Training in progress, step 55, checkpoint

checkpoint-55/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

checkpoint-55/README.md

@@ -0,0 +1,906 @@
+---
+base_model: microsoft/deberta-v3-small
+datasets: []
+language: []
+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:116445
+- loss:CachedGISTEmbedLoss
+widget:
+- source_sentence: what is the main purpose of the brain
+  sentences:
+  - Brain Physiologically, the function of the brain is to exert centralized control
+    over the other organs of the body. The brain acts on the rest of the body both
+    by generating patterns of muscle activity and by driving the secretion of chemicals
+    called hormones. This centralized control allows rapid and coordinated responses
+    to changes in the environment. Some basic types of responsiveness such as reflexes
+    can be mediated by the spinal cord or peripheral ganglia, but sophisticated purposeful
+    control of behavior based on complex sensory input requires the information integrating
+    capabilities of a centralized brain.
+  - How do scientists know that some mountains were once at the bottom of an ocean?
+  - The Smiths Wiki | Fandom powered by Wikia Share Ad blocker interference detected!
+    Wikia is a free-to-use site that makes money from advertising. We have a modified
+    experience for viewers using ad blockers Wikia is not accessible if you’ve made
+    further modifications. Remove the custom ad blocker rule(s) and the page will
+    load as expected. The Smiths were an English rock band formed in Manchester in
+    1982. Based on the songwriting partnership of Morrissey (vocals) and Johnny Marr
+    (guitar), the band also included Andy Rourke (bass), Mike Joyce (drums) and for
+    a brief time Craig Gannon (rhythm guitar). Critics have called them one of the
+    most important alternative rock bands to emerge from the British independent music
+    scene of the 1980s,and the group has had major influence on subsequent artists.
+    Morrissey's lovelorn tales of alienation found an audience amongst youth culture
+    bored by the ubiquitous synthesiser-pop bands of the early 1980s, while Marr's
+    complex melodies helped return guitar-based music to popularity. The group were
+    signed to the independent record label Rough Trade Records , for whom they released
+    four studio albums and several compilations, as well as numerous non-LP singles.
+    Although they had limited commercial success outside the UK while they were still
+    together, and never released a single that charted higher than number 10 in their
+    home country, The Smiths won a growing following, and they remain cult and commercial
+    favourites. The band broke up in 1987 amid disagreements between Morrissey and
+    Marr and has turned down several offers to reform. Welcome to The Smiths Wiki
+- source_sentence: There were 29 Muslims fatalities in the Cave of the Patriarchs
+    massacre .
+  sentences:
+  - In August , after the end of the war in June 1902 , Higgins Southampton left the
+    `` SSBavarian '' and returned to Cape Town the following month .
+  - Between 29 and 52 Muslims were killed and more than 100 others wounded . [   Settlers
+    remember gunman Goldstein ; Hebron riots continue ] .
+  - 29 Muslims were killed and more than 100 others wounded . [   Settlers remember
+    gunman Goldstein ; Hebron riots continue ] .
+- source_sentence: are tabby cats all male?
+  sentences:
+  - Did you know orange tabby cats are typically male? In fact, up to 80 percent of
+    orange tabbies are male, making orange female cats a bit of a rarity. According
+    to the BBC's Focus Magazine, the ginger gene in cats works a little differently
+    compared to humans; it is on the X chromosome.
+  - Shawnee Trails Council was formed from the merger of the Four Rivers Council and
+    the Audubon Council .
+  - 'A picture of a modern looking kitchen area
+
+    '
+- source_sentence: Aamir Khan agreed to act immediately after reading Mehra 's screenplay
+    in `` Rang De Basanti '' .
+  sentences:
+  - Chris Rea —   Free listening, videos, concerts, stats and photos at Last.fm singer-songwriter
+    Christopher Anton Rea (pronounced Ree-ah), born 4 March 1951, is a singer, songwriter,
+    and guitarist from Middlesbrough, England. Rea's recording career began in 1978.
+    Although he almost immediately had a US hit single with "Fool (If You Think It's
+    Over)", Rea's initial focus was on continental Europe, releasing eight albums
+    in the 1980s. It wasn't until 1985's Shamrock Diaries and the songs "Stainsby
+    Girls" and "Josephine," that UK audiences began to take notice of him. Follow
+    up albums… read more
+  - "Healthy Fast Food Meal No. 1. Grilled Chicken Sandwich and Fruit Cup (Chick-fil-A)\
+    \ Several fast food chains offer a grilled chicken sandwich. The trick is ordering\
+    \ it without mayo or creamy sauce, and making sure itâ\x80\x99s served with a\
+    \ whole grain bun."
+  - Aamir Khan agreed to act in `` Rang De Basanti '' immediately after reading Mehra
+    's script .
+- source_sentence: 'A man wearing a blue bow tie and a fedora hat in a car. '
+  sentences:
+  - A man takes a photo of himself wearing a bowtie and hat
+  - Scientists explain the world based on what?
+  - 'County of Angus - definition of County of Angus by The Free Dictionary County
+    of Angus - definition of County of Angus by The Free Dictionary http://www.thefreedictionary.com/County+of+Angus
+     (ăng′gəs) n. Any of a breed of hornless beef cattle that originated in Scotland
+    and are usually black but also occur in a red variety. Also called Black Angus.
+    [After Angus, former county of Scotland.] Angus (ˈæŋɡəs) n (Placename) a council
+    area of E Scotland on the North Sea: the historical county of Angus became part
+    of Tayside region in 1975; reinstated as a unitary authority (excluding City of
+    Dundee) in 1996. Administrative centre: Forfar. Pop: 107 520 (2003 est). Area:
+    2181 sq km (842 sq miles) An•gus'
+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: 0.2589065791031549
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.31323211323674593
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.27236487282828553
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.29656486394161036
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.2585939429800171
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.2833925986586202
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.28511212645281553
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.2967423026930272
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.28511212645281553
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.31323211323674593
+      name: Spearman Max
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: allNLI dev
+      type: allNLI-dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.66796875
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.9721465110778809
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.5343511450381679
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.85741126537323
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.39886039886039887
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8092485549132948
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.4140638596370657
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.666015625
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 518.88671875
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.514018691588785
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 323.9651184082031
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.35181236673773986
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.953757225433526
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.3781233337023534
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.671875
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 114.41839599609375
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.5384615384615384
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 226.82566833496094
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.3941018766756032
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.8497109826589595
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.4272864144491257
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.671875
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 5.084325790405273
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.5404339250493098
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 11.333902359008789
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.4101796407185629
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.791907514450867
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.41769294415599645
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.671875
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 518.88671875
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.5404339250493098
+      name: Max F1
+    - type: max_f1_threshold
+      value: 323.9651184082031
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.4101796407185629
+      name: Max Precision
+    - type: max_recall
+      value: 0.953757225433526
+      name: Max Recall
+    - type: max_ap
+      value: 0.4272864144491257
+      name: Max Ap
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: Qnli dev
+      type: Qnli-dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.640625
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.8695281744003296
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.6578512396694215
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7936367988586426
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.5392953929539296
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8432203389830508
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.6314640856589909
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.609375
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 351.17626953125
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.6501650165016502
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 316.48046875
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.5324324324324324
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.8347457627118644
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.5366456296706419
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.658203125
