Upload 15 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
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,52 @@
----
-license: mit
----
+---
+tags:
+- generated_from_trainer
+datasets:
+- PiC/phrase_retrieval
+model-index:
+- name: finetuned
+  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. -->
+
+# finetuned
+
+This model is a fine-tuned version of [whaleloops/phrase-bert](https://huggingface.co/whaleloops/phrase-bert) on the PiC/phrase_retrieval PR-pass 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.20.1
+- Pytorch 1.10.0+cu113
+- Datasets 2.3.2
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 92.43333333333334,
+    "eval_f1": 94.01345502645503,
+    "eval_samples": 3013,
+    "train_loss": 0.42857344546809384,
+    "train_runtime": 460.898,
+    "train_samples": 20261,
+    "train_samples_per_second": 87.92,
+    "train_steps_per_second": 10.992
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "whaleloops/phrase-bert",
+  "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": "4.20.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca32036e25d8bb4e9c284237924ca33f5d9205c2ef1cd98172eaa6bc34a861a
+size 19171817

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 92.43333333333334,
+    "eval_f1": 94.01345502645503,
+    "eval_samples": 3013
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f69491a3999d9d3af2307a730f0c4012501726e9a42948f8dbde7cb5077d4ebe
+size 435643185

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "name_or_path": "whaleloops/phrase-bert",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/shufanwang/.cache/torch/sentence_transformers/public.ukp.informatik.tu-darmstadt.de_reimers_sentence-transformers_v0.2_bert-base-nli-stsb-mean-tokens.zip/0_BERT/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.42857344546809384,
+    "train_runtime": 460.898,
+    "train_samples": 20261,
+    "train_samples_per_second": 87.92,
+    "train_steps_per_second": 10.992
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 5066,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.7039084090011843e-05,
+      "loss": 1.5542,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.407816818002369e-05,
+      "loss": 0.5455,
+      "step": 1000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.111725227003553e-05,
+      "loss": 0.4854,
+      "step": 1500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.8156336360047373e-05,
+      "loss": 0.4279,
+      "step": 2000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5195420450059218e-05,
+      "loss": 0.4169,
+      "step": 2500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.2234504540071062e-05,
+      "loss": 0.1873,
+      "step": 3000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 9.273588630082906e-06,
+      "loss": 0.2061,
+      "step": 3500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 6.312672720094749e-06,
+      "loss": 0.1751,
+      "step": 4000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.3517568101065932e-06,
+      "loss": 0.1631,
+      "step": 4500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 3.9084090011843665e-07,
+      "loss": 0.1665,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "step": 5066,
+      "total_flos": 1.0588267176456192e+16,
+      "train_loss": 0.42857344546809384,
+      "train_runtime": 460.898,
+      "train_samples_per_second": 87.92,
+      "train_steps_per_second": 10.992
+    }
+  ],
+  "max_steps": 5066,
+  "num_train_epochs": 2,
+  "total_flos": 1.0588267176456192e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60319c99481c832bfe669bfd48feb0e197e7d8c4756367dcf3f36181a8d3beb
+size 3375