added mrpc

bert-large-uncased/mrpc/README.md

@@ -0,0 +1,79 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+- f1
+model-index:
+- name: mrpc
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      config: mrpc
+      split: validation
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8259803921568627
+    - name: F1
+      type: f1
+      value: 0.8786324786324787
+---
+
+<!-- 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. -->
+
+# mrpc
+
+This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the GLUE MRPC dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4417
+- Accuracy: 0.8260
+- F1: 0.8786
+- Combined Score: 0.8523
+
+## 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: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.27.0.dev0
+- Pytorch 1.12.1
+- Datasets 2.9.0
+- Tokenizers 0.13.2

bert-large-uncased/mrpc/all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8259803921568627,
+    "eval_combined_score": 0.8523064353946708,
+    "eval_f1": 0.8786324786324787,
+    "eval_loss": 0.44171762466430664,
+    "eval_runtime": 3.7061,
+    "eval_samples": 408,
+    "eval_samples_per_second": 110.087,
+    "eval_steps_per_second": 13.761,
+    "train_loss": 0.436454883520154,
+    "train_runtime": 256.895,
+    "train_samples": 3668,
+    "train_samples_per_second": 42.835,
+    "train_steps_per_second": 1.343
+}

bert-large-uncased/mrpc/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "mrpc",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

bert-large-uncased/mrpc/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8259803921568627,
+    "eval_combined_score": 0.8523064353946708,
+    "eval_f1": 0.8786324786324787,
+    "eval_loss": 0.44171762466430664,
+    "eval_runtime": 3.7061,
+    "eval_samples": 408,
+    "eval_samples_per_second": 110.087,
+    "eval_steps_per_second": 13.761
+}

bert-large-uncased/mrpc/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0c3b2c54fb9436a6bebafa7c80721bade49115623783436e74c9cfc712b64c
+size 1340711725

bert-large-uncased/mrpc/runs/Jan28_17-07-48_holygpu2c0701.rc.fas.harvard.edu/1674943676.9669356/events.out.tfevents.1674943676.holygpu2c0701.rc.fas.harvard.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c06cf09b1b14d8cb7a7167ae71aae761ba5fc4f5cb3af9647c97621dbbb2be1
+size 5420

bert-large-uncased/mrpc/runs/Jan28_17-07-48_holygpu2c0701.rc.fas.harvard.edu/events.out.tfevents.1674943676.holygpu2c0701.rc.fas.harvard.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c39c2ccd46e2c7d477d0a0a59720124092b802e26e664a9c0fd6d3a0bbc64ca
+size 4328

bert-large-uncased/mrpc/runs/Jan28_17-07-48_holygpu2c0701.rc.fas.harvard.edu/events.out.tfevents.1674943769.holygpu2c0701.rc.fas.harvard.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e59ff2650002e6a9ff65bc9769499e1500c72d069b4fb5ec45004bf4a1a85324
+size 467

bert-large-uncased/mrpc/runs/Jan29_17-17-01_holygpu2c0701.rc.fas.harvard.edu/1675030682.098054/events.out.tfevents.1675030682.holygpu2c0701.rc.fas.harvard.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6becd849ca8baada0700fdc7def10eb3e62e909eb395d463edbedc6b145fffc
+size 5420

bert-large-uncased/mrpc/runs/Jan29_17-17-01_holygpu2c0701.rc.fas.harvard.edu/events.out.tfevents.1675030682.holygpu2c0701.rc.fas.harvard.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76169f7fc5d0540c3d7cae147f11272b5f1ed6f8a11d6d78fe4f9faffc08db14
+size 4331

bert-large-uncased/mrpc/runs/Jan29_17-17-01_holygpu2c0701.rc.fas.harvard.edu/events.out.tfevents.1675030945.holygpu2c0701.rc.fas.harvard.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932e6d30ad20bba279157b416883f3278610465d2e172d385d78d7d33b44fc8d
+size 467

bert-large-uncased/mrpc/special_tokens_map.json

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

bert-large-uncased/mrpc/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-large-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

bert-large-uncased/mrpc/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.436454883520154,
+    "train_runtime": 256.895,
+    "train_samples": 3668,
+    "train_samples_per_second": 42.835,
+    "train_steps_per_second": 1.343
+}

bert-large-uncased/mrpc/trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 345,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 345,
+      "total_flos": 2563743180515328.0,
+      "train_loss": 0.436454883520154,
+      "train_runtime": 256.895,
+      "train_samples_per_second": 42.835,
+      "train_steps_per_second": 1.343
+    }
+  ],
+  "max_steps": 345,
+  "num_train_epochs": 3,
+  "total_flos": 2563743180515328.0,
+  "trial_name": null,
+  "trial_params": null
+}

bert-large-uncased/mrpc/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af64ccc30e3b5b5eed9e4e705382ccae66a6ee46cb0c7851ef1e4c8a70451ffa
+size 3503