Training in progress, step 80, checkpoint

checkpoint-80/1_AdvancedWeightedPooling/config.json

@@ -0,0 +1,8 @@
+{
+  "embed_dim": 768,
+  "num_heads": 8,
+  "dropout": 0.0,
+  "bias": true,
+  "gate_min": 0.2,
+  "gate_max": 0.8
+}

checkpoint-80/1_AdvancedWeightedPooling/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b3bf7f68b54022b657064f0d11be90d3cad99199570681a5d8da186525370b2
+size 11828367

checkpoint-80/README.md

@@ -0,0 +1,899 @@
+---
+base_model: microsoft/deberta-v3-small
+datasets:
+- tals/vitaminc
+language:
+- en
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:225247
+- loss:CachedGISTEmbedLoss
+widget:
+- source_sentence: how long to grill boneless skinless chicken breasts in oven
+  sentences:
+  - "[ syll. a-ka-hi, ak-ahi ] The baby boy name Akahi is also used as a girl name.\
+    \ Its pronunciation is AA K AA HHiy â\x80 . Akahi's origin, as well as its use,\
+    \ is in the Hawaiian language. The name's meaning is never before. Akahi is infrequently\
+    \ used as a baby name for boys."
+  - October consists of 31 days. November has 30 days. When you add both together
+    they have 61 days.
+  - Heat a grill or grill pan. When the grill is hot, place the chicken on the grill
+    and cook for about 4 minutes per side, or until cooked through. You can also bake
+    the thawed chicken in a 375 degree F oven for 15 minutes, or until cooked through.
+- source_sentence: More than 273 people have died from the 2019-20 coronavirus outside
+    mainland China .
+  sentences:
+  - 'More than 3,700 people have died : around 3,100 in mainland China and around
+    550 in all other countries combined .'
+  - 'More than 3,200 people have died : almost 3,000 in mainland China and around
+    275 in other countries .'
+  - more than 4,900 deaths have been attributed to COVID-19 .
+- source_sentence: Most red algae species live in oceans.
+  sentences:
+  - Where do most red algae species live?
+  - Which layer of the earth is molten?
+  - As a diver descends, the increase in pressure causes the body’s air pockets in
+    the ears and lungs to do what?
+- source_sentence: Binary compounds of carbon with less electronegative elements are
+    called carbides.
+  sentences:
+  - What are four children born at one birth called?
+  - Binary compounds of carbon with less electronegative elements are called what?
+  - The water cycle involves movement of water between air and what?
+- source_sentence: What is the basic monetary unit of Iceland?
+  sentences:
+  - 'Ao dai - Vietnamese traditional dress - YouTube Ao dai - Vietnamese traditional
+    dress Want to watch this again later? Sign in to add this video to a playlist.
+    Need to report the video? Sign in to report inappropriate content. Rating is available
+    when the video has been rented. This feature is not available right now. Please
+    try again later. Uploaded on Jul 8, 2009 Simple, yet charming, graceful and elegant,
+    áo dài was designed to praise the slender beauty of Vietnamese women. The dress
+    is a genius combination of ancient and modern. It shows every curve on the girl''s
+    body, creating sexiness for the wearer, yet it still preserves the traditional
+    feminine grace of Vietnamese women with its charming flowing flaps. The simplicity
+    of áo dài makes it convenient and practical, something that other Asian traditional
+    clothes lack. The waist-length slits of the flaps allow every movement of the
+    legs: walking, running, riding a bicycle, climbing a tree, doing high kicks. The
+    looseness of the pants allows comfortability. As a girl walks in áo dài, the movements
+    of the flaps make it seem like she''s not walking but floating in the air. This
+    breath-taking beautiful image of a Vietnamese girl walking in áo dài has been
+    an inspiration for generations of Vietnamese poets, novelists, artists and has
+    left a deep impression for every foreigner who has visited the country. Category'
+  - 'Icelandic monetary unit - definition of Icelandic monetary unit by The Free Dictionary
+    Icelandic monetary unit - definition of Icelandic monetary unit by The Free Dictionary
+    http://www.thefreedictionary.com/Icelandic+monetary+unit Related to Icelandic
+    monetary unit: Icelandic Old Krona ThesaurusAntonymsRelated WordsSynonymsLegend:
+    monetary unit - a unit of money Icelandic krona , krona - the basic unit of money
+    in Iceland eyrir - 100 aurar equal 1 krona in Iceland Want to thank TFD for its
+    existence? Tell a friend about us , add a link to this page, or visit the webmaster''s
+    page for free fun content . Link to this page: Copyright © 2003-2017 Farlex, Inc
+    Disclaimer All content on this website, including dictionary, thesaurus, literature,
+    geography, and other reference data is for informational purposes only. This information
+    should not be considered complete, up to date, and is not intended to be used
+    in place of a visit, consultation, or advice of a legal, medical, or any other
+    professional.'
+  - 'Food-Info.net : E-numbers : E140: Chlorophyll CI 75810, Natural Green 3, Chlorophyll
+    A, Magnesium chlorophyll Origin: Natural green colour, present in all plants and
+    algae. Commercially extracted from nettles, grass and alfalfa. Function & characteristics:'
+model-index:
+- name: SentenceTransformer based on microsoft/deberta-v3-small
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.22248205020578934
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.24802235964390085
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.26632593273308647
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.2843623073856928
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.2323160413842197
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.24799036249272113
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.22239084967931927
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.24791612015173234
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.26632593273308647
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.2843623073856928
+      name: Spearman Max
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: allNLI dev
+      type: allNLI-dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.666015625
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.983686089515686
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.5065885797950219
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7642872333526611
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.3392156862745098
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 1.0
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.34411819659341086
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.666015625
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 755.60302734375
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.5065885797950219
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 587.0625
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.3392156862745098
+      name: Dot Precision
+    - type: dot_recall
+      value: 1.0
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.344109544232086
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.6640625
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 62.69102096557617
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.5058479532163743
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 337.6861877441406
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.3385518590998043
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 1.0
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.35131239981425566
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.666015625
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 5.00581693649292
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.5065885797950219
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 19.022436141967773
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.3392156862745098
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 1.0
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.3441246898925644
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.666015625
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 755.60302734375
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.5065885797950219
+      name: Max F1
+    - type: max_f1_threshold
+      value: 587.0625
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.3392156862745098
+      name: Max Precision
+    - type: max_recall
+      value: 1.0
+      name: Max Recall
+    - type: max_ap
+      value: 0.35131239981425566
+      name: Max Ap
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: Qnli dev
+      type: Qnli-dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.591796875
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.9258557558059692
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.6291834002677376
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.750666618347168
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.4598825831702544
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9957627118644068
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.5585355274462735
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.591796875
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 711.18359375
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.6291834002677376
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 576.5970458984375
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.4598825831702544
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9957627118644068
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.5585297234749824
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.619140625
