Intended uses & limitations
+
+This model is intended for English question answering tasks. It performs best on factual questions where the answer is explicitly stated in the provided context. Note that this model was trained on SQuAD v1.1, which means it always tries to find an answer in the context (it cannot handle questions that have no answer).
+
+### Usage Example
+
+```python
+from transformers import AutoModelForQuestionAnswering, AutoTokenizer
+
+model = AutoModelForQuestionAnswering.from_pretrained("real-jiakai/bert-base-uncased-finetuned-squad")
+tokenizer = AutoTokenizer.from_pretrained("real-jiakai/bert-base-uncased-finetuned-squad")
+
+# Example usage
+context = "BERT was developed by Google in 2018."
+question = "Who developed BERT?"
+
+inputs = tokenizer(question, context, return_tensors="pt")
+outputs = model(**inputs)
+
+answer_start = outputs.start_logits.argmax()
+answer_end = outputs.end_logits.argmax()
+
+answer = tokenizer.decode(inputs["input_ids"][0][answer_start:answer_end+1])
+print(f"Answer: {answer}")  # Expected output: "google"
+```
+
+## Training Infrastructure
+
+- Training Device: Single GPU (NVIDIA Tesla V100 16GB)
+- Training Time: ~70 minutes
+- Framework: PyTorch
+- Training Script: Hugging Face Transformers' `run_qa.py`
+
+### Framework versions
+
+- Transformers 4.47.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

.ipynb_checkpoints/special_tokens_map-checkpoint.json

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

.ipynb_checkpoints/train_results-checkpoint.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 8.674137784986624e+16,
+    "train_loss": 0.6077316944008034,
+    "train_runtime": 4174.9009,
+    "train_samples": 88524,
+    "train_samples_per_second": 106.019,
+    "train_steps_per_second": 8.835
+}

.ipynb_checkpoints/trainer_state-checkpoint.json

@@ -0,0 +1,553 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 36885,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06777822963264199,
+      "grad_norm": 27.22840690612793,
+      "learning_rate": 2.959333062220415e-05,
+      "loss": 2.3635,
+      "step": 500
+    },
+    {
+      "epoch": 0.13555645926528398,
+      "grad_norm": 13.622244834899902,
+      "learning_rate": 2.9186661244408297e-05,
+      "loss": 1.5111,
+      "step": 1000
+    },
+    {
+      "epoch": 0.203334688897926,
+      "grad_norm": 14.186929702758789,
+      "learning_rate": 2.8779991866612443e-05,
+      "loss": 1.3571,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27111291853056796,
+      "grad_norm": 23.26664161682129,
+      "learning_rate": 2.8373322488816593e-05,
+      "loss": 1.3122,
+      "step": 2000
+    },
+    {
+      "epoch": 0.33889114816321,
+      "grad_norm": 16.56296157836914,
+      "learning_rate": 2.796665311102074e-05,
+      "loss": 1.2847,
+      "step": 2500
+    },
+    {
+      "epoch": 0.406669377795852,
+      "grad_norm": 8.389954566955566,
+      "learning_rate": 2.755998373322489e-05,
+      "loss": 1.2343,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47444760742849396,
+      "grad_norm": 10.328352928161621,
+      "learning_rate": 2.7153314355429036e-05,
+      "loss": 1.1899,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5422258370611359,
+      "grad_norm": 14.220015525817871,
+      "learning_rate": 2.6746644977633186e-05,
+      "loss": 1.1337,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6100040666937779,
+      "grad_norm": 23.481950759887695,
+      "learning_rate": 2.6339975599837332e-05,
+      "loss": 1.1337,
+      "step": 4500
+    },
+    {
+      "epoch": 0.67778229632642,
+      "grad_norm": 26.090124130249023,
+      "learning_rate": 2.593330622204148e-05,
+      "loss": 1.1607,
+      "step": 5000
+    },
+    {
+      "epoch": 0.745560525959062,
+      "grad_norm": 16.809215545654297,
+      "learning_rate": 2.552663684424563e-05,
+      "loss": 1.1114,
+      "step": 5500
+    },
+    {
+      "epoch": 0.813338755591704,
+      "grad_norm": 15.458964347839355,
+      "learning_rate": 2.5119967466449778e-05,
+      "loss": 1.0703,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8811169852243459,
+      "grad_norm": 21.379941940307617,