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 206.32894897460938
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.652373660030628
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 261.3590393066406
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.5107913669064749
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.902542372881356
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.6679289689394285
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.65234375
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 10.764808654785156
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.6393210749646393
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 15.096710205078125
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.47983014861995754
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9576271186440678
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.6460602994393339
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.658203125
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 351.17626953125
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.6578512396694215
+      name: Max F1
+    - type: max_f1_threshold
+      value: 316.48046875
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.5392953929539296
+      name: Max Precision
+    - type: max_recall
+      value: 0.9576271186440678
+      name: Max Recall
+    - type: max_ap
+      value: 0.6679289689394285
+      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) on the bobox/enhanced_nli-50_k dataset. 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:**
+    - bobox/enhanced_nli-50_k
+<!-- - **Language:** Unknown -->
+<!-- - **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): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': 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/DeBERTa-small-ST-UnifiedDatasets-baseline-checkpoints-tmp")
+# Run inference
+sentences = [
+    'A man wearing a blue bow tie and a fedora hat in a car. ',
+    'A man takes a photo of himself wearing a bowtie and hat',
+    'County of Angus - definition of County of Angus by The Free Dictionary County of Angus - definition of County of Angus by The Free Dictionary http://www.thefreedictionary.com/County+of+Angus \xa0(ăng′gəs) n. Any of a breed of hornless beef cattle that originated in Scotland and are usually black but also occur in a red variety. Also called Black Angus. [After Angus, former county of Scotland.] Angus (ˈæŋɡəs) n (Placename) a council area of E Scotland on the North Sea: the historical county of Angus became part of Tayside region in 1975; reinstated as a unitary authority (excluding City of Dundee) in 1996. Administrative centre: Forfar. Pop: 107 520 (2003 est). Area: 2181 sq km (842 sq miles) An•gus',
+]
+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      | 0.2589     |
+| **spearman_cosine** | **0.3132** |
+| pearson_manhattan   | 0.2724     |
+| spearman_manhattan  | 0.2966     |
+| pearson_euclidean   | 0.2586     |
+| spearman_euclidean  | 0.2834     |
+| pearson_dot         | 0.2851     |
+| spearman_dot        | 0.2967     |
+| pearson_max         | 0.2851     |
+| spearman_max        | 0.3132     |
+
+#### 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              | 0.668      |
+| cosine_accuracy_threshold    | 0.9721     |
+| cosine_f1                    | 0.5344     |
+| cosine_f1_threshold          | 0.8574     |
+| cosine_precision             | 0.3989     |
+| cosine_recall                | 0.8092     |
+| cosine_ap                    | 0.4141     |
+| dot_accuracy                 | 0.666      |
+| dot_accuracy_threshold       | 518.8867   |
+| dot_f1                       | 0.514      |
+| dot_f1_threshold             | 323.9651   |
+| dot_precision                | 0.3518     |
+| dot_recall                   | 0.9538     |
+| dot_ap                       | 0.3781     |
+| manhattan_accuracy           | 0.6719     |
+| manhattan_accuracy_threshold | 114.4184   |
+| manhattan_f1                 | 0.5385     |
+| manhattan_f1_threshold       | 226.8257   |
+| manhattan_precision          | 0.3941     |
+| manhattan_recall             | 0.8497     |
+| manhattan_ap                 | 0.4273     |
+| euclidean_accuracy           | 0.6719     |
+| euclidean_accuracy_threshold | 5.0843     |
+| euclidean_f1                 | 0.5404     |
+| euclidean_f1_threshold       | 11.3339    |
+| euclidean_precision          | 0.4102     |
+| euclidean_recall             | 0.7919     |
+| euclidean_ap                 | 0.4177     |
+| max_accuracy                 | 0.6719     |
+| max_accuracy_threshold       | 518.8867   |
+| max_f1                       | 0.5404     |
+| max_f1_threshold             | 323.9651   |
+| max_precision                | 0.4102     |
+| max_recall                   | 0.9538     |
+| **max_ap**                   | **0.4273** |
+
+#### 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              | 0.6406     |
+| cosine_accuracy_threshold    | 0.8695     |
+| cosine_f1                    | 0.6579     |
+| cosine_f1_threshold          | 0.7936     |
+| cosine_precision             | 0.5393     |
+| cosine_recall                | 0.8432     |
+| cosine_ap                    | 0.6315     |
+| dot_accuracy                 | 0.6094     |
+| dot_accuracy_threshold       | 351.1763   |
+| dot_f1                       | 0.6502     |
+| dot_f1_threshold             | 316.4805   |
+| dot_precision                | 0.5324     |
+| dot_recall                   | 0.8347     |
+| dot_ap                       | 0.5366     |
+| manhattan_accuracy           | 0.6582     |
+| manhattan_accuracy_threshold | 206.3289   |
+| manhattan_f1                 | 0.6524     |
+| manhattan_f1_threshold       | 261.359    |
+| manhattan_precision          | 0.5108     |
+| manhattan_recall             | 0.9025     |
+| manhattan_ap                 | 0.6679     |
+| euclidean_accuracy           | 0.6523     |
+| euclidean_accuracy_threshold | 10.7648    |
+| euclidean_f1                 | 0.6393     |
+| euclidean_f1_threshold       | 15.0967    |
+| euclidean_precision          | 0.4798     |
+| euclidean_recall             | 0.9576     |
+| euclidean_ap                 | 0.6461     |
+| max_accuracy                 | 0.6582     |
+| max_accuracy_threshold       | 351.1763   |
+| max_f1                       | 0.6579     |
+| max_f1_threshold             | 316.4805   |
+| max_precision                | 0.5393     |
+| max_recall                   | 0.9576     |
+| **max_ap**                   | **0.6679** |
+
+<!--
+## 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
+
+### Training Dataset
+
+#### bobox/enhanced_nli-50_k
+
+* Dataset: bobox/enhanced_nli-50_k
+* Size: 116,445 training samples
+* Columns: <code>sentence1</code> and <code>sentence2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                          | sentence2                                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 33.67 tokens</li><li>max: 338 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 51.48 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | sentence1                                                            | sentence2                                                                                                                                                                                                                                  |
+  |:---------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>who is darnell from my name is earl</code>                     | <code>Eddie Steeples Eddie Steeples (born November 25, 1973)[1] is an American actor known for his roles as the "Rubberband Man" in an advertising campaign for OfficeMax, and as Darnell Turner on the NBC sitcom My Name Is Earl.</code> |
+  | <code>Ferrell and the Chili Peppers toured together in 2013 .</code> | <code>Ferrell and the Chili Peppers wrapped up I 'm With You World Tour in April 2013 .</code>                                                                                                                                             |
+  | <code>Cells have four cycles.</code>                                 | <code>How many cycles do cells have?</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}
+  ```
+
+### Evaluation Dataset
+
+#### bobox/enhanced_nli-50_k
+
+* Dataset: bobox/enhanced_nli-50_k
+* Size: 1,506 evaluation samples
+* Columns: <code>sentence1</code> and <code>sentence2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                          | sentence2                                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 32.36 tokens</li><li>max: 341 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 61.99 tokens</li><li>max: 431 tokens</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                     | sentence2                                                                                                                                                                                 |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Interestingly, snakes use their forked tongues to smell.</code>                                                                         | <code>Snakes use their tongue to smell things.</code>                                                                                                                                     |
+  | <code>Soil is a renewable resource that can take thousand of years to form.</code>                                                            | <code>What is a renewable resource that can take thousand of years to form?</code>                                                                                                        |
+  | <code>As of March 22 , there were more than 321,000 cases with over 13,600 deaths and more than 96,000 recoveries reported worldwide .</code> | <code>As of 22 March , more than 321,000 cases of COVID-19 have been reported in over 180 countries and territories , resulting in more than 13,600 deaths and 96,000 recoveries .</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`: 640
+- `per_device_eval_batch_size`: 128
+- `learning_rate`: 3.75e-05
+- `weight_decay`: 0.0005
+- `lr_scheduler_type`: cosine_with_min_lr
+- `lr_scheduler_kwargs`: {'num_cycles': 0.5, 'min_lr': 7.499999999999999e-06}
+- `warmup_ratio`: 0.33
+- `save_safetensors`: False
+- `fp16`: True
+- `push_to_hub`: True