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 188.09068298339844
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.6301775147928994
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 237.80462646484375
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.48409090909090907
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.902542372881356
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.5898283705050701
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.591796875
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 10.672666549682617
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.6291834002677376
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 19.553747177124023
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.4598825831702544
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9957627118644068
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.5585355274462735
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.619140625
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 711.18359375
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.6301775147928994
+      name: Max F1
+    - type: max_f1_threshold
+      value: 576.5970458984375
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.48409090909090907
+      name: Max Precision
+    - type: max_recall
+      value: 0.9957627118644068
+      name: Max Recall
+    - type: max_ap
+      value: 0.5898283705050701
+      name: Max Ap
+---
+
+# SentenceTransformer based on microsoft/deberta-v3-small
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) <!-- at revision a36c739020e01763fe789b4b85e2df55d6180012 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DebertaV2Model 
+  (1): AdvancedWeightedPooling(
+    (linear_cls): Linear(in_features=768, out_features=768, bias=True)
+    (mha): MultiheadAttention(
+      (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+    )
+    (layernorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+    (layernorm2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+  )
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("bobox/DeBERTa3-s-CustomPooling-test1-checkpoints-tmp")
+# Run inference
+sentences = [
+    'What is the basic monetary unit of Iceland?',
+    "Icelandic monetary unit - definition of Icelandic monetary unit by The Free Dictionary Icelandic monetary unit - definition of Icelandic monetary unit by The Free Dictionary http://www.thefreedictionary.com/Icelandic+monetary+unit Related to Icelandic monetary unit: Icelandic Old Krona ThesaurusAntonymsRelated WordsSynonymsLegend: monetary unit - a unit of money Icelandic krona , krona - the basic unit of money in Iceland eyrir - 100 aurar equal 1 krona in Iceland Want to thank TFD for its existence? Tell a friend about us , add a link to this page, or visit the webmaster's page for free fun content . Link to this page: Copyright © 2003-2017 Farlex, Inc Disclaimer All content on this website, including dictionary, thesaurus, literature, geography, and other reference data is for informational purposes only. This information should not be considered complete, up to date, and is not intended to be used in place of a visit, consultation, or advice of a legal, medical, or any other professional.",
+    'Food-Info.net : E-numbers : E140: Chlorophyll CI 75810, Natural Green 3, Chlorophyll A, Magnesium chlorophyll Origin: Natural green colour, present in all plants and algae. Commercially extracted from nettles, grass and alfalfa. Function & characteristics:',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.2225    |
+| **spearman_cosine** | **0.248** |
+| pearson_manhattan   | 0.2663    |
+| spearman_manhattan  | 0.2844    |
+| pearson_euclidean   | 0.2323    |
+| spearman_euclidean  | 0.248     |
+| pearson_dot         | 0.2224    |
+| spearman_dot        | 0.2479    |
+| pearson_max         | 0.2663    |
+| spearman_max        | 0.2844    |
+
+#### Binary Classification
+* Dataset: `allNLI-dev`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.666      |
+| cosine_accuracy_threshold    | 0.9837     |
+| cosine_f1                    | 0.5066     |
+| cosine_f1_threshold          | 0.7643     |
+| cosine_precision             | 0.3392     |
+| cosine_recall                | 1.0        |
+| cosine_ap                    | 0.3441     |
+| dot_accuracy                 | 0.666      |
+| dot_accuracy_threshold       | 755.603    |
+| dot_f1                       | 0.5066     |
+| dot_f1_threshold             | 587.0625   |
+| dot_precision                | 0.3392     |
+| dot_recall                   | 1.0        |
+| dot_ap                       | 0.3441     |
+| manhattan_accuracy           | 0.6641     |
+| manhattan_accuracy_threshold | 62.691     |
+| manhattan_f1                 | 0.5058     |
+| manhattan_f1_threshold       | 337.6862   |
+| manhattan_precision          | 0.3386     |
+| manhattan_recall             | 1.0        |
+| manhattan_ap                 | 0.3513     |
+| euclidean_accuracy           | 0.666      |
+| euclidean_accuracy_threshold | 5.0058     |
+| euclidean_f1                 | 0.5066     |
+| euclidean_f1_threshold       | 19.0224    |
+| euclidean_precision          | 0.3392     |
+| euclidean_recall             | 1.0        |
+| euclidean_ap                 | 0.3441     |
+| max_accuracy                 | 0.666      |
+| max_accuracy_threshold       | 755.603    |
+| max_f1                       | 0.5066     |
+| max_f1_threshold             | 587.0625   |
+| max_precision                | 0.3392     |
+| max_recall                   | 1.0        |
+| **max_ap**                   | **0.3513** |
+
+#### Binary Classification
+* Dataset: `Qnli-dev`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.5918     |
+| cosine_accuracy_threshold    | 0.9259     |
+| cosine_f1                    | 0.6292     |
+| cosine_f1_threshold          | 0.7507     |
+| cosine_precision             | 0.4599     |
+| cosine_recall                | 0.9958     |
+| cosine_ap                    | 0.5585     |
+| dot_accuracy                 | 0.5918     |
+| dot_accuracy_threshold       | 711.1836   |
+| dot_f1                       | 0.6292     |
+| dot_f1_threshold             | 576.597    |
+| dot_precision                | 0.4599     |
+| dot_recall                   | 0.9958     |
+| dot_ap                       | 0.5585     |
+| manhattan_accuracy           | 0.6191     |
+| manhattan_accuracy_threshold | 188.0907   |
+| manhattan_f1                 | 0.6302     |
+| manhattan_f1_threshold       | 237.8046   |
+| manhattan_precision          | 0.4841     |
+| manhattan_recall             | 0.9025     |
+| manhattan_ap                 | 0.5898     |
+| euclidean_accuracy           | 0.5918     |
+| euclidean_accuracy_threshold | 10.6727    |
+| euclidean_f1                 | 0.6292     |
+| euclidean_f1_threshold       | 19.5537    |
+| euclidean_precision          | 0.4599     |
+| euclidean_recall             | 0.9958     |
+| euclidean_ap                 | 0.5585     |
+| max_accuracy                 | 0.6191     |
+| max_accuracy_threshold       | 711.1836   |
+| max_f1                       | 0.6302     |
+| max_f1_threshold             | 576.597    |
+| max_precision                | 0.4841     |
+| max_recall                   | 0.9958     |
+| **max_ap**                   | **0.5898** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Evaluation Dataset
+
+#### vitaminc-pairs
+
+* Dataset: [vitaminc-pairs](https://huggingface.co/datasets/tals/vitaminc) at [be6febb](https://huggingface.co/datasets/tals/vitaminc/tree/be6febb761b0b2807687e61e0b5282e459df2fa0)
+* Size: 128 evaluation samples
+* Columns: <code>claim</code> and <code>evidence</code>
+* Approximate statistics based on the first 128 samples:
+  |         | claim                                                                             | evidence                                                                           |
+  |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                             |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 21.42 tokens</li><li>max: 41 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 35.55 tokens</li><li>max: 79 tokens</li></ul> |
+* Samples:
+  | claim                                                                               | evidence                                                                                                                                                                                                                                                                                                                                               |
+  |:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Dragon Con had over 5000 guests .</code>                                      | <code>Among the more than 6000 guests and musical performers at the 2009 convention were such notables as Patrick Stewart , William Shatner , Leonard Nimoy , Terry Gilliam , Bruce Boxleitner , James Marsters , and Mary McDonnell .</code>                                                                                                          |
+  | <code>COVID-19 has reached more than 185 countries .</code>                         | <code>As of , more than cases of COVID-19 have been reported in more than 190 countries and 200 territories , resulting in more than deaths .</code>                                                                                                                                                                                                   |