+      "learning_rate": 2.4713298088653925e-05,
+      "loss": 1.0782,
+      "step": 6500
+    },
+    {
+      "epoch": 0.9488952148569879,
+      "grad_norm": 10.91637134552002,
+      "learning_rate": 2.4306628710858075e-05,
+      "loss": 1.0842,
+      "step": 7000
+    },
+    {
+      "epoch": 1.01667344448963,
+      "grad_norm": 13.034053802490234,
+      "learning_rate": 2.389995933306222e-05,
+      "loss": 0.9463,
+      "step": 7500
+    },
+    {
+      "epoch": 1.0844516741222718,
+      "grad_norm": 15.298956871032715,
+      "learning_rate": 2.3493289955266367e-05,
+      "loss": 0.7336,
+      "step": 8000
+    },
+    {
+      "epoch": 1.152229903754914,
+      "grad_norm": 10.17520523071289,
+      "learning_rate": 2.3086620577470517e-05,
+      "loss": 0.7455,
+      "step": 8500
+    },
+    {
+      "epoch": 1.2200081333875559,
+      "grad_norm": 15.160359382629395,
+      "learning_rate": 2.2679951199674667e-05,
+      "loss": 0.7516,
+      "step": 9000
+    },
+    {
+      "epoch": 1.287786363020198,
+      "grad_norm": 29.048612594604492,
+      "learning_rate": 2.2273281821878813e-05,
+      "loss": 0.7434,
+      "step": 9500
+    },
+    {
+      "epoch": 1.35556459265284,
+      "grad_norm": 24.640453338623047,
+      "learning_rate": 2.1866612444082963e-05,
+      "loss": 0.7673,
+      "step": 10000
+    },
+    {
+      "epoch": 1.4233428222854818,
+      "grad_norm": 16.07855224609375,
+      "learning_rate": 2.1459943066287106e-05,
+      "loss": 0.775,
+      "step": 10500
+    },
+    {
+      "epoch": 1.491121051918124,
+      "grad_norm": 12.662883758544922,
+      "learning_rate": 2.1053273688491256e-05,
+      "loss": 0.7561,
+      "step": 11000
+    },
+    {
+      "epoch": 1.5588992815507658,
+      "grad_norm": 13.590459823608398,
+      "learning_rate": 2.0646604310695406e-05,
+      "loss": 0.7537,
+      "step": 11500
+    },
+    {
+      "epoch": 1.626677511183408,
+      "grad_norm": 12.973872184753418,
+      "learning_rate": 2.0239934932899552e-05,
+      "loss": 0.7513,
+      "step": 12000
+    },
+    {
+      "epoch": 1.6944557408160499,
+      "grad_norm": 17.74153709411621,
+      "learning_rate": 1.9833265555103702e-05,
+      "loss": 0.7666,
+      "step": 12500
+    },
+    {
+      "epoch": 1.7622339704486918,
+      "grad_norm": 14.367899894714355,
+      "learning_rate": 1.9426596177307852e-05,
+      "loss": 0.7787,
+      "step": 13000
+    },
+    {
+      "epoch": 1.830012200081334,
+      "grad_norm": 30.40443992614746,
+      "learning_rate": 1.9019926799511995e-05,
+      "loss": 0.7373,
+      "step": 13500
+    },
+    {
+      "epoch": 1.8977904297139758,
+      "grad_norm": 8.429509162902832,
+      "learning_rate": 1.8613257421716145e-05,
+      "loss": 0.7559,
+      "step": 14000
+    },
+    {
+      "epoch": 1.965568659346618,
+      "grad_norm": 12.091238975524902,
+      "learning_rate": 1.8206588043920295e-05,
+      "loss": 0.7537,
+      "step": 14500
+    },
+    {
+      "epoch": 2.03334688897926,
+      "grad_norm": 7.968406677246094,
+      "learning_rate": 1.779991866612444e-05,
+      "loss": 0.6185,
+      "step": 15000
+    },
+    {
+      "epoch": 2.1011251186119018,
+      "grad_norm": 19.485437393188477,
+      "learning_rate": 1.739324928832859e-05,
+      "loss": 0.4977,
+      "step": 15500
+    },
+    {
+      "epoch": 2.1689033482445437,
+      "grad_norm": 19.35041046142578,
+      "learning_rate": 1.6986579910532734e-05,
+      "loss": 0.4627,
+      "step": 16000
+    },
+    {
+      "epoch": 2.236681577877186,
+      "grad_norm": 11.437379837036133,
+      "learning_rate": 1.6579910532736884e-05,
+      "loss": 0.4954,
+      "step": 16500
+    },
+    {
+      "epoch": 2.304459807509828,
+      "grad_norm": 6.330296039581299,
+      "learning_rate": 1.6173241154941034e-05,
+      "loss": 0.4885,
+      "step": 17000
+    },
+    {
+      "epoch": 2.37223803714247,
+      "grad_norm": 26.632694244384766,
+      "learning_rate": 1.576657177714518e-05,
+      "loss": 0.5022,
+      "step": 17500
+    },
+    {
+      "epoch": 2.4400162667751117,
+      "grad_norm": 10.865219116210938,