+- `hub_model_id`: bobox/DeBERTa-small-ST-UnifiedDatasets-baseline-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`: 640
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 3.75e-05
+- `weight_decay`: 0.0005
+- `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': 7.499999999999999e-06}
+- `warmup_ratio`: 0.33
+- `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/DeBERTa-small-ST-UnifiedDatasets-baseline-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
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | Qnli-dev_max_ap | allNLI-dev_max_ap | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:------:|:---------------:|:-----------------:|:------------------------:|
+| 0.0055 | 1    | 8.8159        | -      | -               | -                 | -                        |
+| 0.0110 | 2    | 9.1259        | -      | -               | -                 | -                        |
+| 0.0165 | 3    | 8.9017        | -      | -               | -                 | -                        |
+| 0.0220 | 4    | 9.1969        | -      | -               | -                 | -                        |
+| 0.0275 | 5    | 9.3716        | 1.3746 | 0.6067          | 0.3706            | 0.1943                   |
+| 0.0330 | 6    | 9.0425        | -      | -               | -                 | -                        |
+| 0.0385 | 7    | 8.7309        | -      | -               | -                 | -                        |
+| 0.0440 | 8    | 9.0123        | -      | -               | -                 | -                        |
+| 0.0495 | 9    | 8.8095        | -      | -               | -                 | -                        |
+| 0.0549 | 10   | 9.3194        | 1.3227 | 0.6089          | 0.3721            | 0.1976                   |
+| 0.0604 | 11   | 8.9873        | -      | -               | -                 | -                        |
+| 0.0659 | 12   | 8.5575        | -      | -               | -                 | -                        |
+| 0.0714 | 13   | 8.8096        | -      | -               | -                 | -                        |
+| 0.0769 | 14   | 8.0996        | -      | -               | -                 | -                        |
+| 0.0824 | 15   | 8.1942        | 1.2244 | 0.6140          | 0.3743            | 0.2085                   |
+| 0.0879 | 16   | 8.1654        | -      | -               | -                 | -                        |
+| 0.0934 | 17   | 7.7336        | -      | -               | -                 | -                        |
+| 0.0989 | 18   | 7.9535        | -      | -               | -                 | -                        |
+| 0.1044 | 19   | 7.9322        | -      | -               | -                 | -                        |
+| 0.1099 | 20   | 7.6812        | 1.1301 | 0.6199          | 0.3790            | 0.2233                   |
+| 0.1154 | 21   | 7.551         | -      | -               | -                 | -                        |
+| 0.1209 | 22   | 7.3788        | -      | -               | -                 | -                        |
+| 0.1264 | 23   | 7.1746        | -      | -               | -                 | -                        |
+| 0.1319 | 24   | 7.1849        | -      | -               | -                 | -                        |
+| 0.1374 | 25   | 7.1085        | 1.0723 | 0.6195          | 0.3852            | 0.2357                   |
+| 0.1429 | 26   | 7.3926        | -      | -               | -                 | -                        |
+| 0.1484 | 27   | 7.1817        | -      | -               | -                 | -                        |
+| 0.1538 | 28   | 7.239         | -      | -               | -                 | -                        |
+| 0.1593 | 29   | 7.0023        | -      | -               | -                 | -                        |
+| 0.1648 | 30   | 6.9898        | 1.0282 | 0.6215          | 0.3898            | 0.2477                   |
+| 0.1703 | 31   | 6.9776        | -      | -               | -                 | -                        |
+| 0.1758 | 32   | 6.8088        | -      | -               | -                 | -                        |
+| 0.1813 | 33   | 6.8916        | -      | -               | -                 | -                        |
+| 0.1868 | 34   | 6.6931        | -      | -               | -                 | -                        |
+| 0.1923 | 35   | 6.5707        | 0.9846 | 0.6253          | 0.3952            | 0.2608                   |
+| 0.1978 | 36   | 6.6231        | -      | -               | -                 | -                        |
+| 0.2033 | 37   | 6.4951        | -      | -               | -                 | -                        |
+| 0.2088 | 38   | 6.4607        | -      | -               | -                 | -                        |
+| 0.2143 | 39   | 6.4504        | -      | -               | -                 | -                        |
+| 0.2198 | 40   | 6.3649        | 0.9314 | 0.6299          | 0.4041            | 0.2738                   |
+| 0.2253 | 41   | 6.2244        | -      | -               | -                 | -                        |
+| 0.2308 | 42   | 6.007         | -      | -               | -                 | -                        |
+| 0.2363 | 43   | 5.977         | -      | -               | -                 | -                        |
+| 0.2418 | 44   | 6.0748        | -      | -               | -                 | -                        |
+| 0.2473 | 45   | 5.7946        | 0.8549 | 0.6404          | 0.4116            | 0.2847                   |
+| 0.2527 | 46   | 5.8751        | -      | -               | -                 | -                        |
+| 0.2582 | 47   | 5.543         | -      | -               | -                 | -                        |
+| 0.2637 | 48   | 5.5511        | -      | -               | -                 | -                        |
+| 0.2692 | 49   | 5.411         | -      | -               | -                 | -                        |
+| 0.2747 | 50   | 5.378         | 0.7943 | 0.6557          | 0.4159            | 0.2866                   |
+| 0.2802 | 51   | 5.3831        | -      | -               | -                 | -                        |
+| 0.2857 | 52   | 4.9729        | -      | -               | -                 | -                        |
+| 0.2912 | 53   | 5.0425        | -      | -               | -                 | -                        |
+| 0.2967 | 54   | 4.9446        | -      | -               | -                 | -                        |
+| 0.3022 | 55   | 4.9288        | 0.7178 | 0.6679          | 0.4273            | 0.3132                   |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.0.1
+- Transformers: 4.44.0
+- PyTorch: 2.4.0
+- Accelerate: 0.33.0
+- Datasets: 2.21.0
+- Tokenizers: 0.19.1
+
+## 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-55/added_tokens.json

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

checkpoint-55/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": "4.44.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-55/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.44.0",
+    "pytorch": "2.4.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-55/modules.json

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

checkpoint-55/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff739ea1aebd41763f78ab4fbd3e69fd3499c134215c3442f121e2eb09d7e5e2
+size 1130520122

checkpoint-55/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cac081e343e82b05447bdbf9eba69a8392f074ac4c145f047269de4849479ac
+size 565251810

checkpoint-55/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb18977cba831ef16b5b9ff397991d6bc68979d68a5301ff774c20dbd315171f
+size 14244

checkpoint-55/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0d2459c53df9954d756297e82f27d2632da6c4b10b0ba4d4a016ae5c356b6a
+size 1064

checkpoint-55/sentence_bert_config.json

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

checkpoint-55/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-55/spm.model

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

checkpoint-55/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": true,
+  "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-55/trainer_state.json

@@ -0,0 +1,1397 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3021978021978022,
+  "eval_steps": 5,
+  "global_step": 55,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005494505494505495,
+      "grad_norm": 38.56446075439453,
+      "learning_rate": 2.0718232044198892e-07,
+      "loss": 8.8159,
+      "step": 1
+    },
+    {
+      "epoch": 0.01098901098901099,
+      "grad_norm": 42.89330291748047,
+      "learning_rate": 4.1436464088397783e-07,
+      "loss": 9.1259,
+      "step": 2
+    },
+    {
+      "epoch": 0.016483516483516484,
+      "grad_norm": 40.88720703125,
+      "learning_rate": 6.215469613259668e-07,
+      "loss": 8.9017,
+      "step": 3
+    },
+    {
+      "epoch": 0.02197802197802198,
+      "grad_norm": 43.001651763916016,
+      "learning_rate": 8.287292817679557e-07,
+      "loss": 9.1969,
+      "step": 4
+    },
+    {
+      "epoch": 0.027472527472527472,
+      "grad_norm": 47.374000549316406,
+      "learning_rate": 1.0359116022099446e-06,
+      "loss": 9.3716,
+      "step": 5
+    },
+    {
+      "epoch": 0.027472527472527472,
+      "eval_Qnli-dev_cosine_accuracy": 0.599609375,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.9149316549301147,
+      "eval_Qnli-dev_cosine_ap": 0.5535936772329058,
+      "eval_Qnli-dev_cosine_f1": 0.6315789473684211,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.6663029193878174,
+      "eval_Qnli-dev_cosine_precision": 0.4633663366336634,
+      "eval_Qnli-dev_cosine_recall": 0.9915254237288136,
+      "eval_Qnli-dev_dot_accuracy": 0.576171875,
+      "eval_Qnli-dev_dot_accuracy_threshold": 376.8692321777344,
+      "eval_Qnli-dev_dot_ap": 0.49386849366879665,
+      "eval_Qnli-dev_dot_f1": 0.6291834002677376,
+      "eval_Qnli-dev_dot_f1_threshold": 237.3916015625,
+      "eval_Qnli-dev_dot_precision": 0.4598825831702544,
+      "eval_Qnli-dev_dot_recall": 0.9957627118644068,
+      "eval_Qnli-dev_euclidean_accuracy": 0.603515625,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 8.217397689819336,
+      "eval_Qnli-dev_euclidean_ap": 0.5622359472661989,
+      "eval_Qnli-dev_euclidean_f1": 0.6307277628032345,
+      "eval_Qnli-dev_euclidean_f1_threshold": 17.456497192382812,