+  | <code>In March , Italy had 3.6x times more cases of coronavirus than China .</code> | <code>As of 12 March , among nations with at least one million citizens , Italy has the world 's highest per capita rate of positive coronavirus cases at 206.1 cases per million people ( 3.6x times the rate of China ) and is the country with the second-highest number of positive cases as well as of deaths in the world , after China .</code> |
+* Loss: [<code>CachedGISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedgistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.025}
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 42
+- `per_device_eval_batch_size`: 128
+- `gradient_accumulation_steps`: 2
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.001
+- `lr_scheduler_type`: cosine_with_min_lr
+- `lr_scheduler_kwargs`: {'num_cycles': 0.5, 'min_lr': 1e-05}
+- `warmup_ratio`: 0.25
+- `save_safetensors`: False
+- `fp16`: True
+- `push_to_hub`: True
+- `hub_model_id`: bobox/DeBERTa3-s-CustomPooling-test1-checkpoints-tmp
+- `hub_strategy`: all_checkpoints
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 42
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.001
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine_with_min_lr
+- `lr_scheduler_kwargs`: {'num_cycles': 0.5, 'min_lr': 1e-05}
+- `warmup_ratio`: 0.25
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: False
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: True
+- `resume_from_checkpoint`: None
+- `hub_model_id`: bobox/DeBERTa3-s-CustomPooling-test1-checkpoints-tmp
+- `hub_strategy`: all_checkpoints
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | vitaminc-pairs loss | negation-triplets loss | scitail-pairs-pos loss | scitail-pairs-qa loss | xsum-pairs loss | sciq pairs loss | qasc pairs loss | openbookqa pairs loss | msmarco pairs loss | nq pairs loss | trivia pairs loss | gooaq pairs loss | paws-pos loss | global dataset loss | sts-test_spearman_cosine | allNLI-dev_max_ap | Qnli-dev_max_ap |
+|:------:|:----:|:-------------:|:-------------------:|:----------------------:|:----------------------:|:---------------------:|:---------------:|:---------------:|:---------------:|:---------------------:|:------------------:|:-------------:|:-----------------:|:----------------:|:-------------:|:-------------------:|:------------------------:|:-----------------:|:---------------:|
+| 0.0009 | 1    | 5.8564        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0018 | 2    | 7.1716        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0027 | 3    | 5.9095        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0035 | 4    | 5.0841        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0044 | 5    | 4.0184        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0053 | 6    | 6.2191        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0062 | 7    | 5.6124        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0071 | 8    | 3.9544        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0080 | 9    | 4.7149        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0088 | 10   | 4.9616        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0097 | 11   | 5.2794        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0106 | 12   | 8.8704        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0115 | 13   | 6.0707        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0124 | 14   | 5.4071        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0133 | 15   | 6.9104        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0142 | 16   | 6.0276        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0150 | 17   | 6.737         | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0159 | 18   | 6.5354        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0168 | 19   | 5.206         | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0177 | 20   | 5.2469        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0186 | 21   | 5.3771        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0195 | 22   | 4.979         | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0204 | 23   | 4.7909        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0212 | 24   | 4.9086        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0221 | 25   | 4.8826        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0230 | 26   | 8.2266        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0239 | 27   | 8.3024        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0248 | 28   | 5.8745        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0257 | 29   | 4.7298        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0265 | 30   | 5.4614        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0274 | 31   | 5.8594        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0283 | 32   | 5.2401        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0292 | 33   | 5.1579        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0301 | 34   | 5.2181        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0310 | 35   | 4.6328        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0319 | 36   | 2.121         | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0327 | 37   | 5.9026        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0336 | 38   | 7.3796        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0345 | 39   | 5.5361        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0354 | 40   | 4.0243        | 2.9018              | 5.6903                 | 2.1136                 | 2.8052                | 6.5831          | 0.8882          | 4.1148          | 5.0966                | 10.3911            | 10.9032       | 7.1904            | 8.1935           | 1.3943        | 5.6716              | 0.1879                   | 0.3385            | 0.5781          |
+| 0.0363 | 41   | 4.9072        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0372 | 42   | 3.4439        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0381 | 43   | 4.9787        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0389 | 44   | 5.8318        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0398 | 45   | 5.3226        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0407 | 46   | 5.1181        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0416 | 47   | 4.7834        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0425 | 48   | 6.6303        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0434 | 49   | 5.8171        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0442 | 50   | 5.1962        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0451 | 51   | 5.2096        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0460 | 52   | 5.0943        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0469 | 53   | 4.9038        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0478 | 54   | 4.6479        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0487 | 55   | 5.5098        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0496 | 56   | 4.6979        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0504 | 57   | 3.1969        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0513 | 58   | 4.4127        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0522 | 59   | 3.7746        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0531 | 60   | 4.5378        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0540 | 61   | 5.0209        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0549 | 62   | 6.5936        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0558 | 63   | 4.2315        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0566 | 64   | 6.4269        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0575 | 65   | 4.2644        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0584 | 66   | 5.1388        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0593 | 67   | 5.1852        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0602 | 68   | 4.8057        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0611 | 69   | 3.1725        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0619 | 70   | 3.3322        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0628 | 71   | 5.139         | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0637 | 72   | 4.307         | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0646 | 73   | 5.0133        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0655 | 74   | 4.0507        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0664 | 75   | 3.3895        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0673 | 76   | 5.6736        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0681 | 77   | 4.2572        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0690 | 78   | 3.0796        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0699 | 79   | 5.0199        | -                   | -                      | -                      | -                     | -               | -               | -               | -                     | -                  | -             | -                 | -                | -             | -                   | -                        | -                 | -               |
+| 0.0708 | 80   | 4.1414        | 2.7794              | 4.8890                 | 1.8997                 | 2.6761                | 6.2096          | 0.7622          | 3.3129          | 4.5498                | 7.2056             | 7.6809        | 6.3792            | 6.6567           | 1.3848        | 5.0030              | 0.2480                   | 0.3513            | 0.5898          |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.2.0
+- Transformers: 4.45.1
+- PyTorch: 2.4.0
+- Accelerate: 0.34.2
+- Datasets: 3.0.1
+- Tokenizers: 0.20.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