+      "learning_rate": 1.535990239934933e-05,
+      "loss": 0.484,
+      "step": 18000
+    },
+    {
+      "epoch": 2.5077944964077536,
+      "grad_norm": 15.621503829956055,
+      "learning_rate": 1.4953233021553476e-05,
+      "loss": 0.4992,
+      "step": 18500
+    },
+    {
+      "epoch": 2.575572726040396,
+      "grad_norm": 4.8670973777771,
+      "learning_rate": 1.4546563643757626e-05,
+      "loss": 0.5067,
+      "step": 19000
+    },
+    {
+      "epoch": 2.643350955673038,
+      "grad_norm": 22.809894561767578,
+      "learning_rate": 1.4139894265961774e-05,
+      "loss": 0.4827,
+      "step": 19500
+    },
+    {
+      "epoch": 2.71112918530568,
+      "grad_norm": 10.14173698425293,
+      "learning_rate": 1.373322488816592e-05,
+      "loss": 0.5003,
+      "step": 20000
+    },
+    {
+      "epoch": 2.7789074149383217,
+      "grad_norm": 19.475053787231445,
+      "learning_rate": 1.3326555510370069e-05,
+      "loss": 0.5022,
+      "step": 20500
+    },
+    {
+      "epoch": 2.8466856445709636,
+      "grad_norm": 22.009613037109375,
+      "learning_rate": 1.2919886132574219e-05,
+      "loss": 0.4949,
+      "step": 21000
+    },
+    {
+      "epoch": 2.914463874203606,
+      "grad_norm": 7.058548927307129,
+      "learning_rate": 1.2513216754778365e-05,
+      "loss": 0.4963,
+      "step": 21500
+    },
+    {
+      "epoch": 2.982242103836248,
+      "grad_norm": 45.82003402709961,
+      "learning_rate": 1.2106547376982513e-05,
+      "loss": 0.4881,
+      "step": 22000
+    },
+    {
+      "epoch": 3.05002033346889,
+      "grad_norm": 7.270058631896973,
+      "learning_rate": 1.1699877999186661e-05,
+      "loss": 0.3598,
+      "step": 22500
+    },
+    {
+      "epoch": 3.1177985631015317,
+      "grad_norm": 10.434412956237793,
+      "learning_rate": 1.129320862139081e-05,
+      "loss": 0.3055,
+      "step": 23000
+    },
+    {
+      "epoch": 3.1855767927341736,
+      "grad_norm": 2.4307031631469727,
+      "learning_rate": 1.0886539243594958e-05,
+      "loss": 0.3264,
+      "step": 23500
+    },
+    {
+      "epoch": 3.253355022366816,
+      "grad_norm": 47.332122802734375,
+      "learning_rate": 1.0479869865799104e-05,
+      "loss": 0.315,
+      "step": 24000
+    },
+    {
+      "epoch": 3.321133251999458,
+      "grad_norm": 16.34264373779297,
+      "learning_rate": 1.0073200488003254e-05,
+      "loss": 0.3251,
+      "step": 24500
+    },
+    {
+      "epoch": 3.3889114816320998,
+      "grad_norm": 13.301547050476074,
+      "learning_rate": 9.666531110207402e-06,
+      "loss": 0.3266,
+      "step": 25000
+    },
+    {
+      "epoch": 3.4566897112647417,
+      "grad_norm": 31.915794372558594,
+      "learning_rate": 9.259861732411548e-06,
+      "loss": 0.3122,
+      "step": 25500
+    },
+    {
+      "epoch": 3.5244679408973836,
+      "grad_norm": 4.690245151519775,
+      "learning_rate": 8.853192354615698e-06,
+      "loss": 0.3051,
+      "step": 26000
+    },
+    {
+      "epoch": 3.592246170530026,
+      "grad_norm": 22.70941734313965,
+      "learning_rate": 8.446522976819846e-06,
+      "loss": 0.3013,
+      "step": 26500
+    },
+    {
+      "epoch": 3.660024400162668,
+      "grad_norm": 19.372514724731445,
+      "learning_rate": 8.039853599023993e-06,
+      "loss": 0.3157,
+      "step": 27000
+    },
+    {
+      "epoch": 3.7278026297953097,
+      "grad_norm": 13.642813682556152,
+      "learning_rate": 7.633184221228141e-06,
+      "loss": 0.3301,
+      "step": 27500
+    },
+    {
+      "epoch": 3.7955808594279516,
+      "grad_norm": 31.518564224243164,
+      "learning_rate": 7.226514843432289e-06,
+      "loss": 0.3157,
+      "step": 28000
+    },
+    {
+      "epoch": 3.8633590890605936,
+      "grad_norm": 56.66007614135742,
+      "learning_rate": 6.819845465636438e-06,
+      "loss": 0.308,
+      "step": 28500
+    },
+    {
+      "epoch": 3.931137318693236,
+      "grad_norm": 11.975343704223633,
+      "learning_rate": 6.413176087840585e-06,
+      "loss": 0.2989,
+      "step": 29000
+    },
+    {
+      "epoch": 3.998915548325878,
+      "grad_norm": 17.2923641204834,
