Model save

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+model-index:
+- name: roberta-finetuned-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. -->
+
+# roberta-finetuned-squad_v2
+
+This model was trained from scratch on the squad_v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9064
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.9129        | 0.2   | 100  | 1.4700          |
+| 1.4395        | 0.39  | 200  | 1.2407          |
+| 1.2356        | 0.59  | 300  | 1.0325          |
+| 1.1284        | 0.78  | 400  | 0.9750          |
+| 1.0821        | 0.98  | 500  | 0.9345          |
+| 0.9978        | 1.18  | 600  | 0.9893          |
+| 0.9697        | 1.37  | 700  | 0.9300          |
+| 0.9455        | 1.57  | 800  | 0.9351          |
+| 0.9322        | 1.76  | 900  | 0.9451          |
+| 0.9269        | 1.96  | 1000 | 0.9064          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/roberta-finetuned/checkpoint-1000",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

metrics.json

@@ -0,0 +1,15 @@
+{
+    "exact": 37.40419439063421,
+    "f1": 40.42817816263742,
+    "total": 11873,
+    "HasAns_exact": 72.58771929824562,
+    "HasAns_f1": 78.64435886049151,
+    "HasAns_total": 5928,
+    "NoAns_exact": 2.3212783851976453,
+    "NoAns_f1": 2.3212783851976453,
+    "NoAns_total": 5945,
+    "best_exact": 50.09685841825992,
+    "best_exact_thresh": 0.0,
+    "best_f1": 50.09685841825992,
+    "best_f1_thresh": 0.0
+}

model_card.md

@@ -0,0 +1,32 @@
+
+    ---
+    language: 
+    - en
+    tags:
+    - question-answering
+    - fine-tuned
+    datasets:
+    - squad_v2
+    metrics:
+    - squad
+    ---
+
+    ## roberta-finetuned
+
+    This model is a fine-tuned version of roberta-base for Question Answering on the SQuAD v2 dataset.
+
+    ## Evaluation Results
+    - Exact Match: 37.40419439063421
+    - F1 Score: 40.42817816263742
+    - Total: 11873
+    - Has Answer Exact: 72.58771929824562
+    - Has Answer F1: 78.64435886049151
+    - Has Answer Total: 5928
+    - No Answer Exact: 2.3212783851976453
+    - No Answer F1: 2.3212783851976453
+    - No Answer Total: 5945
+    - Best Exact: 50.09685841825992
+    - Best Exact Threshold: 0.0
+    - Best F1: 50.09685841825992
+    - Best F1 Threshold: 0.0
+    

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f7cf441493e72909629a82d2c0fe91b53e0be257030ae6bd2508f535036fef
+size 496295078

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "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": "</s>",
+  "stride": 128,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,176 @@
+{
+  "best_metric": 0.9063502550125122,
+  "best_model_checkpoint": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/roberta-finetuned/checkpoint-1000",
+  "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": 1.811764705882353e-05,
+      "loss": 2.9129,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.4699586629867554,
+      "eval_runtime": 17.6815,
+      "eval_samples_per_second": 676.131,
+      "eval_steps_per_second": 10.576,
+      "step": 100
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.6176470588235296e-05,
+      "loss": 1.4395,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 1.240740418434143,
+      "eval_runtime": 17.6813,
+      "eval_samples_per_second": 676.14,
+      "eval_steps_per_second": 10.576,
+      "step": 200
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.4215686274509805e-05,
+      "loss": 1.2356,
+      "step": 300
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 1.0324599742889404,
+      "eval_runtime": 17.7184,
+      "eval_samples_per_second": 674.723,
+      "eval_steps_per_second": 10.554,
+      "step": 300
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.2254901960784315e-05,
+      "loss": 1.1284,
+      "step": 400
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 0.9749970436096191,
+      "eval_runtime": 17.7173,
+      "eval_samples_per_second": 674.763,
+      "eval_steps_per_second": 10.555,
+      "step": 400
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0294117647058823e-05,
+      "loss": 1.0821,
+      "step": 500
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 0.9345471858978271,
+      "eval_runtime": 17.7101,
+      "eval_samples_per_second": 675.038,
+      "eval_steps_per_second": 10.559,
+      "step": 500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.9978,
+      "step": 600
+    },
+    {
+      "epoch": 1.18,
+      "eval_loss": 0.9892988801002502,
+      "eval_runtime": 17.6864,
+      "eval_samples_per_second": 675.943,
+      "eval_steps_per_second": 10.573,
+      "step": 600
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 6.372549019607843e-06,
+      "loss": 0.9697,
+      "step": 700
+    },
+    {
+      "epoch": 1.37,
+      "eval_loss": 0.9299613237380981,
+      "eval_runtime": 17.7225,
+      "eval_samples_per_second": 674.565,
+      "eval_steps_per_second": 10.552,
+      "step": 700
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 0.9455,
+      "step": 800
+    },
+    {
+      "epoch": 1.57,
+      "eval_loss": 0.9351199865341187,
+      "eval_runtime": 17.7361,
+      "eval_samples_per_second": 674.051,
+      "eval_steps_per_second": 10.543,
+      "step": 800
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.450980392156863e-06,
+      "loss": 0.9322,
+      "step": 900
+    },
+    {
+      "epoch": 1.76,
+      "eval_loss": 0.9450510144233704,
+      "eval_runtime": 17.7032,
+      "eval_samples_per_second": 675.301,
+      "eval_steps_per_second": 10.563,
+      "step": 900
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 4.901960784313725e-07,
+      "loss": 0.9269,
+      "step": 1000
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 0.9063502550125122,
+      "eval_runtime": 17.6937,
+      "eval_samples_per_second": 675.663,
+      "eval_steps_per_second": 10.569,
+      "step": 1000
+    },
+    {
+      "epoch": 1.96,
+      "step": 1000,
+      "total_flos": 6.688961805360538e+16,
+      "train_loss": 0.0,
+      "train_runtime": 0.5646,
+      "train_samples_per_second": 462448.203,
+      "train_steps_per_second": 903.281
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 0.9063528180122375,
+      "eval_runtime": 17.3728,
+      "eval_samples_per_second": 688.145,
+      "eval_steps_per_second": 5.411,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 510,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 6.688961805360538e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c38402081e29ac8ee9e727b8756c0fd6650f5c2f87de20c1e0ce9d11d10ba63
+size 4664