Model save

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+model-index:
+- name: bert-finetuned-uncased-squad_v2
+  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-finetuned-uncased-squad_v2
+
+This model was trained from scratch on the squad_v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2041
+
+## 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: 2e-05
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.2307        | 0.2   | 100  | 1.8959          |
+| 1.9581        | 0.39  | 200  | 1.4856          |
+| 1.6358        | 0.59  | 300  | 1.3948          |
+| 1.4964        | 0.78  | 400  | 1.2934          |
+| 1.4169        | 0.98  | 500  | 1.2605          |
+| 1.327         | 1.18  | 600  | 1.2218          |
+| 1.2763        | 1.37  | 700  | 1.2539          |
+| 1.2755        | 1.57  | 800  | 1.2090          |
+| 1.251         | 1.76  | 900  | 1.2041          |
+| 1.229         | 1.96  | 1000 | 1.2159          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/bert-finetuned-uncased/checkpoint-1000",
+  "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": "4.34.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

metrics.json

@@ -0,0 +1,15 @@
+{
+    "exact": 27.878379516550154,
+    "f1": 32.12991628283337,
+    "total": 11873,
+    "HasAns_exact": 50.40485829959514,
+    "HasAns_f1": 58.920124160944766,
+    "HasAns_total": 5928,
+    "NoAns_exact": 5.416316232127839,
+    "NoAns_f1": 5.416316232127839,
+    "NoAns_total": 5945,
+    "best_exact": 50.11370336056599,
+    "best_exact_thresh": 0.0,
+    "best_f1": 50.11370336056599,
+    "best_f1_thresh": 0.0
+}

model_card.md

@@ -0,0 +1,32 @@
+
+    ---
+    language: 
+    - en
+    tags:
+    - question-answering
+    - fine-tuned
+    datasets:
+    - squad_v2
+    metrics:
+    - squad
+    ---
+
+    ## bert-finetuned-uncased
+
+    This model is a fine-tuned version of bert-base-uncased for Question Answering on the SQuAD v2 dataset.
+
+    ## Evaluation Results
+    - Exact Match: 27.878379516550154
+    - F1 Score: 32.12991628283337
+    - Total: 11873
+    - Has Answer Exact: 50.40485829959514
+    - Has Answer F1: 58.920124160944766
+    - Has Answer Total: 5928
+    - No Answer Exact: 5.416316232127839
+    - No Answer F1: 5.416316232127839
+    - No Answer Total: 5945
+    - Best Exact: 50.11370336056599
+    - Best Exact Threshold: 0.0
+    - Best F1: 50.11370336056599
+    - Best F1 Threshold: 0.0
+    

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d39e66e7f52d16c9cc4f24176793bc3d6bc7495f18af703341e3c4506ef40b
+size 435640934

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 128,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,176 @@
+{
+  "best_metric": 1.2041057348251343,
+  "best_model_checkpoint": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/bert-finetuned-uncased/checkpoint-900",
+  "epoch": 1.9607843137254903,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.807843137254902e-05,
+      "loss": 3.2307,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.8958784341812134,
+      "eval_runtime": 17.3462,
+      "eval_samples_per_second": 690.006,
+      "eval_steps_per_second": 10.838,
+      "step": 100
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.6117647058823533e-05,
+      "loss": 1.9581,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 1.485579490661621,
+      "eval_runtime": 17.3451,
+      "eval_samples_per_second": 690.051,
+      "eval_steps_per_second": 10.839,
+      "step": 200
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.415686274509804e-05,
+      "loss": 1.6358,
+      "step": 300
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 1.3947598934173584,
+      "eval_runtime": 17.3855,
+      "eval_samples_per_second": 688.449,
+      "eval_steps_per_second": 10.814,
+      "step": 300
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.2196078431372552e-05,
+      "loss": 1.4964,
+      "step": 400
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 1.293440818786621,
+      "eval_runtime": 17.3267,
+      "eval_samples_per_second": 690.782,
+      "eval_steps_per_second": 10.85,
+      "step": 400
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.023529411764706e-05,
+      "loss": 1.4169,
+      "step": 500
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 1.2604990005493164,
+      "eval_runtime": 17.3401,
+      "eval_samples_per_second": 690.251,
+      "eval_steps_per_second": 10.842,
+      "step": 500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 8.274509803921569e-06,
+      "loss": 1.327,
+      "step": 600
+    },
+    {
+      "epoch": 1.18,
+      "eval_loss": 1.2218035459518433,
+      "eval_runtime": 17.3253,
+      "eval_samples_per_second": 690.84,
+      "eval_steps_per_second": 10.851,
+      "step": 600
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 6.313725490196079e-06,
+      "loss": 1.2763,
+      "step": 700
+    },
+    {
+      "epoch": 1.37,
+      "eval_loss": 1.2539091110229492,
+      "eval_runtime": 17.3618,
+      "eval_samples_per_second": 689.388,
+      "eval_steps_per_second": 10.828,
+      "step": 700
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.352941176470588e-06,
+      "loss": 1.2755,
+      "step": 800
+    },
+    {
+      "epoch": 1.57,
+      "eval_loss": 1.2090030908584595,
+      "eval_runtime": 17.401,
+      "eval_samples_per_second": 687.833,
+      "eval_steps_per_second": 10.804,
+      "step": 800
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.392156862745098e-06,
+      "loss": 1.251,
+      "step": 900
+    },
+    {
+      "epoch": 1.76,
+      "eval_loss": 1.2041057348251343,
+      "eval_runtime": 17.3449,
+      "eval_samples_per_second": 690.06,
+      "eval_steps_per_second": 10.839,
+      "step": 900
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 4.3137254901960787e-07,
+      "loss": 1.229,
+      "step": 1000
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.215934157371521,
+      "eval_runtime": 17.3882,
+      "eval_samples_per_second": 688.342,
+      "eval_steps_per_second": 10.812,
+      "step": 1000
+    },
+    {
+      "epoch": 1.96,
+      "step": 1000,
+      "total_flos": 6.687707580928205e+16,
+      "train_loss": 0.0,
+      "train_runtime": 0.5139,
+      "train_samples_per_second": 507861.208,
+      "train_steps_per_second": 992.35
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.204106092453003,
+      "eval_runtime": 17.1369,
+      "eval_samples_per_second": 698.436,
+      "eval_steps_per_second": 5.485,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 510,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 6.687707580928205e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc2823916d105196ea5b63035242c7ca45540892fafe0e7e958e6e13f95a3e48
+size 4664