checkpoint-80/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

checkpoint-80/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2Model"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-80/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.0",
+    "transformers": "4.45.1",
+    "pytorch": "2.4.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-80/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_AdvancedWeightedPooling",
+    "type": "__main__.AdvancedWeightedPooling"
+  }
+]

checkpoint-80/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54cb91d89a9ceb4c5c238647ad187b3837a529d099e477303ac25dab6fcc341c
+size 245742074

checkpoint-80/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02cd4ccb01d28af28e563810d015e0bfcbf2f3d9c978732487e0120e35cdb1f7
+size 565251810

checkpoint-80/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18f9fac3c175cfc1292deb2d04e1fe210321ba3ff20498b0e9c71192ddfeb9c8
+size 14244

checkpoint-80/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2cbfe905841f1188488869af5b7dc208420cd27f8d81a2ad1951627737978f4
+size 1192

checkpoint-80/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

checkpoint-80/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-80/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

checkpoint-80/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

checkpoint-80/trainer_state.json

@@ -0,0 +1,979 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07079646017699115,
+  "eval_steps": 40,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008849557522123894,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 5.8564,
+      "step": 1
+    },
+    {
+      "epoch": 0.0017699115044247787,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 7.1716,
+      "step": 2
+    },
+    {
+      "epoch": 0.002654867256637168,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 5.9095,
+      "step": 3
+    },
+    {
+      "epoch": 0.0035398230088495575,
+      "grad_norm": 21.95326805114746,
+      "learning_rate": 3.5377358490566036e-09,
+      "loss": 5.0841,
+      "step": 4
+    },
+    {
+      "epoch": 0.004424778761061947,
+      "grad_norm": 16.607179641723633,
+      "learning_rate": 7.075471698113207e-09,
+      "loss": 4.0184,
+      "step": 5
+    },
+    {
+      "epoch": 0.005309734513274336,
+      "grad_norm": 33.789615631103516,
+      "learning_rate": 1.0613207547169811e-08,
+      "loss": 6.2191,
+      "step": 6
+    },
+    {
+      "epoch": 0.006194690265486726,
+      "grad_norm": 28.073551177978516,
+      "learning_rate": 1.4150943396226414e-08,
+      "loss": 5.6124,
+      "step": 7
+    },
+    {
+      "epoch": 0.007079646017699115,
+      "grad_norm": 17.365602493286133,
+      "learning_rate": 1.768867924528302e-08,
+      "loss": 3.9544,
+      "step": 8
+    },
+    {
+      "epoch": 0.007964601769911504,
+      "grad_norm": 19.384475708007812,
+      "learning_rate": 2.1226415094339622e-08,
+      "loss": 4.7149,
+      "step": 9
+    },
+    {
+      "epoch": 0.008849557522123894,
+      "grad_norm": 19.67770004272461,
+      "learning_rate": 2.4764150943396227e-08,
+      "loss": 4.9616,
+      "step": 10
+    },
+    {
+      "epoch": 0.009734513274336283,
+      "grad_norm": 24.233421325683594,
+      "learning_rate": 2.830188679245283e-08,
+      "loss": 5.2794,
+      "step": 11
+    },
+    {
+      "epoch": 0.010619469026548672,
+      "grad_norm": Infinity,
+      "learning_rate": 2.830188679245283e-08,
+      "loss": 8.8704,
+      "step": 12
+    },
+    {
+      "epoch": 0.011504424778761062,
+      "grad_norm": 34.37785720825195,
+      "learning_rate": 3.183962264150943e-08,
+      "loss": 6.0707,
+      "step": 13
+    },
+    {
+      "epoch": 0.012389380530973451,
+      "grad_norm": 25.11741065979004,
+      "learning_rate": 3.537735849056604e-08,
+      "loss": 5.4071,
+      "step": 14
+    },
+    {
+      "epoch": 0.01327433628318584,
+      "grad_norm": 53.84364700317383,
+      "learning_rate": 3.891509433962264e-08,
+      "loss": 6.9104,
+      "step": 15
+    },
+    {
+      "epoch": 0.01415929203539823,
+      "grad_norm": 32.0903434753418,
+      "learning_rate": 4.2452830188679244e-08,
+      "loss": 6.0276,
+      "step": 16
+    },
+    {
+      "epoch": 0.01504424778761062,
+      "grad_norm": 39.742130279541016,
+      "learning_rate": 4.599056603773585e-08,
+      "loss": 6.737,
+      "step": 17
+    },
+    {
+      "epoch": 0.01592920353982301,
+      "grad_norm": 45.267417907714844,
+      "learning_rate": 4.9528301886792454e-08,
+      "loss": 6.5354,
+      "step": 18
+    },
+    {
+      "epoch": 0.016814159292035398,
+      "grad_norm": 22.39731788635254,
+      "learning_rate": 5.3066037735849055e-08,
+      "loss": 5.206,
+      "step": 19
+    },
+    {
+      "epoch": 0.017699115044247787,
+      "grad_norm": 20.858232498168945,
+      "learning_rate": 5.660377358490566e-08,
+      "loss": 5.2469,
+      "step": 20
+    },
+    {
+      "epoch": 0.018584070796460177,
+      "grad_norm": 23.96446990966797,
+      "learning_rate": 6.014150943396226e-08,
+      "loss": 5.3771,
+      "step": 21
+    },
+    {
+      "epoch": 0.019469026548672566,
+      "grad_norm": 22.945741653442383,
+      "learning_rate": 6.367924528301887e-08,
+      "loss": 4.979,
+      "step": 22
+    },
+    {
+      "epoch": 0.020353982300884955,
+      "grad_norm": 15.497300148010254,
+      "learning_rate": 6.721698113207547e-08,
+      "loss": 4.7909,
+      "step": 23
+    },
+    {
+      "epoch": 0.021238938053097345,
+      "grad_norm": 20.039024353027344,
+      "learning_rate": 7.075471698113208e-08,
+      "loss": 4.9086,
+      "step": 24
+    },
+    {
+      "epoch": 0.022123893805309734,
+      "grad_norm": 21.30576515197754,
+      "learning_rate": 7.429245283018869e-08,
+      "loss": 4.8826,
+      "step": 25
+    },
+    {
+      "epoch": 0.023008849557522124,
+      "grad_norm": 64.5285873413086,
+      "learning_rate": 7.783018867924529e-08,
+      "loss": 8.2266,
+      "step": 26
+    },
+    {
+      "epoch": 0.023893805309734513,
+      "grad_norm": 59.894893646240234,
+      "learning_rate": 8.13679245283019e-08,
+      "loss": 8.3024,
+      "step": 27
+    },
+    {
+      "epoch": 0.024778761061946902,
+      "grad_norm": 25.504356384277344,
+      "learning_rate": 8.490566037735849e-08,
+      "loss": 5.8745,
+      "step": 28
+    },
+    {
+      "epoch": 0.02566371681415929,
+      "grad_norm": 15.169568061828613,
