Upload 16 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
+qa/eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

qa/README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: baseline
+  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. -->
+
+# baseline
+
+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
+
+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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu118
+- Datasets 3.3.1
+- Tokenizers 0.21.0

qa/all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 81.49479659413434,
+    "eval_f1": 88.62945564424126,
+    "eval_runtime": 61.0301,
+    "eval_samples": 10784,
+    "eval_samples_per_second": 176.7,
+    "eval_steps_per_second": 22.087,
+    "total_flos": 3.541929151120589e+16,
+    "train_loss": 1.148573803161563,
+    "train_runtime": 3245.3985,
+    "train_samples": 88524,
+    "train_samples_per_second": 54.554,
+    "train_steps_per_second": 4.546
+}

qa/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": "4.49.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

qa/eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8d44953cbe0ce20d1d1b62b72e7adba18bf1dc81d055492e22bfa21ff46657
+size 49596120

qa/eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 81.49479659413434,
+    "eval_f1": 88.62945564424126,
+    "eval_runtime": 61.0301,
+    "eval_samples": 10784,
+    "eval_samples_per_second": 176.7,
+    "eval_steps_per_second": 22.087
+}

qa/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38003bd65e4bfa70dd16886f29af7ab00d1aa0ae4de191b0a7de4d7883d17dde
+size 442683784

qa/runs/May15_03-24-14_cs-Precision-7960-Tower/events.out.tfevents.1747293859.cs-Precision-7960-Tower.147971.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bfca6273a2422943de7b634cf75efd69b8e92079abe84df9e9c9e026d497f6
+size 11535

qa/runs/May15_03-24-14_cs-Precision-7960-Tower/events.out.tfevents.1747297197.cs-Precision-7960-Tower.147971.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:259c79a03ba9c522b1fd728e92dae5cfc31c6cd73b2377d124749c83a0163910
+size 412

qa/special_tokens_map.json

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

qa/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]"
+}

qa/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 3.541929151120589e+16,
+    "train_loss": 1.148573803161563,
+    "train_runtime": 3245.3985,
+    "train_samples": 88524,
+    "train_samples_per_second": 54.554,
+    "train_steps_per_second": 4.546
+}