+      "eval_Qnli-dev_euclidean_precision": 0.4624505928853755,
+      "eval_Qnli-dev_euclidean_recall": 0.9915254237288136,
+      "eval_Qnli-dev_manhattan_accuracy": 0.6171875,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 170.3812255859375,
+      "eval_Qnli-dev_manhattan_ap": 0.6067473143476283,
+      "eval_Qnli-dev_manhattan_f1": 0.629878869448183,
+      "eval_Qnli-dev_manhattan_f1_threshold": 251.22586059570312,
+      "eval_Qnli-dev_manhattan_precision": 0.46153846153846156,
+      "eval_Qnli-dev_manhattan_recall": 0.9915254237288136,
+      "eval_Qnli-dev_max_accuracy": 0.6171875,
+      "eval_Qnli-dev_max_accuracy_threshold": 376.8692321777344,
+      "eval_Qnli-dev_max_ap": 0.6067473143476283,
+      "eval_Qnli-dev_max_f1": 0.6315789473684211,
+      "eval_Qnli-dev_max_f1_threshold": 251.22586059570312,
+      "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": 0.984787106513977,
+      "eval_allNLI-dev_cosine_ap": 0.34628735123984455,
+      "eval_allNLI-dev_cosine_f1": 0.5105105105105106,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.7257537841796875,
+      "eval_allNLI-dev_cosine_precision": 0.3448275862068966,
+      "eval_allNLI-dev_cosine_recall": 0.9826589595375722,
+      "eval_allNLI-dev_dot_accuracy": 0.66015625,
+      "eval_allNLI-dev_dot_accuracy_threshold": 510.50128173828125,
+      "eval_allNLI-dev_dot_ap": 0.3331728171237445,
+      "eval_allNLI-dev_dot_f1": 0.5073746312684366,
+      "eval_allNLI-dev_dot_f1_threshold": 320.4217834472656,
+      "eval_allNLI-dev_dot_precision": 0.3405940594059406,
+      "eval_allNLI-dev_dot_recall": 0.9942196531791907,
+      "eval_allNLI-dev_euclidean_accuracy": 0.6640625,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 3.554497241973877,
+      "eval_allNLI-dev_euclidean_ap": 0.3510566487009116,
+      "eval_allNLI-dev_euclidean_f1": 0.5120481927710844,
+      "eval_allNLI-dev_euclidean_f1_threshold": 16.369325637817383,
+      "eval_allNLI-dev_euclidean_precision": 0.34623217922606925,
+      "eval_allNLI-dev_euclidean_recall": 0.9826589595375722,
+      "eval_allNLI-dev_manhattan_accuracy": 0.6640625,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 59.6655387878418,
+      "eval_allNLI-dev_manhattan_ap": 0.3706224646404015,
+      "eval_allNLI-dev_manhattan_f1": 0.5096870342771982,
+      "eval_allNLI-dev_manhattan_f1_threshold": 247.54861450195312,
+      "eval_allNLI-dev_manhattan_precision": 0.3433734939759036,
+      "eval_allNLI-dev_manhattan_recall": 0.9884393063583815,
+      "eval_allNLI-dev_max_accuracy": 0.6640625,
+      "eval_allNLI-dev_max_accuracy_threshold": 510.50128173828125,
+      "eval_allNLI-dev_max_ap": 0.3706224646404015,
+      "eval_allNLI-dev_max_f1": 0.5120481927710844,
+      "eval_allNLI-dev_max_f1_threshold": 320.4217834472656,
+      "eval_allNLI-dev_max_precision": 0.34623217922606925,
+      "eval_allNLI-dev_max_recall": 0.9942196531791907,
+      "eval_loss": 1.3745524883270264,
+      "eval_runtime": 56.8233,
+      "eval_samples_per_second": 26.503,
+      "eval_sequential_score": 0.6067473143476283,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.1514570156735535,
+      "eval_sts-test_pearson_dot": 0.28408663830954645,
+      "eval_sts-test_pearson_euclidean": 0.14094815932702276,
+      "eval_sts-test_pearson_manhattan": 0.18757962873571718,
+      "eval_sts-test_pearson_max": 0.28408663830954645,
+      "eval_sts-test_spearman_cosine": 0.19430208270682803,
+      "eval_sts-test_spearman_dot": 0.29861509823099586,
+      "eval_sts-test_spearman_euclidean": 0.16253371729283397,
+      "eval_sts-test_spearman_manhattan": 0.20774542441268956,
+      "eval_sts-test_spearman_max": 0.29861509823099586,
+      "step": 5
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 41.89334487915039,
+      "learning_rate": 1.2430939226519335e-06,
+      "loss": 9.0425,
+      "step": 6
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 38.501129150390625,
+      "learning_rate": 1.4502762430939224e-06,
+      "loss": 8.7309,
+      "step": 7
+    },
+    {
+      "epoch": 0.04395604395604396,
+      "grad_norm": 42.019371032714844,
+      "learning_rate": 1.6574585635359113e-06,
+      "loss": 9.0123,
+      "step": 8
+    },
+    {
+      "epoch": 0.04945054945054945,
+      "grad_norm": 41.45735168457031,
+      "learning_rate": 1.8646408839779003e-06,
+      "loss": 8.8095,
+      "step": 9
+    },
+    {
+      "epoch": 0.054945054945054944,
+      "grad_norm": 45.60405731201172,
+      "learning_rate": 2.071823204419889e-06,
+      "loss": 9.3194,
+      "step": 10
+    },
+    {
+      "epoch": 0.054945054945054944,
+      "eval_Qnli-dev_cosine_accuracy": 0.6015625,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.915002703666687,
+      "eval_Qnli-dev_cosine_ap": 0.5561367291733588,
+      "eval_Qnli-dev_cosine_f1": 0.6315789473684211,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.6884599328041077,
+      "eval_Qnli-dev_cosine_precision": 0.4633663366336634,
+      "eval_Qnli-dev_cosine_recall": 0.9915254237288136,
+      "eval_Qnli-dev_dot_accuracy": 0.580078125,
+      "eval_Qnli-dev_dot_accuracy_threshold": 375.57147216796875,
+      "eval_Qnli-dev_dot_ap": 0.49566240556276475,
+      "eval_Qnli-dev_dot_f1": 0.6291834002677376,
+      "eval_Qnli-dev_dot_f1_threshold": 236.90142822265625,
+      "eval_Qnli-dev_dot_precision": 0.4598825831702544,
+      "eval_Qnli-dev_dot_recall": 0.9957627118644068,
+      "eval_Qnli-dev_euclidean_accuracy": 0.599609375,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 8.115190505981445,
+      "eval_Qnli-dev_euclidean_ap": 0.5639171158048,
+      "eval_Qnli-dev_euclidean_f1": 0.6307277628032345,
+      "eval_Qnli-dev_euclidean_f1_threshold": 16.781246185302734,
+      "eval_Qnli-dev_euclidean_precision": 0.4624505928853755,
+      "eval_Qnli-dev_euclidean_recall": 0.9915254237288136,
+      "eval_Qnli-dev_manhattan_accuracy": 0.6171875,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 169.50537109375,
+      "eval_Qnli-dev_manhattan_ap": 0.608914651260932,
+      "eval_Qnli-dev_manhattan_f1": 0.629878869448183,
+      "eval_Qnli-dev_manhattan_f1_threshold": 245.56036376953125,
+      "eval_Qnli-dev_manhattan_precision": 0.46153846153846156,
+      "eval_Qnli-dev_manhattan_recall": 0.9915254237288136,
+      "eval_Qnli-dev_max_accuracy": 0.6171875,
+      "eval_Qnli-dev_max_accuracy_threshold": 375.57147216796875,
+      "eval_Qnli-dev_max_ap": 0.608914651260932,
+      "eval_Qnli-dev_max_f1": 0.6315789473684211,
+      "eval_Qnli-dev_max_f1_threshold": 245.56036376953125,
+      "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": 0.985245406627655,
+      "eval_allNLI-dev_cosine_ap": 0.34847362780632896,
+      "eval_allNLI-dev_cosine_f1": 0.5097451274362819,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.7295986413955688,
+      "eval_allNLI-dev_cosine_precision": 0.3441295546558704,
+      "eval_allNLI-dev_cosine_recall": 0.9826589595375722,
+      "eval_allNLI-dev_dot_accuracy": 0.66015625,
+      "eval_allNLI-dev_dot_accuracy_threshold": 511.2210693359375,
+      "eval_allNLI-dev_dot_ap": 0.3336754845077054,
+      "eval_allNLI-dev_dot_f1": 0.5066273932253312,
+      "eval_allNLI-dev_dot_f1_threshold": 324.83251953125,
+      "eval_allNLI-dev_dot_precision": 0.33992094861660077,
+      "eval_allNLI-dev_dot_recall": 0.9942196531791907,
+      "eval_allNLI-dev_euclidean_accuracy": 0.666015625,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 4.795613765716553,
+      "eval_allNLI-dev_euclidean_ap": 0.3551307012605588,
+      "eval_allNLI-dev_euclidean_f1": 0.5121212121212121,
+      "eval_allNLI-dev_euclidean_f1_threshold": 15.640409469604492,
+      "eval_allNLI-dev_euclidean_precision": 0.3470225872689938,
+      "eval_allNLI-dev_euclidean_recall": 0.976878612716763,
+      "eval_allNLI-dev_manhattan_accuracy": 0.6640625,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 59.08678436279297,
+      "eval_allNLI-dev_manhattan_ap": 0.37214209846872026,
+      "eval_allNLI-dev_manhattan_f1": 0.5096870342771982,
+      "eval_allNLI-dev_manhattan_f1_threshold": 243.08975219726562,
+      "eval_allNLI-dev_manhattan_precision": 0.3433734939759036,
+      "eval_allNLI-dev_manhattan_recall": 0.9884393063583815,
+      "eval_allNLI-dev_max_accuracy": 0.666015625,
+      "eval_allNLI-dev_max_accuracy_threshold": 511.2210693359375,
+      "eval_allNLI-dev_max_ap": 0.37214209846872026,
+      "eval_allNLI-dev_max_f1": 0.5121212121212121,
+      "eval_allNLI-dev_max_f1_threshold": 324.83251953125,
+      "eval_allNLI-dev_max_precision": 0.3470225872689938,
+      "eval_allNLI-dev_max_recall": 0.9942196531791907,
+      "eval_loss": 1.3227455615997314,
+      "eval_runtime": 56.8227,
+      "eval_samples_per_second": 26.503,
+      "eval_sequential_score": 0.608914651260932,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.15490047433594056,
+      "eval_sts-test_pearson_dot": 0.2911984188989889,
+      "eval_sts-test_pearson_euclidean": 0.14360669882703436,
+      "eval_sts-test_pearson_manhattan": 0.1892258838489897,
+      "eval_sts-test_pearson_max": 0.2911984188989889,
+      "eval_sts-test_spearman_cosine": 0.19757270192698087,
+      "eval_sts-test_spearman_dot": 0.3042365279306765,
+      "eval_sts-test_spearman_euclidean": 0.16524958184415522,
+      "eval_sts-test_spearman_manhattan": 0.21029544078929435,
+      "eval_sts-test_spearman_max": 0.3042365279306765,
+      "step": 10
+    },
+    {
+      "epoch": 0.06043956043956044,
+      "grad_norm": 39.49834442138672,
+      "learning_rate": 2.2790055248618783e-06,
+      "loss": 8.9873,
+      "step": 11
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 35.96696853637695,
+      "learning_rate": 2.486187845303867e-06,
+      "loss": 8.5575,
+      "step": 12
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 37.535030364990234,
+      "learning_rate": 2.693370165745856e-06,
+      "loss": 8.8096,
+      "step": 13
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 27.989038467407227,
+      "learning_rate": 2.900552486187845e-06,
+      "loss": 8.0996,
+      "step": 14
+    },
+    {
+      "epoch": 0.08241758241758242,
+      "grad_norm": 27.93619728088379,
+      "learning_rate": 3.107734806629834e-06,
+      "loss": 8.1942,
+      "step": 15
+    },
+    {
+      "epoch": 0.08241758241758242,
+      "eval_Qnli-dev_cosine_accuracy": 0.59765625,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.9154062867164612,