+      "learning_rate": 8.84433962264151e-08,
+      "loss": 4.7298,
+      "step": 29
+    },
+    {
+      "epoch": 0.02654867256637168,
+      "grad_norm": 24.09995460510254,
+      "learning_rate": 9.19811320754717e-08,
+      "loss": 5.4614,
+      "step": 30
+    },
+    {
+      "epoch": 0.02743362831858407,
+      "grad_norm": 28.669275283813477,
+      "learning_rate": 9.55188679245283e-08,
+      "loss": 5.8594,
+      "step": 31
+    },
+    {
+      "epoch": 0.02831858407079646,
+      "grad_norm": 23.37987518310547,
+      "learning_rate": 9.905660377358491e-08,
+      "loss": 5.2401,
+      "step": 32
+    },
+    {
+      "epoch": 0.02920353982300885,
+      "grad_norm": 22.815292358398438,
+      "learning_rate": 1.0259433962264152e-07,
+      "loss": 5.1579,
+      "step": 33
+    },
+    {
+      "epoch": 0.03008849557522124,
+      "grad_norm": 13.775344848632812,
+      "learning_rate": 1.0613207547169811e-07,
+      "loss": 5.2181,
+      "step": 34
+    },
+    {
+      "epoch": 0.030973451327433628,
+      "grad_norm": 18.642087936401367,
+      "learning_rate": 1.0966981132075472e-07,
+      "loss": 4.6328,
+      "step": 35
+    },
+    {
+      "epoch": 0.03185840707964602,
+      "grad_norm": 18.041406631469727,
+      "learning_rate": 1.1320754716981131e-07,
+      "loss": 2.121,
+      "step": 36
+    },
+    {
+      "epoch": 0.03274336283185841,
+      "grad_norm": 23.423933029174805,
+      "learning_rate": 1.1674528301886792e-07,
+      "loss": 5.9026,
+      "step": 37
+    },
+    {
+      "epoch": 0.033628318584070796,
+      "grad_norm": 46.25591278076172,
+      "learning_rate": 1.2028301886792452e-07,
+      "loss": 7.3796,
+      "step": 38
+    },
+    {
+      "epoch": 0.034513274336283185,
+      "grad_norm": 20.376422882080078,
+      "learning_rate": 1.2382075471698114e-07,
+      "loss": 5.5361,
+      "step": 39
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "grad_norm": 12.82562255859375,
+      "learning_rate": 1.2735849056603773e-07,
+      "loss": 4.0243,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_Qnli-dev_cosine_accuracy": 0.5859375,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.9302856922149658,
+      "eval_Qnli-dev_cosine_ap": 0.5480269179285036,
+      "eval_Qnli-dev_cosine_f1": 0.6315789473684211,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.7634451389312744,
+      "eval_Qnli-dev_cosine_precision": 0.4633663366336634,
+      "eval_Qnli-dev_cosine_recall": 0.9915254237288136,
+      "eval_Qnli-dev_dot_accuracy": 0.5859375,
+      "eval_Qnli-dev_dot_accuracy_threshold": 714.4895629882812,
+      "eval_Qnli-dev_dot_ap": 0.548060663242546,
+      "eval_Qnli-dev_dot_f1": 0.6315789473684211,
+      "eval_Qnli-dev_dot_f1_threshold": 586.342529296875,
+      "eval_Qnli-dev_dot_precision": 0.4633663366336634,
+      "eval_Qnli-dev_dot_recall": 0.9915254237288136,
+      "eval_Qnli-dev_euclidean_accuracy": 0.5859375,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 10.348224639892578,
+      "eval_Qnli-dev_euclidean_ap": 0.5480269179285036,
+      "eval_Qnli-dev_euclidean_f1": 0.6315789473684211,
+      "eval_Qnli-dev_euclidean_f1_threshold": 19.05518341064453,
+      "eval_Qnli-dev_euclidean_precision": 0.4633663366336634,
+      "eval_Qnli-dev_euclidean_recall": 0.9915254237288136,
+      "eval_Qnli-dev_manhattan_accuracy": 0.59765625,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 175.22628784179688,
+      "eval_Qnli-dev_manhattan_ap": 0.5780924813828909,
+      "eval_Qnli-dev_manhattan_f1": 0.6291834002677376,
+      "eval_Qnli-dev_manhattan_f1_threshold": 334.39178466796875,
+      "eval_Qnli-dev_manhattan_precision": 0.4598825831702544,
+      "eval_Qnli-dev_manhattan_recall": 0.9957627118644068,
+      "eval_Qnli-dev_max_accuracy": 0.59765625,
+      "eval_Qnli-dev_max_accuracy_threshold": 714.4895629882812,
+      "eval_Qnli-dev_max_ap": 0.5780924813828909,
+      "eval_Qnli-dev_max_f1": 0.6315789473684211,
+      "eval_Qnli-dev_max_f1_threshold": 586.342529296875,
+      "eval_Qnli-dev_max_precision": 0.4633663366336634,
+      "eval_Qnli-dev_max_recall": 0.9957627118644068,
+      "eval_allNLI-dev_cosine_accuracy": 0.6640625,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.9888672828674316,
+      "eval_allNLI-dev_cosine_ap": 0.32886365768247516,
+      "eval_allNLI-dev_cosine_f1": 0.5095729013254787,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.7477295398712158,
+      "eval_allNLI-dev_cosine_precision": 0.34189723320158105,
+      "eval_allNLI-dev_cosine_recall": 1.0,
+      "eval_allNLI-dev_dot_accuracy": 0.6640625,
+      "eval_allNLI-dev_dot_accuracy_threshold": 759.483154296875,
+      "eval_allNLI-dev_dot_ap": 0.3288581611938815,
+      "eval_allNLI-dev_dot_f1": 0.5095729013254787,
+      "eval_allNLI-dev_dot_f1_threshold": 574.2760620117188,
+      "eval_allNLI-dev_dot_precision": 0.34189723320158105,
+      "eval_allNLI-dev_dot_recall": 1.0,
+      "eval_allNLI-dev_euclidean_accuracy": 0.6640625,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 3.8085508346557617,
+      "eval_allNLI-dev_euclidean_ap": 0.32886365768247516,
+      "eval_allNLI-dev_euclidean_f1": 0.5095729013254787,
+      "eval_allNLI-dev_euclidean_f1_threshold": 19.684810638427734,
+      "eval_allNLI-dev_euclidean_precision": 0.34189723320158105,
+      "eval_allNLI-dev_euclidean_recall": 1.0,
+      "eval_allNLI-dev_manhattan_accuracy": 0.6640625,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 65.93238830566406,
+      "eval_allNLI-dev_manhattan_ap": 0.33852594919898543,
+      "eval_allNLI-dev_manhattan_f1": 0.5058479532163743,
+      "eval_allNLI-dev_manhattan_f1_threshold": 335.4263916015625,
+      "eval_allNLI-dev_manhattan_precision": 0.3385518590998043,
+      "eval_allNLI-dev_manhattan_recall": 1.0,
+      "eval_allNLI-dev_max_accuracy": 0.6640625,
+      "eval_allNLI-dev_max_accuracy_threshold": 759.483154296875,
+      "eval_allNLI-dev_max_ap": 0.33852594919898543,
+      "eval_allNLI-dev_max_f1": 0.5095729013254787,
+      "eval_allNLI-dev_max_f1_threshold": 574.2760620117188,
+      "eval_allNLI-dev_max_precision": 0.34189723320158105,
+      "eval_allNLI-dev_max_recall": 1.0,
+      "eval_sequential_score": 0.5780924813828909,
+      "eval_sts-test_pearson_cosine": 0.1533465318414369,
+      "eval_sts-test_pearson_dot": 0.15333057450060855,
+      "eval_sts-test_pearson_euclidean": 0.1664717893342273,
+      "eval_sts-test_pearson_manhattan": 0.20717970064899288,
+      "eval_sts-test_pearson_max": 0.20717970064899288,