+      "learning_rate": 6.0065067100447335e-06,
+      "loss": 0.3123,
+      "step": 29500
+    },
+    {
+      "epoch": 4.06669377795852,
+      "grad_norm": 23.894207000732422,
+      "learning_rate": 5.5998373322488825e-06,
+      "loss": 0.2082,
+      "step": 30000
+    },
+    {
+      "epoch": 4.134472007591162,
+      "grad_norm": 9.123438835144043,
+      "learning_rate": 5.19316795445303e-06,
+      "loss": 0.2065,
+      "step": 30500
+    },
+    {
+      "epoch": 4.2022502372238035,
+      "grad_norm": 19.249637603759766,
+      "learning_rate": 4.786498576657178e-06,
+      "loss": 0.1926,
+      "step": 31000
+    },
+    {
+      "epoch": 4.270028466856446,
+      "grad_norm": 41.71086883544922,
+      "learning_rate": 4.379829198861326e-06,
+      "loss": 0.2034,
+      "step": 31500
+    },
+    {
+      "epoch": 4.337806696489087,
+      "grad_norm": 1.5960214138031006,
+      "learning_rate": 3.973159821065474e-06,
+      "loss": 0.2139,
+      "step": 32000
+    },
+    {
+      "epoch": 4.40558492612173,
+      "grad_norm": 10.51189136505127,
+      "learning_rate": 3.566490443269622e-06,
+      "loss": 0.195,
+      "step": 32500
+    },
+    {
+      "epoch": 4.473363155754372,
+      "grad_norm": 6.574166297912598,
+      "learning_rate": 3.15982106547377e-06,
+      "loss": 0.2121,
+      "step": 33000
+    },
+    {
+      "epoch": 4.5411413853870135,
+      "grad_norm": 49.01862716674805,
+      "learning_rate": 2.753151687677918e-06,
+      "loss": 0.2121,
+      "step": 33500
+    },
+    {
+      "epoch": 4.608919615019656,
+      "grad_norm": 24.359651565551758,
+      "learning_rate": 2.346482309882066e-06,
+      "loss": 0.2126,
+      "step": 34000
+    },
+    {
+      "epoch": 4.676697844652297,
+      "grad_norm": 11.81959056854248,
+      "learning_rate": 1.939812932086214e-06,
+      "loss": 0.2153,
+      "step": 34500
+    },
+    {
+      "epoch": 4.74447607428494,
+      "grad_norm": 20.48014259338379,
+      "learning_rate": 1.533143554290362e-06,
+      "loss": 0.1941,
+      "step": 35000
+    },
+    {
+      "epoch": 4.812254303917582,
+      "grad_norm": 10.205302238464355,
+      "learning_rate": 1.12647417649451e-06,
+      "loss": 0.1981,
+      "step": 35500
+    },
+    {
+      "epoch": 4.8800325335502235,
+      "grad_norm": 4.869925498962402,
+      "learning_rate": 7.19804798698658e-07,
+      "loss": 0.1984,
+      "step": 36000
+    },
+    {
+      "epoch": 4.947810763182866,
+      "grad_norm": 15.551806449890137,
+      "learning_rate": 3.13135420902806e-07,
+      "loss": 0.196,
+      "step": 36500
+    },
+    {
+      "epoch": 5.0,
+      "step": 36885,
+      "total_flos": 8.674137784986624e+16,
+      "train_loss": 0.6077316944008034,
+      "train_runtime": 4174.9009,
+      "train_samples_per_second": 106.019,
+      "train_steps_per_second": 8.835
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 36885,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.674137784986624e+16,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

README.md

@@ -0,0 +1,86 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: debug_squad
+  results: []
+---
+
+# bert-base-uncased-finetuned-squad
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the SQuAD dataset.
+
+## Model description
+
+- **Model Type:** BERT for Question Answering
+- **Base Model:** bert-base-uncased
+- **Language:** English
+- **Task:** Question Answering
+- **Dataset:** [SQuAD v1.1](https://rajpurkar.github.io/SQuAD-explorer/)
+
+## 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: AdamW_TORCH with beta=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+- training_loss: 0.6077
+- eval_exact_match: 79.508
+- eval_f1: 87.7293
+- train_runtime: 1:09:34.90
+- train_samples_per_second: 106.019
+- train_steps_per_second: 8.835
+
+## Intended uses & limitations
+
+This model is intended for English question answering tasks. It performs best on factual questions where the answer is explicitly stated in the provided context. Note that this model was trained on SQuAD v1.1, which means it always tries to find an answer in the context (it cannot handle questions that have no answer).