+      "eval_Qnli-dev_cosine_ap": 0.5603803949927255,
+      "eval_Qnli-dev_cosine_f1": 0.6315789473684211,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.7283656597137451,
+      "eval_Qnli-dev_cosine_precision": 0.4633663366336634,
+      "eval_Qnli-dev_cosine_recall": 0.9915254237288136,
+      "eval_Qnli-dev_dot_accuracy": 0.58203125,
+      "eval_Qnli-dev_dot_accuracy_threshold": 388.41607666015625,
+      "eval_Qnli-dev_dot_ap": 0.497501149468079,
+      "eval_Qnli-dev_dot_f1": 0.6291834002677376,
+      "eval_Qnli-dev_dot_f1_threshold": 236.0553741455078,
+      "eval_Qnli-dev_dot_precision": 0.4598825831702544,
+      "eval_Qnli-dev_dot_recall": 0.9957627118644068,
+      "eval_Qnli-dev_euclidean_accuracy": 0.58984375,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 8.941183090209961,
+      "eval_Qnli-dev_euclidean_ap": 0.5662645897099401,
+      "eval_Qnli-dev_euclidean_f1": 0.6307277628032345,
+      "eval_Qnli-dev_euclidean_f1_threshold": 15.756710052490234,
+      "eval_Qnli-dev_euclidean_precision": 0.4624505928853755,
+      "eval_Qnli-dev_euclidean_recall": 0.9915254237288136,
+      "eval_Qnli-dev_manhattan_accuracy": 0.615234375,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 163.0137939453125,
+      "eval_Qnli-dev_manhattan_ap": 0.6139853178845948,
+      "eval_Qnli-dev_manhattan_f1": 0.6291834002677376,
+      "eval_Qnli-dev_manhattan_f1_threshold": 285.00634765625,
+      "eval_Qnli-dev_manhattan_precision": 0.4598825831702544,
+      "eval_Qnli-dev_manhattan_recall": 0.9957627118644068,
+      "eval_Qnli-dev_max_accuracy": 0.615234375,
+      "eval_Qnli-dev_max_accuracy_threshold": 388.41607666015625,
+      "eval_Qnli-dev_max_ap": 0.6139853178845948,
+      "eval_Qnli-dev_max_f1": 0.6315789473684211,
+      "eval_Qnli-dev_max_f1_threshold": 285.00634765625,
+      "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": 0.9861629009246826,
+      "eval_allNLI-dev_cosine_ap": 0.35265879982526854,
+      "eval_allNLI-dev_cosine_f1": 0.5096296296296297,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.7308962941169739,
+      "eval_allNLI-dev_cosine_precision": 0.3426294820717131,
+      "eval_allNLI-dev_cosine_recall": 0.9942196531791907,
+      "eval_allNLI-dev_dot_accuracy": 0.662109375,
+      "eval_allNLI-dev_dot_accuracy_threshold": 498.35491943359375,
+      "eval_allNLI-dev_dot_ap": 0.33242433107393726,
+      "eval_allNLI-dev_dot_f1": 0.5058823529411766,
+      "eval_allNLI-dev_dot_f1_threshold": 329.3536376953125,
+      "eval_allNLI-dev_dot_precision": 0.33925049309664695,
+      "eval_allNLI-dev_dot_recall": 0.9942196531791907,
+      "eval_allNLI-dev_euclidean_accuracy": 0.666015625,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 4.617646217346191,
+      "eval_allNLI-dev_euclidean_ap": 0.3596931915774687,
+      "eval_allNLI-dev_euclidean_f1": 0.5104477611940298,
+      "eval_allNLI-dev_euclidean_f1_threshold": 15.696537971496582,
+      "eval_allNLI-dev_euclidean_precision": 0.3440643863179074,
+      "eval_allNLI-dev_euclidean_recall": 0.9884393063583815,
+      "eval_allNLI-dev_manhattan_accuracy": 0.6640625,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 57.86843490600586,
+      "eval_allNLI-dev_manhattan_ap": 0.37425821741092197,
+      "eval_allNLI-dev_manhattan_f1": 0.5089285714285714,
+      "eval_allNLI-dev_manhattan_f1_threshold": 239.49026489257812,
+      "eval_allNLI-dev_manhattan_precision": 0.342685370741483,
+      "eval_allNLI-dev_manhattan_recall": 0.9884393063583815,
+      "eval_allNLI-dev_max_accuracy": 0.666015625,
+      "eval_allNLI-dev_max_accuracy_threshold": 498.35491943359375,
+      "eval_allNLI-dev_max_ap": 0.37425821741092197,
+      "eval_allNLI-dev_max_f1": 0.5104477611940298,
+      "eval_allNLI-dev_max_f1_threshold": 329.3536376953125,
+      "eval_allNLI-dev_max_precision": 0.3440643863179074,
+      "eval_allNLI-dev_max_recall": 0.9942196531791907,
+      "eval_loss": 1.224420189857483,
+      "eval_runtime": 56.895,
+      "eval_samples_per_second": 26.47,
+      "eval_sequential_score": 0.6139853178845948,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.16376006142638552,
+      "eval_sts-test_pearson_dot": 0.30438012531511927,
+      "eval_sts-test_pearson_euclidean": 0.1505780981176037,
+      "eval_sts-test_pearson_manhattan": 0.19362843879381605,
+      "eval_sts-test_pearson_max": 0.30438012531511927,
+      "eval_sts-test_spearman_cosine": 0.20852655768027648,
+      "eval_sts-test_spearman_dot": 0.3147068910558995,
+      "eval_sts-test_spearman_euclidean": 0.17318335397119086,
+      "eval_sts-test_spearman_manhattan": 0.21532141020490103,
+      "eval_sts-test_spearman_max": 0.3147068910558995,
+      "step": 15
+    },
+    {
+      "epoch": 0.08791208791208792,
+      "grad_norm": 28.57341766357422,
+      "learning_rate": 3.3149171270718227e-06,
+      "loss": 8.1654,
+      "step": 16
+    },
+    {
+      "epoch": 0.09340659340659341,
+      "grad_norm": 21.84433364868164,
+      "learning_rate": 3.522099447513812e-06,
+      "loss": 7.7336,
+      "step": 17
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 23.60162353515625,
+      "learning_rate": 3.7292817679558005e-06,
+      "loss": 7.9535,
+      "step": 18
+    },
+    {
+      "epoch": 0.1043956043956044,
+      "grad_norm": 22.785541534423828,
+      "learning_rate": 3.936464088397789e-06,
+      "loss": 7.9322,
+      "step": 19
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "grad_norm": 18.464128494262695,
+      "learning_rate": 4.143646408839778e-06,
+      "loss": 7.6812,
+      "step": 20
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "eval_Qnli-dev_cosine_accuracy": 0.583984375,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.9213418960571289,
+      "eval_Qnli-dev_cosine_ap": 0.5636458261475978,
+      "eval_Qnli-dev_cosine_f1": 0.6328767123287672,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.7996987700462341,
+      "eval_Qnli-dev_cosine_precision": 0.4676113360323887,
+      "eval_Qnli-dev_cosine_recall": 0.9788135593220338,
+      "eval_Qnli-dev_dot_accuracy": 0.578125,
+      "eval_Qnli-dev_dot_accuracy_threshold": 391.3887939453125,
+      "eval_Qnli-dev_dot_ap": 0.49946111380185365,
+      "eval_Qnli-dev_dot_f1": 0.6291834002677376,
+      "eval_Qnli-dev_dot_f1_threshold": 237.4534149169922,
+      "eval_Qnli-dev_dot_precision": 0.4598825831702544,
+      "eval_Qnli-dev_dot_recall": 0.9957627118644068,
+      "eval_Qnli-dev_euclidean_accuracy": 0.59375,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 7.3581438064575195,
+      "eval_Qnli-dev_euclidean_ap": 0.5724385046320207,
+      "eval_Qnli-dev_euclidean_f1": 0.6321525885558583,
+      "eval_Qnli-dev_euclidean_f1_threshold": 13.227872848510742,
+      "eval_Qnli-dev_euclidean_precision": 0.46586345381526106,
+      "eval_Qnli-dev_euclidean_recall": 0.9830508474576272,
+      "eval_Qnli-dev_manhattan_accuracy": 0.62109375,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 162.46531677246094,
+      "eval_Qnli-dev_manhattan_ap": 0.6199265668268106,
+      "eval_Qnli-dev_manhattan_f1": 0.6332794830371568,
+      "eval_Qnli-dev_manhattan_f1_threshold": 181.62945556640625,
+      "eval_Qnli-dev_manhattan_precision": 0.5117493472584856,
+      "eval_Qnli-dev_manhattan_recall": 0.8305084745762712,
+      "eval_Qnli-dev_max_accuracy": 0.62109375,
+      "eval_Qnli-dev_max_accuracy_threshold": 391.3887939453125,
+      "eval_Qnli-dev_max_ap": 0.6199265668268106,
+      "eval_Qnli-dev_max_f1": 0.6332794830371568,
+      "eval_Qnli-dev_max_f1_threshold": 237.4534149169922,
+      "eval_Qnli-dev_max_precision": 0.5117493472584856,
+      "eval_Qnli-dev_max_recall": 0.9957627118644068,
+      "eval_allNLI-dev_cosine_accuracy": 0.6640625,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.987220287322998,
+      "eval_allNLI-dev_cosine_ap": 0.3616430753144169,
+      "eval_allNLI-dev_cosine_f1": 0.5103857566765578,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.7597876787185669,
+      "eval_allNLI-dev_cosine_precision": 0.34331337325349304,
+      "eval_allNLI-dev_cosine_recall": 0.9942196531791907,
+      "eval_allNLI-dev_dot_accuracy": 0.662109375,
+      "eval_allNLI-dev_dot_accuracy_threshold": 499.94134521484375,
+      "eval_allNLI-dev_dot_ap": 0.32968058746925677,
+      "eval_allNLI-dev_dot_f1": 0.5065885797950219,
+      "eval_allNLI-dev_dot_f1_threshold": 326.2508850097656,
+      "eval_allNLI-dev_dot_precision": 0.3392156862745098,
+      "eval_allNLI-dev_dot_recall": 1.0,
+      "eval_allNLI-dev_euclidean_accuracy": 0.66796875,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 4.4667768478393555,
+      "eval_allNLI-dev_euclidean_ap": 0.36738456823550303,
+      "eval_allNLI-dev_euclidean_f1": 0.5081723625557207,
+      "eval_allNLI-dev_euclidean_f1_threshold": 15.153694152832031,
+      "eval_allNLI-dev_euclidean_precision": 0.342,
+      "eval_allNLI-dev_euclidean_recall": 0.9884393063583815,
+      "eval_allNLI-dev_manhattan_accuracy": 0.6640625,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 56.36178970336914,
+      "eval_allNLI-dev_manhattan_ap": 0.37895381964253766,
+      "eval_allNLI-dev_manhattan_f1": 0.5074183976261127,
+      "eval_allNLI-dev_manhattan_f1_threshold": 235.34033203125,
+      "eval_allNLI-dev_manhattan_precision": 0.3413173652694611,
+      "eval_allNLI-dev_manhattan_recall": 0.9884393063583815,
+      "eval_allNLI-dev_max_accuracy": 0.66796875,
+      "eval_allNLI-dev_max_accuracy_threshold": 499.94134521484375,
+      "eval_allNLI-dev_max_ap": 0.37895381964253766,
+      "eval_allNLI-dev_max_f1": 0.5103857566765578,
+      "eval_allNLI-dev_max_f1_threshold": 326.2508850097656,
+      "eval_allNLI-dev_max_precision": 0.34331337325349304,
+      "eval_allNLI-dev_max_recall": 1.0,
+      "eval_loss": 1.1300753355026245,
+      "eval_runtime": 56.883,
+      "eval_samples_per_second": 26.475,
+      "eval_sequential_score": 0.6199265668268106,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.1779758357593114,
+      "eval_sts-test_pearson_dot": 0.3143294512111131,
+      "eval_sts-test_pearson_euclidean": 0.16236578525254278,
+      "eval_sts-test_pearson_manhattan": 0.20112989669839879,
+      "eval_sts-test_pearson_max": 0.3143294512111131,
+      "eval_sts-test_spearman_cosine": 0.22331353797679107,
+      "eval_sts-test_spearman_dot": 0.32041258738078016,
+      "eval_sts-test_spearman_euclidean": 0.18499862675500958,