+      "eval_sts-test_spearman_cosine": 0.18786210334203038,
+      "eval_sts-test_spearman_dot": 0.1878347337472397,
+      "eval_sts-test_spearman_euclidean": 0.18786046572196458,
+      "eval_sts-test_spearman_manhattan": 0.22429466463153608,
+      "eval_sts-test_spearman_max": 0.22429466463153608,
+      "eval_vitaminc-pairs_loss": 2.901831865310669,
+      "eval_vitaminc-pairs_runtime": 4.078,
+      "eval_vitaminc-pairs_samples_per_second": 31.388,
+      "eval_vitaminc-pairs_steps_per_second": 0.245,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_negation-triplets_loss": 5.690315246582031,
+      "eval_negation-triplets_runtime": 0.7141,
+      "eval_negation-triplets_samples_per_second": 179.254,
+      "eval_negation-triplets_steps_per_second": 1.4,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_scitail-pairs-pos_loss": 2.1135852336883545,
+      "eval_scitail-pairs-pos_runtime": 0.8282,
+      "eval_scitail-pairs-pos_samples_per_second": 154.543,
+      "eval_scitail-pairs-pos_steps_per_second": 1.207,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_scitail-pairs-qa_loss": 2.8052029609680176,
+      "eval_scitail-pairs-qa_runtime": 0.5471,
+      "eval_scitail-pairs-qa_samples_per_second": 233.943,
+      "eval_scitail-pairs-qa_steps_per_second": 1.828,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_xsum-pairs_loss": 6.583061695098877,
+      "eval_xsum-pairs_runtime": 2.8921,
+      "eval_xsum-pairs_samples_per_second": 44.259,
+      "eval_xsum-pairs_steps_per_second": 0.346,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_sciq_pairs_loss": 0.8882207870483398,
+      "eval_sciq_pairs_runtime": 3.7993,
+      "eval_sciq_pairs_samples_per_second": 33.69,
+      "eval_sciq_pairs_steps_per_second": 0.263,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_qasc_pairs_loss": 4.1147541999816895,
+      "eval_qasc_pairs_runtime": 0.6768,
+      "eval_qasc_pairs_samples_per_second": 189.125,
+      "eval_qasc_pairs_steps_per_second": 1.478,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_openbookqa_pairs_loss": 5.096628665924072,
+      "eval_openbookqa_pairs_runtime": 0.5776,
+      "eval_openbookqa_pairs_samples_per_second": 221.615,
+      "eval_openbookqa_pairs_steps_per_second": 1.731,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_msmarco_pairs_loss": 10.391141891479492,
+      "eval_msmarco_pairs_runtime": 1.2577,
+      "eval_msmarco_pairs_samples_per_second": 101.77,
+      "eval_msmarco_pairs_steps_per_second": 0.795,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_nq_pairs_loss": 10.903197288513184,
+      "eval_nq_pairs_runtime": 2.5051,
+      "eval_nq_pairs_samples_per_second": 51.095,
+      "eval_nq_pairs_steps_per_second": 0.399,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_trivia_pairs_loss": 7.190384387969971,
+      "eval_trivia_pairs_runtime": 3.6482,
+      "eval_trivia_pairs_samples_per_second": 35.085,
+      "eval_trivia_pairs_steps_per_second": 0.274,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_gooaq_pairs_loss": 8.193528175354004,
+      "eval_gooaq_pairs_runtime": 0.9648,
+      "eval_gooaq_pairs_samples_per_second": 132.67,
+      "eval_gooaq_pairs_steps_per_second": 1.036,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_paws-pos_loss": 1.3942564725875854,
+      "eval_paws-pos_runtime": 0.6718,
+      "eval_paws-pos_samples_per_second": 190.538,
+      "eval_paws-pos_steps_per_second": 1.489,
+      "step": 40
+    },
+    {
+      "epoch": 0.035398230088495575,
+      "eval_global_dataset_loss": 5.671571731567383,
+      "eval_global_dataset_runtime": 23.0452,
+      "eval_global_dataset_samples_per_second": 28.77,
+      "eval_global_dataset_steps_per_second": 0.26,
+      "step": 40
+    },
+    {
+      "epoch": 0.036283185840707964,
+      "grad_norm": 18.026830673217773,
+      "learning_rate": 1.3089622641509433e-07,
+      "loss": 4.9072,
+      "step": 41
+    },
+    {
+      "epoch": 0.03716814159292035,
+      "grad_norm": 15.423810958862305,
+      "learning_rate": 1.3443396226415095e-07,
+      "loss": 3.4439,
+      "step": 42
+    },
+    {
+      "epoch": 0.03805309734513274,
+      "grad_norm": 16.31403160095215,
+      "learning_rate": 1.3797169811320754e-07,
+      "loss": 4.9787,
+      "step": 43
+    },
+    {
+      "epoch": 0.03893805309734513,
+      "grad_norm": 21.37955093383789,
+      "learning_rate": 1.4150943396226417e-07,
+      "loss": 5.8318,
+      "step": 44
+    },
+    {
+      "epoch": 0.03982300884955752,
+      "grad_norm": 18.23583984375,
+      "learning_rate": 1.4504716981132076e-07,
+      "loss": 5.3226,
+      "step": 45
+    },
+    {
+      "epoch": 0.04070796460176991,
+      "grad_norm": 20.878713607788086,
+      "learning_rate": 1.4858490566037738e-07,
+      "loss": 5.1181,
+      "step": 46
+    },
+    {
+      "epoch": 0.0415929203539823,
+      "grad_norm": 18.71149444580078,
+      "learning_rate": 1.5212264150943398e-07,
+      "loss": 4.7834,
+      "step": 47
+    },
+    {
+      "epoch": 0.04247787610619469,
+      "grad_norm": 38.85902786254883,
+      "learning_rate": 1.5566037735849057e-07,
+      "loss": 6.6303,
+      "step": 48
+    },
+    {
+      "epoch": 0.04336283185840708,
+      "grad_norm": 37.41562271118164,
+      "learning_rate": 1.591981132075472e-07,
+      "loss": 5.8171,
+      "step": 49
+    },
+    {
+      "epoch": 0.04424778761061947,
+      "grad_norm": 17.541080474853516,
+      "learning_rate": 1.627358490566038e-07,
+      "loss": 5.1962,
+      "step": 50
+    },
+    {
+      "epoch": 0.04513274336283186,
+      "grad_norm": 16.145116806030273,
+      "learning_rate": 1.6627358490566038e-07,
+      "loss": 5.2096,
+      "step": 51
+    },
+    {
+      "epoch": 0.04601769911504425,
+      "grad_norm": 20.175189971923828,
+      "learning_rate": 1.6981132075471698e-07,
+      "loss": 5.0943,
+      "step": 52
+    },
+    {
+      "epoch": 0.046902654867256637,
+      "grad_norm": 13.441214561462402,
+      "learning_rate": 1.733490566037736e-07,
+      "loss": 4.9038,
+      "step": 53
+    },
+    {
+      "epoch": 0.047787610619469026,
+      "grad_norm": 13.396607398986816,
+      "learning_rate": 1.768867924528302e-07,
+      "loss": 4.6479,
+      "step": 54
+    },
+    {
+      "epoch": 0.048672566371681415,
+      "grad_norm": 13.68046760559082,
+      "learning_rate": 1.804245283018868e-07,
+      "loss": 5.5098,
+      "step": 55
+    },
+    {