qa/trainer_state.json

@@ -0,0 +1,245 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 14754,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06777822963264199,
+      "grad_norm": 31.397275924682617,
+      "learning_rate": 2.8983326555510372e-05,
+      "loss": 2.7299,
+      "step": 500
+    },
+    {
+      "epoch": 0.13555645926528398,
+      "grad_norm": 25.8492431640625,
+      "learning_rate": 2.796665311102074e-05,
+      "loss": 1.752,
+      "step": 1000
+    },
+    {
+      "epoch": 0.203334688897926,
+      "grad_norm": 29.627431869506836,
+      "learning_rate": 2.694997966653111e-05,
+      "loss": 1.5588,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27111291853056796,
+      "grad_norm": 21.147193908691406,
+      "learning_rate": 2.593330622204148e-05,
+      "loss": 1.5014,
+      "step": 2000
+    },
+    {
+      "epoch": 0.33889114816321,
+      "grad_norm": 17.81966781616211,
+      "learning_rate": 2.491663277755185e-05,
+      "loss": 1.4768,
+      "step": 2500
+    },
+    {
+      "epoch": 0.406669377795852,
+      "grad_norm": 20.26822853088379,
+      "learning_rate": 2.389995933306222e-05,
+      "loss": 1.4064,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47444760742849396,
+      "grad_norm": 16.216028213500977,
+      "learning_rate": 2.288328588857259e-05,
+      "loss": 1.3502,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5422258370611359,
+      "grad_norm": 17.930505752563477,
+      "learning_rate": 2.1866612444082963e-05,
+      "loss": 1.3101,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6100040666937779,
+      "grad_norm": 26.499574661254883,
+      "learning_rate": 2.084993899959333e-05,
+      "loss": 1.2922,
+      "step": 4500
+    },
+    {
+      "epoch": 0.67778229632642,
+      "grad_norm": 26.83368492126465,
+      "learning_rate": 1.9833265555103702e-05,
+      "loss": 1.3053,
+      "step": 5000
+    },
+    {
+      "epoch": 0.745560525959062,
+      "grad_norm": 22.85872459411621,
+      "learning_rate": 1.8816592110614073e-05,
+      "loss": 1.2555,
+      "step": 5500
+    },
+    {
+      "epoch": 0.813338755591704,
+      "grad_norm": 23.48080825805664,
+      "learning_rate": 1.779991866612444e-05,
+      "loss": 1.2068,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8811169852243459,
+      "grad_norm": 20.919252395629883,
+      "learning_rate": 1.6783245221634812e-05,
+      "loss": 1.1991,
+      "step": 6500
+    },
+    {
+      "epoch": 0.9488952148569879,
+      "grad_norm": 23.9005126953125,
+      "learning_rate": 1.576657177714518e-05,
+      "loss": 1.2156,
+      "step": 7000
+    },
+    {
+      "epoch": 1.01667344448963,
+      "grad_norm": 22.660743713378906,
+      "learning_rate": 1.4749898332655551e-05,
+      "loss": 1.0827,
+      "step": 7500
+    },
+    {
+      "epoch": 1.0844516741222718,
+      "grad_norm": 25.28419303894043,
+      "learning_rate": 1.373322488816592e-05,
+      "loss": 0.8481,
+      "step": 8000
+    },
+    {
+      "epoch": 1.152229903754914,
+      "grad_norm": 14.510698318481445,
+      "learning_rate": 1.271655144367629e-05,
+      "loss": 0.872,
+      "step": 8500
+    },
+    {
+      "epoch": 1.2200081333875559,
+      "grad_norm": 29.12289810180664,
+      "learning_rate": 1.1699877999186661e-05,
+      "loss": 0.8375,
+      "step": 9000
+    },
+    {
+      "epoch": 1.287786363020198,
+      "grad_norm": 19.038454055786133,
+      "learning_rate": 1.0683204554697033e-05,
+      "loss": 0.8464,
+      "step": 9500
+    },
+    {
+      "epoch": 1.35556459265284,
+      "grad_norm": 21.09101676940918,
+      "learning_rate": 9.666531110207402e-06,
+      "loss": 0.8746,
+      "step": 10000
+    },
+    {
+      "epoch": 1.4233428222854818,
+      "grad_norm": 20.79250144958496,
+      "learning_rate": 8.649857665717772e-06,
+      "loss": 0.8776,
+      "step": 10500
+    },
+    {
+      "epoch": 1.491121051918124,
+      "grad_norm": 21.217571258544922,
+      "learning_rate": 7.633184221228141e-06,
+      "loss": 0.8523,
+      "step": 11000
+    },
+    {
+      "epoch": 1.5588992815507658,
+      "grad_norm": 15.557079315185547,
+      "learning_rate": 6.616510776738511e-06,
+      "loss": 0.8387,
+      "step": 11500
+    },
+    {
+      "epoch": 1.626677511183408,
+      "grad_norm": 14.53345012664795,
+      "learning_rate": 5.5998373322488825e-06,
+      "loss": 0.8377,
+      "step": 12000
+    },
+    {
+      "epoch": 1.6944557408160499,
+      "grad_norm": 26.921611785888672,
+      "learning_rate": 4.583163887759252e-06,
+      "loss": 0.8449,
+      "step": 12500
+    },
+    {
+      "epoch": 1.7622339704486918,
+      "grad_norm": 12.789366722106934,
+      "learning_rate": 3.566490443269622e-06,
+      "loss": 0.8547,
+      "step": 13000
+    },
+    {
+      "epoch": 1.830012200081334,
+      "grad_norm": 37.19759750366211,
+      "learning_rate": 2.549816998779992e-06,
+      "loss": 0.818,
+      "step": 13500
+    },
+    {
+      "epoch": 1.8977904297139758,
+      "grad_norm": 14.62682819366455,
+      "learning_rate": 1.533143554290362e-06,
+      "loss": 0.8128,
+      "step": 14000
+    },
+    {
+      "epoch": 1.965568659346618,
+      "grad_norm": 21.051790237426758,
+      "learning_rate": 5.164701098007319e-07,
+      "loss": 0.8115,
+      "step": 14500
+    },
+    {
+      "epoch": 2.0,
+      "step": 14754,
+      "total_flos": 3.541929151120589e+16,
+      "train_loss": 1.148573803161563,
+      "train_runtime": 3245.3985,
+      "train_samples_per_second": 54.554,
+      "train_steps_per_second": 4.546
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14754,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 3.541929151120589e+16,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

qa/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8e61ba1ca1cb106ca9adca5e9262fa9a262238814728a69256855c78c32f51
+size 5304