Model save

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+model-index:
+- name: distilbert-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. -->
+
+# distilbert-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: 1.3930
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.6437        | 0.39  | 100  | 2.1780          |
+| 2.1596        | 0.78  | 200  | 1.6557          |
+| 1.8138        | 1.18  | 300  | 1.5683          |
+| 1.6987        | 1.57  | 400  | 1.5076          |
+| 1.6586        | 1.96  | 500  | 1.5350          |
+| 1.5957        | 1.18  | 600  | 1.4431          |
+| 1.5825        | 1.37  | 700  | 1.4955          |
+| 1.5523        | 1.57  | 800  | 1.4444          |
+| 1.5346        | 1.76  | 900  | 1.3930          |
+| 1.5098        | 1.96  | 1000 | 1.4285          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/distilbert-finetuned-uncased/checkpoint-1000",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "vocab_size": 30522
+}

metrics.json

@@ -0,0 +1,15 @@
+{
+    "exact": 23.347090036216628,
+    "f1": 26.869992349988973,
+    "total": 11873,
+    "HasAns_exact": 38.630229419703106,
+    "HasAns_f1": 45.686136837283904,
+    "HasAns_total": 5928,
+    "NoAns_exact": 8.107653490328007,
+    "NoAns_f1": 8.107653490328007,
+    "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
+    ---
+
+    ## distilbert-finetuned-uncased
+
+    This model is a fine-tuned version of distilbert-base-uncased for Question Answering on the SQuAD v2 dataset.
+
+    ## Evaluation Results
+    - Exact Match: 23.347090036216628
+    - F1 Score: 26.869992349988973
+    - Total: 11873
+    - Has Answer Exact: 38.630229419703106
+    - Has Answer F1: 45.686136837283904
+    - Has Answer Total: 5928
+    - No Answer Exact: 8.107653490328007
+    - No Answer F1: 8.107653490328007
+    - 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 sha256:703662f67d3e9c690769d54fb804e87a29ff8bf79e3e8252b54853998eb7c3eb
+size 265493026

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": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,176 @@
+{
+  "best_metric": 1.393009066581726,
+  "best_model_checkpoint": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/distilbert-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": 0.39,
+      "learning_rate": 1.607843137254902e-05,
+      "loss": 3.6437,
+      "step": 100
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 2.1780340671539307,
+      "eval_runtime": 8.4412,
+      "eval_samples_per_second": 1417.927,
+      "eval_steps_per_second": 11.136,
+      "step": 100
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.215686274509804e-05,
+      "loss": 2.1596,
+      "step": 200
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 1.6557185649871826,
+      "eval_runtime": 8.3581,
+      "eval_samples_per_second": 1432.022,
+      "eval_steps_per_second": 11.247,
+      "step": 200
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 1.8138,
+      "step": 300
+    },
+    {
+      "epoch": 1.18,
+      "eval_loss": 1.5682721138000488,
+      "eval_runtime": 8.4191,
+      "eval_samples_per_second": 1421.643,
+      "eval_steps_per_second": 11.165,
+      "step": 300
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.313725490196079e-06,
+      "loss": 1.6987,
+      "step": 400
+    },
+    {
+      "epoch": 1.57,
+      "eval_loss": 1.5075817108154297,
+      "eval_runtime": 8.3595,
+      "eval_samples_per_second": 1431.779,
+      "eval_steps_per_second": 11.245,
+      "step": 400
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.921568627450981e-07,
+      "loss": 1.6586,
+      "step": 500
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.535025715827942,
+      "eval_runtime": 8.4289,
+      "eval_samples_per_second": 1419.991,
+      "eval_steps_per_second": 11.152,
+      "step": 500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 1.5957,
+      "step": 600
+    },
+    {
+      "epoch": 1.18,
+      "eval_loss": 1.4431041479110718,
+      "eval_runtime": 8.5594,
+      "eval_samples_per_second": 1398.342,
+      "eval_steps_per_second": 21.964,
+      "step": 600
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 6.274509803921569e-06,
+      "loss": 1.5825,
+      "step": 700
+    },
+    {
+      "epoch": 1.37,
+      "eval_loss": 1.495514154434204,
+      "eval_runtime": 8.5285,
+      "eval_samples_per_second": 1403.419,
+      "eval_steps_per_second": 22.044,
+      "step": 700
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.313725490196079e-06,
+      "loss": 1.5523,
+      "step": 800
+    },
+    {
+      "epoch": 1.57,
+      "eval_loss": 1.4444433450698853,
+      "eval_runtime": 8.5112,
+      "eval_samples_per_second": 1406.272,
+      "eval_steps_per_second": 22.089,
+      "step": 800
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 1.5346,
+      "step": 900
+    },
+    {
+      "epoch": 1.76,
+      "eval_loss": 1.393009066581726,
+      "eval_runtime": 8.5265,
+      "eval_samples_per_second": 1403.737,
+      "eval_steps_per_second": 22.049,
+      "step": 900
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.921568627450981e-07,
+      "loss": 1.5098,
+      "step": 1000
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.4284701347351074,
+      "eval_runtime": 8.5994,
+      "eval_samples_per_second": 1391.84,
+      "eval_steps_per_second": 21.862,
+      "step": 1000
+    },
+    {
+      "epoch": 1.96,
+      "step": 1000,
+      "total_flos": 5.015589595888435e+16,
+      "train_loss": 0.0,
+      "train_runtime": 0.3601,
+      "train_samples_per_second": 724781.196,
+      "train_steps_per_second": 1416.207
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.3930128812789917,
+      "eval_runtime": 9.4791,
+      "eval_samples_per_second": 1262.677,
+      "eval_steps_per_second": 9.917,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 510,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 5.015589595888435e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a87f249870b023cff0f9cafac8f8d72e450d34b95adf974c8ffc69ce6945fe6
+size 4664