+      "epoch": 0.049557522123893805,
+      "grad_norm": 13.278443336486816,
+      "learning_rate": 1.839622641509434e-07,
+      "loss": 4.6979,
+      "step": 56
+    },
+    {
+      "epoch": 0.050442477876106194,
+      "grad_norm": 15.295453071594238,
+      "learning_rate": 1.875e-07,
+      "loss": 3.1969,
+      "step": 57
+    },
+    {
+      "epoch": 0.05132743362831858,
+      "grad_norm": 12.185781478881836,
+      "learning_rate": 1.910377358490566e-07,
+      "loss": 4.4127,
+      "step": 58
+    },
+    {
+      "epoch": 0.05221238938053097,
+      "grad_norm": 10.874494552612305,
+      "learning_rate": 1.9457547169811322e-07,
+      "loss": 3.7746,
+      "step": 59
+    },
+    {
+      "epoch": 0.05309734513274336,
+      "grad_norm": 9.654823303222656,
+      "learning_rate": 1.9811320754716982e-07,
+      "loss": 4.5378,
+      "step": 60
+    },
+    {
+      "epoch": 0.05398230088495575,
+      "grad_norm": 21.123645782470703,
+      "learning_rate": 2.016509433962264e-07,
+      "loss": 5.0209,
+      "step": 61
+    },
+    {
+      "epoch": 0.05486725663716814,
+      "grad_norm": 33.47934341430664,
+      "learning_rate": 2.0518867924528303e-07,
+      "loss": 6.5936,
+      "step": 62
+    },
+    {
+      "epoch": 0.05575221238938053,
+      "grad_norm": 10.2566556930542,
+      "learning_rate": 2.0872641509433963e-07,
+      "loss": 4.2315,
+      "step": 63
+    },
+    {
+      "epoch": 0.05663716814159292,
+      "grad_norm": 28.198625564575195,
+      "learning_rate": 2.1226415094339622e-07,
+      "loss": 6.4269,
+      "step": 64
+    },
+    {
+      "epoch": 0.05752212389380531,
+      "grad_norm": 9.386558532714844,
+      "learning_rate": 2.1580188679245282e-07,
+      "loss": 4.2644,
+      "step": 65
+    },
+    {
+      "epoch": 0.0584070796460177,
+      "grad_norm": 12.687555313110352,
+      "learning_rate": 2.1933962264150944e-07,
+      "loss": 5.1388,
+      "step": 66
+    },
+    {
+      "epoch": 0.05929203539823009,
+      "grad_norm": 14.834878921508789,
+      "learning_rate": 2.2287735849056603e-07,
+      "loss": 5.1852,
+      "step": 67
+    },
+    {
+      "epoch": 0.06017699115044248,
+      "grad_norm": 10.888677597045898,
+      "learning_rate": 2.2641509433962263e-07,
+      "loss": 4.8057,
+      "step": 68
+    },
+    {
+      "epoch": 0.061061946902654866,
+      "grad_norm": 13.97256851196289,
+      "learning_rate": 2.2995283018867925e-07,
+      "loss": 3.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.061946902654867256,
+      "grad_norm": 11.82534122467041,
+      "learning_rate": 2.3349056603773584e-07,
+      "loss": 3.3322,
+      "step": 70
+    },
+    {
+      "epoch": 0.06283185840707965,
+      "grad_norm": 16.99266242980957,
+      "learning_rate": 2.3702830188679244e-07,
+      "loss": 5.139,
+      "step": 71
+    },
+    {
+      "epoch": 0.06371681415929203,
+      "grad_norm": 8.74513053894043,
+      "learning_rate": 2.4056603773584903e-07,
+      "loss": 4.307,
+      "step": 72
+    },
+    {
+      "epoch": 0.06460176991150443,
+      "grad_norm": 11.715869903564453,
+      "learning_rate": 2.4410377358490563e-07,
+      "loss": 5.0133,
+      "step": 73
+    },
+    {
+      "epoch": 0.06548672566371681,
+      "grad_norm": 9.844196319580078,
+      "learning_rate": 2.476415094339623e-07,
+      "loss": 4.0507,
+      "step": 74
+    },
+    {
+      "epoch": 0.06637168141592921,
+      "grad_norm": 12.447444915771484,
+      "learning_rate": 2.5117924528301887e-07,
+      "loss": 3.3895,
+      "step": 75
+    },
+    {
+      "epoch": 0.06725663716814159,
+      "grad_norm": 23.91596794128418,
+      "learning_rate": 2.5471698113207547e-07,
+      "loss": 5.6736,
+      "step": 76
+    },
+    {
+      "epoch": 0.06814159292035399,
+      "grad_norm": 9.635603904724121,
+      "learning_rate": 2.5825471698113206e-07,
+      "loss": 4.2572,
+      "step": 77
+    },
+    {
+      "epoch": 0.06902654867256637,
+      "grad_norm": 14.971665382385254,
+      "learning_rate": 2.6179245283018866e-07,
+      "loss": 3.0796,
+      "step": 78
+    },
+    {
+      "epoch": 0.06991150442477877,
+      "grad_norm": 11.226128578186035,
+      "learning_rate": 2.6533018867924525e-07,
+      "loss": 5.0199,
+      "step": 79
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "grad_norm": 11.01388931274414,
+      "learning_rate": 2.688679245283019e-07,
+      "loss": 4.1414,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_Qnli-dev_cosine_accuracy": 0.591796875,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.9258557558059692,
+      "eval_Qnli-dev_cosine_ap": 0.5585355274462735,
+      "eval_Qnli-dev_cosine_f1": 0.6291834002677376,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.750666618347168,
+      "eval_Qnli-dev_cosine_precision": 0.4598825831702544,
+      "eval_Qnli-dev_cosine_recall": 0.9957627118644068,
+      "eval_Qnli-dev_dot_accuracy": 0.591796875,
+      "eval_Qnli-dev_dot_accuracy_threshold": 711.18359375,
+      "eval_Qnli-dev_dot_ap": 0.5585297234749824,
+      "eval_Qnli-dev_dot_f1": 0.6291834002677376,
+      "eval_Qnli-dev_dot_f1_threshold": 576.5970458984375,
+      "eval_Qnli-dev_dot_precision": 0.4598825831702544,
+      "eval_Qnli-dev_dot_recall": 0.9957627118644068,
+      "eval_Qnli-dev_euclidean_accuracy": 0.591796875,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 10.672666549682617,
+      "eval_Qnli-dev_euclidean_ap": 0.5585355274462735,
+      "eval_Qnli-dev_euclidean_f1": 0.6291834002677376,
+      "eval_Qnli-dev_euclidean_f1_threshold": 19.553747177124023,
+      "eval_Qnli-dev_euclidean_precision": 0.4598825831702544,
+      "eval_Qnli-dev_euclidean_recall": 0.9957627118644068,
+      "eval_Qnli-dev_manhattan_accuracy": 0.619140625,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 188.09068298339844,
+      "eval_Qnli-dev_manhattan_ap": 0.5898283705050701,
+      "eval_Qnli-dev_manhattan_f1": 0.6301775147928994,
+      "eval_Qnli-dev_manhattan_f1_threshold": 237.80462646484375,
+      "eval_Qnli-dev_manhattan_precision": 0.48409090909090907,
+      "eval_Qnli-dev_manhattan_recall": 0.902542372881356,
+      "eval_Qnli-dev_max_accuracy": 0.619140625,
+      "eval_Qnli-dev_max_accuracy_threshold": 711.18359375,
+      "eval_Qnli-dev_max_ap": 0.5898283705050701,
+      "eval_Qnli-dev_max_f1": 0.6301775147928994,
+      "eval_Qnli-dev_max_f1_threshold": 576.5970458984375,
+      "eval_Qnli-dev_max_precision": 0.48409090909090907,
+      "eval_Qnli-dev_max_recall": 0.9957627118644068,