+      "eval_sts-test_spearman_manhattan": 0.22244513974949096,
+      "eval_sts-test_spearman_max": 0.32041258738078016,
+      "step": 20
+    },
+    {
+      "epoch": 0.11538461538461539,
+      "grad_norm": 16.04839324951172,
+      "learning_rate": 4.3508287292817675e-06,
+      "loss": 7.551,
+      "step": 21
+    },
+    {
+      "epoch": 0.12087912087912088,
+      "grad_norm": 13.244675636291504,
+      "learning_rate": 4.558011049723757e-06,
+      "loss": 7.3788,
+      "step": 22
+    },
+    {
+      "epoch": 0.12637362637362637,
+      "grad_norm": 10.887700080871582,
+      "learning_rate": 4.765193370165746e-06,
+      "loss": 7.1746,
+      "step": 23
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 11.019057273864746,
+      "learning_rate": 4.972375690607734e-06,
+      "loss": 7.1849,
+      "step": 24
+    },
+    {
+      "epoch": 0.13736263736263737,
+      "grad_norm": 10.919517517089844,
+      "learning_rate": 5.179558011049724e-06,
+      "loss": 7.1085,
+      "step": 25
+    },
+    {
+      "epoch": 0.13736263736263737,
+      "eval_Qnli-dev_cosine_accuracy": 0.58984375,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.9257529973983765,
+      "eval_Qnli-dev_cosine_ap": 0.5652038241773732,
+      "eval_Qnli-dev_cosine_f1": 0.6346153846153846,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.8198822140693665,
+      "eval_Qnli-dev_cosine_precision": 0.4695121951219512,
+      "eval_Qnli-dev_cosine_recall": 0.9788135593220338,
+      "eval_Qnli-dev_dot_accuracy": 0.57421875,
+      "eval_Qnli-dev_dot_accuracy_threshold": 398.296875,
+      "eval_Qnli-dev_dot_ap": 0.5000550252228433,
+      "eval_Qnli-dev_dot_f1": 0.6291834002677376,
+      "eval_Qnli-dev_dot_f1_threshold": 245.24951171875,
+      "eval_Qnli-dev_dot_precision": 0.4598825831702544,
+      "eval_Qnli-dev_dot_recall": 0.9957627118644068,
+      "eval_Qnli-dev_euclidean_accuracy": 0.587890625,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 7.207454681396484,
+      "eval_Qnli-dev_euclidean_ap": 0.5720947339439485,
+      "eval_Qnli-dev_euclidean_f1": 0.631424375917768,
+      "eval_Qnli-dev_euclidean_f1_threshold": 11.139533996582031,
+      "eval_Qnli-dev_euclidean_precision": 0.48314606741573035,
+      "eval_Qnli-dev_euclidean_recall": 0.9110169491525424,
+      "eval_Qnli-dev_manhattan_accuracy": 0.630859375,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 159.41851806640625,
+      "eval_Qnli-dev_manhattan_ap": 0.6195419467022242,
+      "eval_Qnli-dev_manhattan_f1": 0.6365007541478129,
+      "eval_Qnli-dev_manhattan_f1_threshold": 184.75155639648438,
+      "eval_Qnli-dev_manhattan_precision": 0.49414519906323184,
+      "eval_Qnli-dev_manhattan_recall": 0.8940677966101694,
+      "eval_Qnli-dev_max_accuracy": 0.630859375,
+      "eval_Qnli-dev_max_accuracy_threshold": 398.296875,
+      "eval_Qnli-dev_max_ap": 0.6195419467022242,
+      "eval_Qnli-dev_max_f1": 0.6365007541478129,
+      "eval_Qnli-dev_max_f1_threshold": 245.24951171875,
+      "eval_Qnli-dev_max_precision": 0.49414519906323184,
+      "eval_Qnli-dev_max_recall": 0.9957627118644068,
+      "eval_allNLI-dev_cosine_accuracy": 0.666015625,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.9775335788726807,
+      "eval_allNLI-dev_cosine_ap": 0.37066068068308244,
+      "eval_allNLI-dev_cosine_f1": 0.5066666666666666,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.7791957855224609,
+      "eval_allNLI-dev_cosine_precision": 0.34063745019920316,
+      "eval_allNLI-dev_cosine_recall": 0.9884393063583815,
+      "eval_allNLI-dev_dot_accuracy": 0.66015625,
+      "eval_allNLI-dev_dot_accuracy_threshold": 524.8079223632812,
+      "eval_allNLI-dev_dot_ap": 0.3301995657806253,
+      "eval_allNLI-dev_dot_f1": 0.5058479532163743,
+      "eval_allNLI-dev_dot_f1_threshold": 326.4276428222656,
+      "eval_allNLI-dev_dot_precision": 0.3385518590998043,
+      "eval_allNLI-dev_dot_recall": 1.0,
+      "eval_allNLI-dev_euclidean_accuracy": 0.66796875,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 4.273993492126465,
+      "eval_allNLI-dev_euclidean_ap": 0.3729474782349314,
+      "eval_allNLI-dev_euclidean_f1": 0.5075075075075075,
+      "eval_allNLI-dev_euclidean_f1_threshold": 13.357471466064453,
+      "eval_allNLI-dev_euclidean_precision": 0.34279918864097364,
+      "eval_allNLI-dev_euclidean_recall": 0.976878612716763,
+      "eval_allNLI-dev_manhattan_accuracy": 0.666015625,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 87.52474975585938,
+      "eval_allNLI-dev_manhattan_ap": 0.3851618671264259,
+      "eval_allNLI-dev_manhattan_f1": 0.5066273932253312,
+      "eval_allNLI-dev_manhattan_f1_threshold": 237.66885375976562,
+      "eval_allNLI-dev_manhattan_precision": 0.33992094861660077,
+      "eval_allNLI-dev_manhattan_recall": 0.9942196531791907,
+      "eval_allNLI-dev_max_accuracy": 0.66796875,
+      "eval_allNLI-dev_max_accuracy_threshold": 524.8079223632812,
+      "eval_allNLI-dev_max_ap": 0.3851618671264259,
+      "eval_allNLI-dev_max_f1": 0.5075075075075075,
+      "eval_allNLI-dev_max_f1_threshold": 326.4276428222656,
+      "eval_allNLI-dev_max_precision": 0.34279918864097364,
+      "eval_allNLI-dev_max_recall": 1.0,
+      "eval_loss": 1.0723015069961548,
+      "eval_runtime": 56.965,
+      "eval_samples_per_second": 26.437,
+      "eval_sequential_score": 0.6195419467022242,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.19236546870487506,
+      "eval_sts-test_pearson_dot": 0.31683240996339884,
+      "eval_sts-test_pearson_euclidean": 0.17509975514192921,
+      "eval_sts-test_pearson_manhattan": 0.2091062445542419,
+      "eval_sts-test_pearson_max": 0.31683240996339884,
+      "eval_sts-test_spearman_cosine": 0.23571321748312007,
+      "eval_sts-test_spearman_dot": 0.3217659550277789,
+      "eval_sts-test_spearman_euclidean": 0.1966071039599386,
+      "eval_sts-test_spearman_manhattan": 0.23094926670295998,
+      "eval_sts-test_spearman_max": 0.3217659550277789,
+      "step": 25
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 11.845592498779297,
+      "learning_rate": 5.386740331491712e-06,
+      "loss": 7.3926,
+      "step": 26
+    },
+    {
+      "epoch": 0.14835164835164835,
+      "grad_norm": 11.545681953430176,
+      "learning_rate": 5.593922651933701e-06,
+      "loss": 7.1817,
+      "step": 27
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 11.321039199829102,
+      "learning_rate": 5.80110497237569e-06,
+      "loss": 7.239,
+      "step": 28
+    },
+    {
+      "epoch": 0.15934065934065933,
+      "grad_norm": 9.933686256408691,
+      "learning_rate": 6.00828729281768e-06,
+      "loss": 7.0023,
+      "step": 29
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 10.041378021240234,
+      "learning_rate": 6.215469613259668e-06,
+      "loss": 6.9898,
+      "step": 30
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "eval_Qnli-dev_cosine_accuracy": 0.59375,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.9396011233329773,
+      "eval_Qnli-dev_cosine_ap": 0.57014985501852,
+      "eval_Qnli-dev_cosine_f1": 0.6318681318681318,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.8371821045875549,
+      "eval_Qnli-dev_cosine_precision": 0.46747967479674796,
+      "eval_Qnli-dev_cosine_recall": 0.9745762711864406,
+      "eval_Qnli-dev_dot_accuracy": 0.57421875,
+      "eval_Qnli-dev_dot_accuracy_threshold": 411.27325439453125,
+      "eval_Qnli-dev_dot_ap": 0.49761647661900815,
+      "eval_Qnli-dev_dot_f1": 0.6291834002677376,
+      "eval_Qnli-dev_dot_f1_threshold": 262.31964111328125,
+      "eval_Qnli-dev_dot_precision": 0.4598825831702544,
+      "eval_Qnli-dev_dot_recall": 0.9957627118644068,
+      "eval_Qnli-dev_euclidean_accuracy": 0.595703125,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 7.126171112060547,
+      "eval_Qnli-dev_euclidean_ap": 0.5771748855905092,
+      "eval_Qnli-dev_euclidean_f1": 0.6312925170068028,
+      "eval_Qnli-dev_euclidean_f1_threshold": 12.285415649414062,
+      "eval_Qnli-dev_euclidean_precision": 0.4649298597194389,
+      "eval_Qnli-dev_euclidean_recall": 0.9830508474576272,
+      "eval_Qnli-dev_manhattan_accuracy": 0.62890625,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 153.70269775390625,
+      "eval_Qnli-dev_manhattan_ap": 0.621529978717656,
+      "eval_Qnli-dev_manhattan_f1": 0.6396255850234009,
+      "eval_Qnli-dev_manhattan_f1_threshold": 176.74929809570312,
+      "eval_Qnli-dev_manhattan_precision": 0.5061728395061729,
+      "eval_Qnli-dev_manhattan_recall": 0.8686440677966102,
+      "eval_Qnli-dev_max_accuracy": 0.62890625,
+      "eval_Qnli-dev_max_accuracy_threshold": 411.27325439453125,
+      "eval_Qnli-dev_max_ap": 0.621529978717656,
+      "eval_Qnli-dev_max_f1": 0.6396255850234009,
+      "eval_Qnli-dev_max_f1_threshold": 262.31964111328125,
+      "eval_Qnli-dev_max_precision": 0.5061728395061729,
+      "eval_Qnli-dev_max_recall": 0.9957627118644068,
+      "eval_allNLI-dev_cosine_accuracy": 0.66796875,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.9714565277099609,
+      "eval_allNLI-dev_cosine_ap": 0.3762859388623787,
+      "eval_allNLI-dev_cosine_f1": 0.5060606060606061,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.8386883735656738,
+      "eval_allNLI-dev_cosine_precision": 0.34291581108829566,
+      "eval_allNLI-dev_cosine_recall": 0.9653179190751445,
+      "eval_allNLI-dev_dot_accuracy": 0.66015625,
+      "eval_allNLI-dev_dot_accuracy_threshold": 532.74462890625,
+      "eval_allNLI-dev_dot_ap": 0.3295831980167142,
+      "eval_allNLI-dev_dot_f1": 0.5036603221083455,
+      "eval_allNLI-dev_dot_f1_threshold": 337.565185546875,
+      "eval_allNLI-dev_dot_precision": 0.33725490196078434,
+      "eval_allNLI-dev_dot_recall": 0.9942196531791907,
+      "eval_allNLI-dev_euclidean_accuracy": 0.66796875,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 4.119659423828125,
+      "eval_allNLI-dev_euclidean_ap": 0.3787739041503637,
+      "eval_allNLI-dev_euclidean_f1": 0.5098634294385432,
+      "eval_allNLI-dev_euclidean_f1_threshold": 12.496034622192383,
+      "eval_allNLI-dev_euclidean_precision": 0.345679012345679,
+      "eval_allNLI-dev_euclidean_recall": 0.9710982658959537,
+      "eval_allNLI-dev_manhattan_accuracy": 0.666015625,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 80.58773803710938,
+      "eval_allNLI-dev_manhattan_ap": 0.3898279315596962,
+      "eval_allNLI-dev_manhattan_f1": 0.5066273932253312,