+
+### Usage Example
+
+```python
+from transformers import AutoModelForQuestionAnswering, AutoTokenizer
+
+model = AutoModelForQuestionAnswering.from_pretrained("real-jiakai/bert-base-uncased-finetuned-squad")
+tokenizer = AutoTokenizer.from_pretrained("real-jiakai/bert-base-uncased-finetuned-squad")
+
+# Example usage
+context = "BERT was developed by Google in 2018."
+question = "Who developed BERT?"
+
+inputs = tokenizer(question, context, return_tensors="pt")
+outputs = model(**inputs)
+
+answer_start = outputs.start_logits.argmax()
+answer_end = outputs.end_logits.argmax()
+
+answer = tokenizer.decode(inputs["input_ids"][0][answer_start:answer_end+1])
+print(f"Answer: {answer}")  # Expected output: "google"
+```
+
+## Training Infrastructure
+
+- Training Device: Single GPU (NVIDIA Tesla V100 16GB)
+- Training Time: ~70 minutes
+- Framework: PyTorch
+- Training Script: Hugging Face Transformers' `run_qa.py`
+
+### Framework versions
+
+- Transformers 4.47.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_exact_match": 79.50804162724693,
+    "eval_f1": 87.72929499724285,
+    "eval_runtime": 37.9794,
+    "eval_samples": 10784,
+    "eval_samples_per_second": 283.944,
+    "eval_steps_per_second": 35.493,
+    "total_flos": 8.674137784986624e+16,
+    "train_loss": 0.6077316944008034,
+    "train_runtime": 4174.9009,
+    "train_samples": 88524,
+    "train_samples_per_second": 106.019,
+    "train_steps_per_second": 8.835
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "google-bert/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": "4.47.0.dev0",
+  "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:dd23ae26442aa490ccf5ba110358c152327bb4173330536e6a75b52268c7a61d
+size 49623255

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_exact_match": 79.50804162724693,
+    "eval_f1": 87.72929499724285,
+    "eval_runtime": 37.9794,
+    "eval_samples": 10784,
+    "eval_samples_per_second": 283.944,
+    "eval_steps_per_second": 35.493
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce896c126d5592f15d16e130c207405576ec4e190565096669edfea7d130bbf0
+size 435596088

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 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 8.674137784986624e+16,
+    "train_loss": 0.6077316944008034,
+    "train_runtime": 4174.9009,
+    "train_samples": 88524,
+    "train_samples_per_second": 106.019,
+    "train_steps_per_second": 8.835
+}

trainer_state.json

@@ -0,0 +1,553 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 36885,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06777822963264199,
+      "grad_norm": 27.22840690612793,
+      "learning_rate": 2.959333062220415e-05,
+      "loss": 2.3635,
+      "step": 500
+    },
+    {
+      "epoch": 0.13555645926528398,
+      "grad_norm": 13.622244834899902,
+      "learning_rate": 2.9186661244408297e-05,
+      "loss": 1.5111,
+      "step": 1000
+    },
+    {
+      "epoch": 0.203334688897926,
+      "grad_norm": 14.186929702758789,
+      "learning_rate": 2.8779991866612443e-05,
+      "loss": 1.3571,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27111291853056796,
+      "grad_norm": 23.26664161682129,
+      "learning_rate": 2.8373322488816593e-05,
+      "loss": 1.3122,
+      "step": 2000
+    },
+    {
+      "epoch": 0.33889114816321,
+      "grad_norm": 16.56296157836914,
+      "learning_rate": 2.796665311102074e-05,
+      "loss": 1.2847,
+      "step": 2500
+    },
+    {
+      "epoch": 0.406669377795852,
+      "grad_norm": 8.389954566955566,
+      "learning_rate": 2.755998373322489e-05,
+      "loss": 1.2343,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47444760742849396,
+      "grad_norm": 10.328352928161621,
+      "learning_rate": 2.7153314355429036e-05,
+      "loss": 1.1899,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5422258370611359,
+      "grad_norm": 14.220015525817871,
+      "learning_rate": 2.6746644977633186e-05,
+      "loss": 1.1337,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6100040666937779,
+      "grad_norm": 23.481950759887695,