+      "eval_allNLI-dev_cosine_accuracy": 0.666015625,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.983686089515686,
+      "eval_allNLI-dev_cosine_ap": 0.34411819659341086,
+      "eval_allNLI-dev_cosine_f1": 0.5065885797950219,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.7642872333526611,
+      "eval_allNLI-dev_cosine_precision": 0.3392156862745098,
+      "eval_allNLI-dev_cosine_recall": 1.0,
+      "eval_allNLI-dev_dot_accuracy": 0.666015625,
+      "eval_allNLI-dev_dot_accuracy_threshold": 755.60302734375,
+      "eval_allNLI-dev_dot_ap": 0.344109544232086,
+      "eval_allNLI-dev_dot_f1": 0.5065885797950219,
+      "eval_allNLI-dev_dot_f1_threshold": 587.0625,
+      "eval_allNLI-dev_dot_precision": 0.3392156862745098,
+      "eval_allNLI-dev_dot_recall": 1.0,
+      "eval_allNLI-dev_euclidean_accuracy": 0.666015625,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 5.00581693649292,
+      "eval_allNLI-dev_euclidean_ap": 0.3441246898925644,
+      "eval_allNLI-dev_euclidean_f1": 0.5065885797950219,
+      "eval_allNLI-dev_euclidean_f1_threshold": 19.022436141967773,
+      "eval_allNLI-dev_euclidean_precision": 0.3392156862745098,
+      "eval_allNLI-dev_euclidean_recall": 1.0,
+      "eval_allNLI-dev_manhattan_accuracy": 0.6640625,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 62.69102096557617,
+      "eval_allNLI-dev_manhattan_ap": 0.35131239981425566,
+      "eval_allNLI-dev_manhattan_f1": 0.5058479532163743,
+      "eval_allNLI-dev_manhattan_f1_threshold": 337.6861877441406,
+      "eval_allNLI-dev_manhattan_precision": 0.3385518590998043,
+      "eval_allNLI-dev_manhattan_recall": 1.0,
+      "eval_allNLI-dev_max_accuracy": 0.666015625,
+      "eval_allNLI-dev_max_accuracy_threshold": 755.60302734375,
+      "eval_allNLI-dev_max_ap": 0.35131239981425566,
+      "eval_allNLI-dev_max_f1": 0.5065885797950219,
+      "eval_allNLI-dev_max_f1_threshold": 587.0625,
+      "eval_allNLI-dev_max_precision": 0.3392156862745098,
+      "eval_allNLI-dev_max_recall": 1.0,
+      "eval_sequential_score": 0.5898283705050701,
+      "eval_sts-test_pearson_cosine": 0.22248205020578934,
+      "eval_sts-test_pearson_dot": 0.22239084967931927,
+      "eval_sts-test_pearson_euclidean": 0.2323160413842197,
+      "eval_sts-test_pearson_manhattan": 0.26632593273308647,
+      "eval_sts-test_pearson_max": 0.26632593273308647,
+      "eval_sts-test_spearman_cosine": 0.24802235964390085,
+      "eval_sts-test_spearman_dot": 0.24791612015173234,
+      "eval_sts-test_spearman_euclidean": 0.24799036249272113,
+      "eval_sts-test_spearman_manhattan": 0.2843623073856928,
+      "eval_sts-test_spearman_max": 0.2843623073856928,
+      "eval_vitaminc-pairs_loss": 2.7793872356414795,
+      "eval_vitaminc-pairs_runtime": 3.7649,
+      "eval_vitaminc-pairs_samples_per_second": 33.998,
+      "eval_vitaminc-pairs_steps_per_second": 0.266,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_negation-triplets_loss": 4.888970851898193,
+      "eval_negation-triplets_runtime": 0.7134,
+      "eval_negation-triplets_samples_per_second": 179.432,
+      "eval_negation-triplets_steps_per_second": 1.402,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_scitail-pairs-pos_loss": 1.8996644020080566,
+      "eval_scitail-pairs-pos_runtime": 0.8506,
+      "eval_scitail-pairs-pos_samples_per_second": 150.477,
+      "eval_scitail-pairs-pos_steps_per_second": 1.176,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_scitail-pairs-qa_loss": 2.6760551929473877,
+      "eval_scitail-pairs-qa_runtime": 0.5685,
+      "eval_scitail-pairs-qa_samples_per_second": 225.171,
+      "eval_scitail-pairs-qa_steps_per_second": 1.759,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_xsum-pairs_loss": 6.209648609161377,
+      "eval_xsum-pairs_runtime": 2.9221,
+      "eval_xsum-pairs_samples_per_second": 43.804,
+      "eval_xsum-pairs_steps_per_second": 0.342,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_sciq_pairs_loss": 0.7622462511062622,
+      "eval_sciq_pairs_runtime": 3.7816,
+      "eval_sciq_pairs_samples_per_second": 33.848,
+      "eval_sciq_pairs_steps_per_second": 0.264,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_qasc_pairs_loss": 3.3129472732543945,
+      "eval_qasc_pairs_runtime": 0.6761,
+      "eval_qasc_pairs_samples_per_second": 189.334,
+      "eval_qasc_pairs_steps_per_second": 1.479,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_openbookqa_pairs_loss": 4.549765586853027,
+      "eval_openbookqa_pairs_runtime": 0.5767,
+      "eval_openbookqa_pairs_samples_per_second": 221.954,
+      "eval_openbookqa_pairs_steps_per_second": 1.734,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_msmarco_pairs_loss": 7.205582141876221,
+      "eval_msmarco_pairs_runtime": 1.2621,
+      "eval_msmarco_pairs_samples_per_second": 101.416,
+      "eval_msmarco_pairs_steps_per_second": 0.792,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_nq_pairs_loss": 7.680945873260498,
+      "eval_nq_pairs_runtime": 2.5052,
+      "eval_nq_pairs_samples_per_second": 51.095,
+      "eval_nq_pairs_steps_per_second": 0.399,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_trivia_pairs_loss": 6.37924861907959,
+      "eval_trivia_pairs_runtime": 3.6293,
+      "eval_trivia_pairs_samples_per_second": 35.268,
+      "eval_trivia_pairs_steps_per_second": 0.276,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_gooaq_pairs_loss": 6.656675338745117,
+      "eval_gooaq_pairs_runtime": 0.9698,
+      "eval_gooaq_pairs_samples_per_second": 131.988,
+      "eval_gooaq_pairs_steps_per_second": 1.031,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_paws-pos_loss": 1.3848179578781128,
+      "eval_paws-pos_runtime": 0.6727,
+      "eval_paws-pos_samples_per_second": 190.278,
+      "eval_paws-pos_steps_per_second": 1.487,
+      "step": 80
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "eval_global_dataset_loss": 5.002967834472656,
+      "eval_global_dataset_runtime": 23.048,
+      "eval_global_dataset_samples_per_second": 28.766,
+      "eval_global_dataset_steps_per_second": 0.26,
+      "step": 80
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 3390,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 80,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 42,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-80/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bfb21b1a8b0022475cba81f0306eaa079a06c682d78c599327457cfd397d216
+size 5688