+      "eval_allNLI-dev_manhattan_f1_threshold": 231.53036499023438,
+      "eval_allNLI-dev_manhattan_precision": 0.33992094861660077,
+      "eval_allNLI-dev_manhattan_recall": 0.9942196531791907,
+      "eval_allNLI-dev_max_accuracy": 0.66796875,
+      "eval_allNLI-dev_max_accuracy_threshold": 532.74462890625,
+      "eval_allNLI-dev_max_ap": 0.3898279315596962,
+      "eval_allNLI-dev_max_f1": 0.5098634294385432,
+      "eval_allNLI-dev_max_f1_threshold": 337.565185546875,
+      "eval_allNLI-dev_max_precision": 0.345679012345679,
+      "eval_allNLI-dev_max_recall": 0.9942196531791907,
+      "eval_loss": 1.0282095670700073,
+      "eval_runtime": 57.0236,
+      "eval_samples_per_second": 26.41,
+      "eval_sequential_score": 0.621529978717656,
+      "eval_steps_per_second": 0.21,
+      "eval_sts-test_pearson_cosine": 0.2061136669654613,
+      "eval_sts-test_pearson_dot": 0.31343978856163146,
+      "eval_sts-test_pearson_euclidean": 0.18904663819220255,
+      "eval_sts-test_pearson_manhattan": 0.21785478120910598,
+      "eval_sts-test_pearson_max": 0.31343978856163146,
+      "eval_sts-test_spearman_cosine": 0.24768503017928584,
+      "eval_sts-test_spearman_dot": 0.31740404957995916,
+      "eval_sts-test_spearman_euclidean": 0.20965200715300875,
+      "eval_sts-test_spearman_manhattan": 0.2394205014793063,
+      "eval_sts-test_spearman_max": 0.31740404957995916,
+      "step": 30
+    },
+    {
+      "epoch": 0.17032967032967034,
+      "grad_norm": 9.322327613830566,
+      "learning_rate": 6.422651933701657e-06,
+      "loss": 6.9776,
+      "step": 31
+    },
+    {
+      "epoch": 0.17582417582417584,
+      "grad_norm": 8.770292282104492,
+      "learning_rate": 6.629834254143645e-06,
+      "loss": 6.8088,
+      "step": 32
+    },
+    {
+      "epoch": 0.1813186813186813,
+      "grad_norm": 10.2041654586792,
+      "learning_rate": 6.837016574585635e-06,
+      "loss": 6.8916,
+      "step": 33
+    },
+    {
+      "epoch": 0.18681318681318682,
+      "grad_norm": 8.867596626281738,
+      "learning_rate": 7.044198895027624e-06,
+      "loss": 6.6931,
+      "step": 34
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 9.029094696044922,
+      "learning_rate": 7.251381215469613e-06,
+      "loss": 6.5707,
+      "step": 35
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "eval_Qnli-dev_cosine_accuracy": 0.609375,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.9358766078948975,
+      "eval_Qnli-dev_cosine_ap": 0.5800406926662295,
+      "eval_Qnli-dev_cosine_f1": 0.6291834002677376,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.6559731960296631,
+      "eval_Qnli-dev_cosine_precision": 0.4598825831702544,
+      "eval_Qnli-dev_cosine_recall": 0.9957627118644068,
+      "eval_Qnli-dev_dot_accuracy": 0.572265625,
+      "eval_Qnli-dev_dot_accuracy_threshold": 415.3104248046875,
+      "eval_Qnli-dev_dot_ap": 0.49721213365007333,
+      "eval_Qnli-dev_dot_f1": 0.6291834002677376,
+      "eval_Qnli-dev_dot_f1_threshold": 280.5462951660156,
+      "eval_Qnli-dev_dot_precision": 0.4598825831702544,
+      "eval_Qnli-dev_dot_recall": 0.9957627118644068,
+      "eval_Qnli-dev_euclidean_accuracy": 0.59765625,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 7.095188140869141,
+      "eval_Qnli-dev_euclidean_ap": 0.5853229647222131,
+      "eval_Qnli-dev_euclidean_f1": 0.6291834002677376,
+      "eval_Qnli-dev_euclidean_f1_threshold": 17.898162841796875,
+      "eval_Qnli-dev_euclidean_precision": 0.4598825831702544,
+      "eval_Qnli-dev_euclidean_recall": 0.9957627118644068,
+      "eval_Qnli-dev_manhattan_accuracy": 0.62890625,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 154.3598175048828,
+      "eval_Qnli-dev_manhattan_ap": 0.6252613860599432,
+      "eval_Qnli-dev_manhattan_f1": 0.6388888888888888,
+      "eval_Qnli-dev_manhattan_f1_threshold": 178.0916748046875,
+      "eval_Qnli-dev_manhattan_precision": 0.5024271844660194,
+      "eval_Qnli-dev_manhattan_recall": 0.8771186440677966,
+      "eval_Qnli-dev_max_accuracy": 0.62890625,
+      "eval_Qnli-dev_max_accuracy_threshold": 415.3104248046875,
+      "eval_Qnli-dev_max_ap": 0.6252613860599432,
+      "eval_Qnli-dev_max_f1": 0.6388888888888888,
+      "eval_Qnli-dev_max_f1_threshold": 280.5462951660156,
+      "eval_Qnli-dev_max_precision": 0.5024271844660194,
+      "eval_Qnli-dev_max_recall": 0.9957627118644068,
+      "eval_allNLI-dev_cosine_accuracy": 0.673828125,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.9733000993728638,
+      "eval_allNLI-dev_cosine_ap": 0.383380605789286,
+      "eval_allNLI-dev_cosine_f1": 0.5067466266866567,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.8367289900779724,
+      "eval_allNLI-dev_cosine_precision": 0.34210526315789475,
+      "eval_allNLI-dev_cosine_recall": 0.976878612716763,
+      "eval_allNLI-dev_dot_accuracy": 0.66015625,
+      "eval_allNLI-dev_dot_accuracy_threshold": 538.5443115234375,
+      "eval_allNLI-dev_dot_ap": 0.33316876894590236,
+      "eval_allNLI-dev_dot_f1": 0.5037037037037037,
+      "eval_allNLI-dev_dot_f1_threshold": 373.13201904296875,
+      "eval_allNLI-dev_dot_precision": 0.3386454183266932,
+      "eval_allNLI-dev_dot_recall": 0.9826589595375722,
+      "eval_allNLI-dev_euclidean_accuracy": 0.669921875,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 5.027232646942139,
+      "eval_allNLI-dev_euclidean_ap": 0.38454616945711223,
+      "eval_allNLI-dev_euclidean_f1": 0.5075987841945289,
+      "eval_allNLI-dev_euclidean_f1_threshold": 12.088457107543945,
+      "eval_allNLI-dev_euclidean_precision": 0.3443298969072165,
+      "eval_allNLI-dev_euclidean_recall": 0.9653179190751445,
+      "eval_allNLI-dev_manhattan_accuracy": 0.66796875,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 79.79684448242188,
+      "eval_allNLI-dev_manhattan_ap": 0.39522701729473053,
+      "eval_allNLI-dev_manhattan_f1": 0.5073746312684366,
+      "eval_allNLI-dev_manhattan_f1_threshold": 228.69581604003906,
+      "eval_allNLI-dev_manhattan_precision": 0.3405940594059406,
+      "eval_allNLI-dev_manhattan_recall": 0.9942196531791907,
+      "eval_allNLI-dev_max_accuracy": 0.673828125,
+      "eval_allNLI-dev_max_accuracy_threshold": 538.5443115234375,
+      "eval_allNLI-dev_max_ap": 0.39522701729473053,
+      "eval_allNLI-dev_max_f1": 0.5075987841945289,
+      "eval_allNLI-dev_max_f1_threshold": 373.13201904296875,
+      "eval_allNLI-dev_max_precision": 0.3443298969072165,
+      "eval_allNLI-dev_max_recall": 0.9942196531791907,
+      "eval_loss": 0.9846486449241638,
+      "eval_runtime": 56.9294,
+      "eval_samples_per_second": 26.454,
+      "eval_sequential_score": 0.6252613860599432,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.22023788463370408,
+      "eval_sts-test_pearson_dot": 0.30789406379111994,
+      "eval_sts-test_pearson_euclidean": 0.20441439700667358,
+      "eval_sts-test_pearson_manhattan": 0.22863465206140024,
+      "eval_sts-test_pearson_max": 0.30789406379111994,
+      "eval_sts-test_spearman_cosine": 0.2607946884475894,
+      "eval_sts-test_spearman_dot": 0.3140236287969756,
+      "eval_sts-test_spearman_euclidean": 0.2252769995703387,
+      "eval_sts-test_spearman_manhattan": 0.2514165246078849,
+      "eval_sts-test_spearman_max": 0.3140236287969756,
+      "step": 35
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 8.10656452178955,
+      "learning_rate": 7.458563535911601e-06,
+      "loss": 6.6231,
+      "step": 36
+    },
+    {
+      "epoch": 0.2032967032967033,
+      "grad_norm": 8.79859733581543,
+      "learning_rate": 7.665745856353591e-06,
+      "loss": 6.4951,
+      "step": 37
+    },
+    {
+      "epoch": 0.2087912087912088,
+      "grad_norm": 8.37302303314209,
+      "learning_rate": 7.872928176795578e-06,
+      "loss": 6.4607,
+      "step": 38
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 9.559539794921875,
+      "learning_rate": 8.08011049723757e-06,
+      "loss": 6.4504,
+      "step": 39
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "grad_norm": 9.13284683227539,
+      "learning_rate": 8.287292817679557e-06,
+      "loss": 6.3649,
+      "step": 40
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "eval_Qnli-dev_cosine_accuracy": 0.609375,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.9314916133880615,
+      "eval_Qnli-dev_cosine_ap": 0.585206574495468,
+      "eval_Qnli-dev_cosine_f1": 0.6291834002677376,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.6699934005737305,
+      "eval_Qnli-dev_cosine_precision": 0.4598825831702544,
+      "eval_Qnli-dev_cosine_recall": 0.9957627118644068,
+      "eval_Qnli-dev_dot_accuracy": 0.568359375,
+      "eval_Qnli-dev_dot_accuracy_threshold": 410.2371826171875,
+      "eval_Qnli-dev_dot_ap": 0.4994333901484545,
+      "eval_Qnli-dev_dot_f1": 0.6291834002677376,
+      "eval_Qnli-dev_dot_f1_threshold": 284.4015808105469,
+      "eval_Qnli-dev_dot_precision": 0.4598825831702544,
+      "eval_Qnli-dev_dot_recall": 0.9957627118644068,
+      "eval_Qnli-dev_euclidean_accuracy": 0.607421875,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 7.864487171173096,
+      "eval_Qnli-dev_euclidean_ap": 0.594681744506572,
+      "eval_Qnli-dev_euclidean_f1": 0.6291834002677376,
+      "eval_Qnli-dev_euclidean_f1_threshold": 17.5451717376709,
+      "eval_Qnli-dev_euclidean_precision": 0.4598825831702544,
+      "eval_Qnli-dev_euclidean_recall": 0.9957627118644068,
+      "eval_Qnli-dev_manhattan_accuracy": 0.626953125,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 160.8733367919922,
+      "eval_Qnli-dev_manhattan_ap": 0.629870060597291,
+      "eval_Qnli-dev_manhattan_f1": 0.6411149825783973,
+      "eval_Qnli-dev_manhattan_f1_threshold": 176.17674255371094,
+      "eval_Qnli-dev_manhattan_precision": 0.5443786982248521,
+      "eval_Qnli-dev_manhattan_recall": 0.7796610169491526,
+      "eval_Qnli-dev_max_accuracy": 0.626953125,
+      "eval_Qnli-dev_max_accuracy_threshold": 410.2371826171875,
+      "eval_Qnli-dev_max_ap": 0.629870060597291,
+      "eval_Qnli-dev_max_f1": 0.6411149825783973,
+      "eval_Qnli-dev_max_f1_threshold": 284.4015808105469,
+      "eval_Qnli-dev_max_precision": 0.5443786982248521,
+      "eval_Qnli-dev_max_recall": 0.9957627118644068,
+      "eval_allNLI-dev_cosine_accuracy": 0.671875,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.9736817479133606,
+      "eval_allNLI-dev_cosine_ap": 0.3931696251670499,