+      "learning_rate": 2.6339975599837332e-05,
+      "loss": 1.1337,
+      "step": 4500
+    },
+    {
+      "epoch": 0.67778229632642,
+      "grad_norm": 26.090124130249023,
+      "learning_rate": 2.593330622204148e-05,
+      "loss": 1.1607,
+      "step": 5000
+    },
+    {
+      "epoch": 0.745560525959062,
+      "grad_norm": 16.809215545654297,
+      "learning_rate": 2.552663684424563e-05,
+      "loss": 1.1114,
+      "step": 5500
+    },
+    {
+      "epoch": 0.813338755591704,
+      "grad_norm": 15.458964347839355,
+      "learning_rate": 2.5119967466449778e-05,
+      "loss": 1.0703,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8811169852243459,
+      "grad_norm": 21.379941940307617,
+      "learning_rate": 2.4713298088653925e-05,
+      "loss": 1.0782,
+      "step": 6500
+    },
+    {
+      "epoch": 0.9488952148569879,
+      "grad_norm": 10.91637134552002,
+      "learning_rate": 2.4306628710858075e-05,
+      "loss": 1.0842,
+      "step": 7000
+    },
+    {
+      "epoch": 1.01667344448963,
+      "grad_norm": 13.034053802490234,
+      "learning_rate": 2.389995933306222e-05,
+      "loss": 0.9463,
+      "step": 7500
+    },
+    {
+      "epoch": 1.0844516741222718,
+      "grad_norm": 15.298956871032715,
+      "learning_rate": 2.3493289955266367e-05,
+      "loss": 0.7336,
+      "step": 8000
+    },
+    {
+      "epoch": 1.152229903754914,
+      "grad_norm": 10.17520523071289,
+      "learning_rate": 2.3086620577470517e-05,
+      "loss": 0.7455,
+      "step": 8500
+    },
+    {
+      "epoch": 1.2200081333875559,
+      "grad_norm": 15.160359382629395,
+      "learning_rate": 2.2679951199674667e-05,
+      "loss": 0.7516,
+      "step": 9000
+    },
+    {
+      "epoch": 1.287786363020198,
+      "grad_norm": 29.048612594604492,
+      "learning_rate": 2.2273281821878813e-05,
+      "loss": 0.7434,
+      "step": 9500
+    },
+    {
+      "epoch": 1.35556459265284,
+      "grad_norm": 24.640453338623047,
+      "learning_rate": 2.1866612444082963e-05,
+      "loss": 0.7673,
+      "step": 10000
+    },
+    {
+      "epoch": 1.4233428222854818,
+      "grad_norm": 16.07855224609375,
+      "learning_rate": 2.1459943066287106e-05,
+      "loss": 0.775,
+      "step": 10500
+    },
+    {
+      "epoch": 1.491121051918124,
+      "grad_norm": 12.662883758544922,
+      "learning_rate": 2.1053273688491256e-05,
+      "loss": 0.7561,
+      "step": 11000
+    },
+    {
+      "epoch": 1.5588992815507658,
+      "grad_norm": 13.590459823608398,
+      "learning_rate": 2.0646604310695406e-05,
+      "loss": 0.7537,
+      "step": 11500
+    },
+    {
+      "epoch": 1.626677511183408,
+      "grad_norm": 12.973872184753418,
+      "learning_rate": 2.0239934932899552e-05,
+      "loss": 0.7513,
+      "step": 12000
+    },
+    {
+      "epoch": 1.6944557408160499,
+      "grad_norm": 17.74153709411621,
+      "learning_rate": 1.9833265555103702e-05,
+      "loss": 0.7666,
+      "step": 12500
+    },
+    {
+      "epoch": 1.7622339704486918,
+      "grad_norm": 14.367899894714355,
+      "learning_rate": 1.9426596177307852e-05,
+      "loss": 0.7787,
+      "step": 13000
+    },
+    {
+      "epoch": 1.830012200081334,
+      "grad_norm": 30.40443992614746,
+      "learning_rate": 1.9019926799511995e-05,
+      "loss": 0.7373,
+      "step": 13500
+    },
+    {
+      "epoch": 1.8977904297139758,
+      "grad_norm": 8.429509162902832,
+      "learning_rate": 1.8613257421716145e-05,
+      "loss": 0.7559,
+      "step": 14000
+    },
+    {
+      "epoch": 1.965568659346618,
+      "grad_norm": 12.091238975524902,
+      "learning_rate": 1.8206588043920295e-05,
+      "loss": 0.7537,
+      "step": 14500
+    },
+    {
+      "epoch": 2.03334688897926,
+      "grad_norm": 7.968406677246094,
+      "learning_rate": 1.779991866612444e-05,
+      "loss": 0.6185,
+      "step": 15000
+    },
+    {
+      "epoch": 2.1011251186119018,
+      "grad_norm": 19.485437393188477,
+      "learning_rate": 1.739324928832859e-05,
+      "loss": 0.4977,
+      "step": 15500
+    },
+    {
+      "epoch": 2.1689033482445437,
+      "grad_norm": 19.35041046142578,
+      "learning_rate": 1.6986579910532734e-05,
+      "loss": 0.4627,
+      "step": 16000
+    },
+    {
+      "epoch": 2.236681577877186,
+      "grad_norm": 11.437379837036133,
+      "learning_rate": 1.6579910532736884e-05,
+      "loss": 0.4954,
+      "step": 16500
+    },
+    {
+      "epoch": 2.304459807509828,
+      "grad_norm": 6.330296039581299,
+      "learning_rate": 1.6173241154941034e-05,
+      "loss": 0.4885,
+      "step": 17000
+    },
+    {
+      "epoch": 2.37223803714247,
+      "grad_norm": 26.632694244384766,
+      "learning_rate": 1.576657177714518e-05,
+      "loss": 0.5022,
+      "step": 17500
+    },
+    {
+      "epoch": 2.4400162667751117,
+      "grad_norm": 10.865219116210938,
+      "learning_rate": 1.535990239934933e-05,
+      "loss": 0.484,
+      "step": 18000
+    },
+    {
+      "epoch": 2.5077944964077536,
+      "grad_norm": 15.621503829956055,
+      "learning_rate": 1.4953233021553476e-05,
+      "loss": 0.4992,
+      "step": 18500
+    },
+    {
+      "epoch": 2.575572726040396,
+      "grad_norm": 4.8670973777771,
+      "learning_rate": 1.4546563643757626e-05,
+      "loss": 0.5067,
+      "step": 19000
+    },
+    {
+      "epoch": 2.643350955673038,
+      "grad_norm": 22.809894561767578,
+      "learning_rate": 1.4139894265961774e-05,
+      "loss": 0.4827,
+      "step": 19500
+    },
+    {
+      "epoch": 2.71112918530568,
+      "grad_norm": 10.14173698425293,
+      "learning_rate": 1.373322488816592e-05,
+      "loss": 0.5003,
+      "step": 20000
+    },
+    {
+      "epoch": 2.7789074149383217,
+      "grad_norm": 19.475053787231445,
+      "learning_rate": 1.3326555510370069e-05,
+      "loss": 0.5022,
+      "step": 20500
+    },
+    {
+      "epoch": 2.8466856445709636,
+      "grad_norm": 22.009613037109375,
+      "learning_rate": 1.2919886132574219e-05,
+      "loss": 0.4949,
+      "step": 21000
+    },
+    {
+      "epoch": 2.914463874203606,
+      "grad_norm": 7.058548927307129,
+      "learning_rate": 1.2513216754778365e-05,
+      "loss": 0.4963,
+      "step": 21500
+    },
+    {
+      "epoch": 2.982242103836248,
+      "grad_norm": 45.82003402709961,
+      "learning_rate": 1.2106547376982513e-05,
+      "loss": 0.4881,
+      "step": 22000
+    },
+    {
+      "epoch": 3.05002033346889,
+      "grad_norm": 7.270058631896973,
+      "learning_rate": 1.1699877999186661e-05,
+      "loss": 0.3598,
+      "step": 22500
+    },
+    {
+      "epoch": 3.1177985631015317,
+      "grad_norm": 10.434412956237793,
+      "learning_rate": 1.129320862139081e-05,
+      "loss": 0.3055,
+      "step": 23000
+    },
+    {
+      "epoch": 3.1855767927341736,
+      "grad_norm": 2.4307031631469727,
+      "learning_rate": 1.0886539243594958e-05,
+      "loss": 0.3264,
+      "step": 23500
+    },
+    {
+      "epoch": 3.253355022366816,
+      "grad_norm": 47.332122802734375,
+      "learning_rate": 1.0479869865799104e-05,
+      "loss": 0.315,
+      "step": 24000
+    },
+    {
+      "epoch": 3.321133251999458,
+      "grad_norm": 16.34264373779297,
+      "learning_rate": 1.0073200488003254e-05,
+      "loss": 0.3251,
+      "step": 24500
+    },
+    {
+      "epoch": 3.3889114816320998,
+      "grad_norm": 13.301547050476074,
+      "learning_rate": 9.666531110207402e-06,
+      "loss": 0.3266,
+      "step": 25000
+    },
+    {
+      "epoch": 3.4566897112647417,
+      "grad_norm": 31.915794372558594,
+      "learning_rate": 9.259861732411548e-06,
+      "loss": 0.3122,
+      "step": 25500
+    },
+    {
+      "epoch": 3.5244679408973836,
+      "grad_norm": 4.690245151519775,
+      "learning_rate": 8.853192354615698e-06,
+      "loss": 0.3051,
+      "step": 26000
+    },
+    {
+      "epoch": 3.592246170530026,
+      "grad_norm": 22.70941734313965,
+      "learning_rate": 8.446522976819846e-06,
+      "loss": 0.3013,
+      "step": 26500
+    },
+    {
+      "epoch": 3.660024400162668,
+      "grad_norm": 19.372514724731445,
+      "learning_rate": 8.039853599023993e-06,
+      "loss": 0.3157,
+      "step": 27000
+    },
+    {
+      "epoch": 3.7278026297953097,
+      "grad_norm": 13.642813682556152,
+      "learning_rate": 7.633184221228141e-06,
+      "loss": 0.3301,
+      "step": 27500
+    },
+    {
+      "epoch": 3.7955808594279516,
+      "grad_norm": 31.518564224243164,
+      "learning_rate": 7.226514843432289e-06,
+      "loss": 0.3157,
+      "step": 28000
+    },
+    {
+      "epoch": 3.8633590890605936,
+      "grad_norm": 56.66007614135742,
+      "learning_rate": 6.819845465636438e-06,
+      "loss": 0.308,
+      "step": 28500
+    },
+    {
+      "epoch": 3.931137318693236,
+      "grad_norm": 11.975343704223633,
+      "learning_rate": 6.413176087840585e-06,
+      "loss": 0.2989,
+      "step": 29000
+    },
+    {
+      "epoch": 3.998915548325878,
+      "grad_norm": 17.2923641204834,
+      "learning_rate": 6.0065067100447335e-06,
+      "loss": 0.3123,
+      "step": 29500
+    },
+    {
+      "epoch": 4.06669377795852,
+      "grad_norm": 23.894207000732422,
+      "learning_rate": 5.5998373322488825e-06,
+      "loss": 0.2082,
+      "step": 30000
+    },
+    {
+      "epoch": 4.134472007591162,
+      "grad_norm": 9.123438835144043,
+      "learning_rate": 5.19316795445303e-06,
+      "loss": 0.2065,
+      "step": 30500
+    },
+    {
+      "epoch": 4.2022502372238035,
+      "grad_norm": 19.249637603759766,
+      "learning_rate": 4.786498576657178e-06,
+      "loss": 0.1926,
+      "step": 31000
+    },
+    {
+      "epoch": 4.270028466856446,
+      "grad_norm": 41.71086883544922,
+      "learning_rate": 4.379829198861326e-06,
+      "loss": 0.2034,
+      "step": 31500
+    },
+    {
+      "epoch": 4.337806696489087,
+      "grad_norm": 1.5960214138031006,
+      "learning_rate": 3.973159821065474e-06,
+      "loss": 0.2139,
+      "step": 32000
+    },
+    {
+      "epoch": 4.40558492612173,
+      "grad_norm": 10.51189136505127,
+      "learning_rate": 3.566490443269622e-06,
+      "loss": 0.195,
+      "step": 32500
+    },
+    {
+      "epoch": 4.473363155754372,
+      "grad_norm": 6.574166297912598,
+      "learning_rate": 3.15982106547377e-06,
+      "loss": 0.2121,
+      "step": 33000
+    },
+    {
+      "epoch": 4.5411413853870135,
+      "grad_norm": 49.01862716674805,
+      "learning_rate": 2.753151687677918e-06,
+      "loss": 0.2121,
+      "step": 33500
+    },
+    {
+      "epoch": 4.608919615019656,
+      "grad_norm": 24.359651565551758,
+      "learning_rate": 2.346482309882066e-06,
+      "loss": 0.2126,
+      "step": 34000
+    },
+    {
+      "epoch": 4.676697844652297,
+      "grad_norm": 11.81959056854248,
+      "learning_rate": 1.939812932086214e-06,
+      "loss": 0.2153,
+      "step": 34500
+    },
+    {
+      "epoch": 4.74447607428494,
+      "grad_norm": 20.48014259338379,
+      "learning_rate": 1.533143554290362e-06,
+      "loss": 0.1941,
+      "step": 35000
+    },
+    {
+      "epoch": 4.812254303917582,
+      "grad_norm": 10.205302238464355,
+      "learning_rate": 1.12647417649451e-06,
+      "loss": 0.1981,
+      "step": 35500
+    },
+    {
+      "epoch": 4.8800325335502235,
+      "grad_norm": 4.869925498962402,
+      "learning_rate": 7.19804798698658e-07,
+      "loss": 0.1984,
+      "step": 36000
+    },
+    {
+      "epoch": 4.947810763182866,
+      "grad_norm": 15.551806449890137,
+      "learning_rate": 3.13135420902806e-07,
+      "loss": 0.196,
+      "step": 36500
+    },
+    {
+      "epoch": 5.0,
+      "step": 36885,
+      "total_flos": 8.674137784986624e+16,
+      "train_loss": 0.6077316944008034,
+      "train_runtime": 4174.9009,
+      "train_samples_per_second": 106.019,
+      "train_steps_per_second": 8.835
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 36885,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.674137784986624e+16,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde90f6aad9ad0797f44f8353b152203daf510ae41a77550fbd06ecf2ecd736f
+size 5368