+      "eval_allNLI-dev_cosine_f1": 0.5082212257100149,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.8241816759109497,
+      "eval_allNLI-dev_cosine_precision": 0.34274193548387094,
+      "eval_allNLI-dev_cosine_recall": 0.9826589595375722,
+      "eval_allNLI-dev_dot_accuracy": 0.66015625,
+      "eval_allNLI-dev_dot_accuracy_threshold": 535.3334350585938,
+      "eval_allNLI-dev_dot_ap": 0.3396037265960903,
+      "eval_allNLI-dev_dot_f1": 0.5065885797950219,
+      "eval_allNLI-dev_dot_f1_threshold": 339.2867431640625,
+      "eval_allNLI-dev_dot_precision": 0.3392156862745098,
+      "eval_allNLI-dev_dot_recall": 1.0,
+      "eval_allNLI-dev_euclidean_accuracy": 0.671875,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 5.143446922302246,
+      "eval_allNLI-dev_euclidean_ap": 0.39265337020239105,
+      "eval_allNLI-dev_euclidean_f1": 0.5096870342771982,
+      "eval_allNLI-dev_euclidean_f1_threshold": 13.402521133422852,
+      "eval_allNLI-dev_euclidean_precision": 0.3433734939759036,
+      "eval_allNLI-dev_euclidean_recall": 0.9884393063583815,
+      "eval_allNLI-dev_manhattan_accuracy": 0.669921875,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 84.37629699707031,
+      "eval_allNLI-dev_manhattan_ap": 0.4041341581180743,
+      "eval_allNLI-dev_manhattan_f1": 0.5081240768094535,
+      "eval_allNLI-dev_manhattan_f1_threshold": 237.8282012939453,
+      "eval_allNLI-dev_manhattan_precision": 0.3412698412698413,
+      "eval_allNLI-dev_manhattan_recall": 0.9942196531791907,
+      "eval_allNLI-dev_max_accuracy": 0.671875,
+      "eval_allNLI-dev_max_accuracy_threshold": 535.3334350585938,
+      "eval_allNLI-dev_max_ap": 0.4041341581180743,
+      "eval_allNLI-dev_max_f1": 0.5096870342771982,
+      "eval_allNLI-dev_max_f1_threshold": 339.2867431640625,
+      "eval_allNLI-dev_max_precision": 0.3433734939759036,
+      "eval_allNLI-dev_max_recall": 1.0,
+      "eval_loss": 0.9314436912536621,
+      "eval_runtime": 56.8956,
+      "eval_samples_per_second": 26.47,
+      "eval_sequential_score": 0.629870060597291,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.2343040951892625,
+      "eval_sts-test_pearson_dot": 0.30372753804498825,
+      "eval_sts-test_pearson_euclidean": 0.21952614769670548,
+      "eval_sts-test_pearson_manhattan": 0.24089043440705574,
+      "eval_sts-test_pearson_max": 0.30372753804498825,
+      "eval_sts-test_spearman_cosine": 0.2738163657359974,
+      "eval_sts-test_spearman_dot": 0.3138135663760044,
+      "eval_sts-test_spearman_euclidean": 0.2414264767711758,
+      "eval_sts-test_spearman_manhattan": 0.26426890787444923,
+      "eval_sts-test_spearman_max": 0.3138135663760044,
+      "step": 40
+    },
+    {
+      "epoch": 0.22527472527472528,
+      "grad_norm": 10.145929336547852,
+      "learning_rate": 8.494475138121546e-06,
+      "loss": 6.2244,
+      "step": 41
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 11.5704345703125,
+      "learning_rate": 8.701657458563535e-06,
+      "loss": 6.007,
+      "step": 42
+    },
+    {
+      "epoch": 0.23626373626373626,
+      "grad_norm": 12.0188627243042,
+      "learning_rate": 8.908839779005524e-06,
+      "loss": 5.977,
+      "step": 43
+    },
+    {
+      "epoch": 0.24175824175824176,
+      "grad_norm": 10.774896621704102,
+      "learning_rate": 9.116022099447513e-06,
+      "loss": 6.0748,
+      "step": 44
+    },
+    {
+      "epoch": 0.24725274725274726,
+      "grad_norm": 10.21664810180664,
+      "learning_rate": 9.323204419889502e-06,
+      "loss": 5.7946,
+      "step": 45
+    },
+    {
+      "epoch": 0.24725274725274726,
+      "eval_Qnli-dev_cosine_accuracy": 0.626953125,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.9162209033966064,
+      "eval_Qnli-dev_cosine_ap": 0.5960506092402249,
+      "eval_Qnli-dev_cosine_f1": 0.6291834002677376,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.6565881967544556,
+      "eval_Qnli-dev_cosine_precision": 0.4598825831702544,
+      "eval_Qnli-dev_cosine_recall": 0.9957627118644068,
+      "eval_Qnli-dev_dot_accuracy": 0.580078125,
+      "eval_Qnli-dev_dot_accuracy_threshold": 380.0188293457031,
+      "eval_Qnli-dev_dot_ap": 0.5101751614495642,
+      "eval_Qnli-dev_dot_f1": 0.6291834002677376,
+      "eval_Qnli-dev_dot_f1_threshold": 259.723876953125,
+      "eval_Qnli-dev_dot_precision": 0.4598825831702544,
+      "eval_Qnli-dev_dot_recall": 0.9957627118644068,
+      "eval_Qnli-dev_euclidean_accuracy": 0.6171875,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 8.577693939208984,
+      "eval_Qnli-dev_euclidean_ap": 0.6056069399590038,
+      "eval_Qnli-dev_euclidean_f1": 0.6297297297297297,
+      "eval_Qnli-dev_euclidean_f1_threshold": 13.569040298461914,
+      "eval_Qnli-dev_euclidean_precision": 0.4623015873015873,
+      "eval_Qnli-dev_euclidean_recall": 0.9872881355932204,
+      "eval_Qnli-dev_manhattan_accuracy": 0.634765625,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 177.60205078125,
+      "eval_Qnli-dev_manhattan_ap": 0.6403997437330724,
+      "eval_Qnli-dev_manhattan_f1": 0.6466165413533835,
+      "eval_Qnli-dev_manhattan_f1_threshold": 206.83108520507812,
+      "eval_Qnli-dev_manhattan_precision": 0.5011655011655012,
+      "eval_Qnli-dev_manhattan_recall": 0.9110169491525424,
+      "eval_Qnli-dev_max_accuracy": 0.634765625,
+      "eval_Qnli-dev_max_accuracy_threshold": 380.0188293457031,
+      "eval_Qnli-dev_max_ap": 0.6403997437330724,
+      "eval_Qnli-dev_max_f1": 0.6466165413533835,
+      "eval_Qnli-dev_max_f1_threshold": 259.723876953125,
+      "eval_Qnli-dev_max_precision": 0.5011655011655012,
+      "eval_Qnli-dev_max_recall": 0.9957627118644068,
+      "eval_allNLI-dev_cosine_accuracy": 0.669921875,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.9787822961807251,
+      "eval_allNLI-dev_cosine_ap": 0.40222842666723646,
+      "eval_allNLI-dev_cosine_f1": 0.5096870342771982,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.7735908031463623,
+      "eval_allNLI-dev_cosine_precision": 0.3433734939759036,
+      "eval_allNLI-dev_cosine_recall": 0.9884393063583815,
+      "eval_allNLI-dev_dot_accuracy": 0.662109375,
+      "eval_allNLI-dev_dot_accuracy_threshold": 506.13720703125,
+      "eval_allNLI-dev_dot_ap": 0.3502405242734096,
+      "eval_allNLI-dev_dot_f1": 0.5065885797950219,
+      "eval_allNLI-dev_dot_f1_threshold": 313.13623046875,
+      "eval_allNLI-dev_dot_precision": 0.3392156862745098,
+      "eval_allNLI-dev_dot_recall": 1.0,
+      "eval_allNLI-dev_euclidean_accuracy": 0.669921875,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 4.530505180358887,
+      "eval_allNLI-dev_euclidean_ap": 0.40012968794878784,
+      "eval_allNLI-dev_euclidean_f1": 0.5105105105105106,
+      "eval_allNLI-dev_euclidean_f1_threshold": 13.752574920654297,
+      "eval_allNLI-dev_euclidean_precision": 0.3448275862068966,
+      "eval_allNLI-dev_euclidean_recall": 0.9826589595375722,
+      "eval_allNLI-dev_manhattan_accuracy": 0.669921875,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 84.84814453125,
+      "eval_allNLI-dev_manhattan_ap": 0.411550187432712,
+      "eval_allNLI-dev_manhattan_f1": 0.5152671755725191,
+      "eval_allNLI-dev_manhattan_f1_threshold": 184.89407348632812,
+      "eval_allNLI-dev_manhattan_precision": 0.38461538461538464,
+      "eval_allNLI-dev_manhattan_recall": 0.7803468208092486,
+      "eval_allNLI-dev_max_accuracy": 0.669921875,
+      "eval_allNLI-dev_max_accuracy_threshold": 506.13720703125,
+      "eval_allNLI-dev_max_ap": 0.411550187432712,
+      "eval_allNLI-dev_max_f1": 0.5152671755725191,
+      "eval_allNLI-dev_max_f1_threshold": 313.13623046875,
+      "eval_allNLI-dev_max_precision": 0.38461538461538464,
+      "eval_allNLI-dev_max_recall": 1.0,
+      "eval_loss": 0.8549203276634216,
+      "eval_runtime": 56.9038,
+      "eval_samples_per_second": 26.466,
+      "eval_sequential_score": 0.6403997437330724,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.24573194235606088,
+      "eval_sts-test_pearson_dot": 0.30146061611878155,
+      "eval_sts-test_pearson_euclidean": 0.2321150570038752,
+      "eval_sts-test_pearson_manhattan": 0.25210046027138755,
+      "eval_sts-test_pearson_max": 0.30146061611878155,
+      "eval_sts-test_spearman_cosine": 0.2847268127657434,
+      "eval_sts-test_spearman_dot": 0.31326692971810843,
+      "eval_sts-test_spearman_euclidean": 0.2512167997282951,
+      "eval_sts-test_spearman_manhattan": 0.27196800438674845,
+      "eval_sts-test_spearman_max": 0.31326692971810843,
+      "step": 45
+    },
+    {
+      "epoch": 0.25274725274725274,
+      "grad_norm": 9.914789199829102,
+      "learning_rate": 9.530386740331491e-06,
+      "loss": 5.8751,
+      "step": 46
+    },
+    {
+      "epoch": 0.25824175824175827,
+      "grad_norm": 10.506736755371094,
+      "learning_rate": 9.73756906077348e-06,
+      "loss": 5.543,
+      "step": 47
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 8.838153839111328,
+      "learning_rate": 9.944751381215468e-06,
+      "loss": 5.5511,
+      "step": 48
+    },
+    {
+      "epoch": 0.2692307692307692,
+      "grad_norm": 9.893248558044434,
+      "learning_rate": 1.0151933701657457e-05,
+      "loss": 5.411,
+      "step": 49
+    },
+    {
+      "epoch": 0.27472527472527475,
+      "grad_norm": 9.514713287353516,
+      "learning_rate": 1.0359116022099448e-05,
+      "loss": 5.378,
+      "step": 50
+    },
+    {
+      "epoch": 0.27472527472527475,
+      "eval_Qnli-dev_cosine_accuracy": 0.6328125,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.8978130221366882,
+      "eval_Qnli-dev_cosine_ap": 0.6213005329057975,
+      "eval_Qnli-dev_cosine_f1": 0.6384266263237518,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.8041039705276489,
+      "eval_Qnli-dev_cosine_precision": 0.4964705882352941,
+      "eval_Qnli-dev_cosine_recall": 0.8940677966101694,
+      "eval_Qnli-dev_dot_accuracy": 0.58984375,
+      "eval_Qnli-dev_dot_accuracy_threshold": 356.9898681640625,
+      "eval_Qnli-dev_dot_ap": 0.5268541601927336,
+      "eval_Qnli-dev_dot_f1": 0.6318758815232722,
+      "eval_Qnli-dev_dot_f1_threshold": 291.1335754394531,
+      "eval_Qnli-dev_dot_precision": 0.47357293868921774,
+      "eval_Qnli-dev_dot_recall": 0.9491525423728814,
+      "eval_Qnli-dev_euclidean_accuracy": 0.638671875,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 10.523520469665527,
+      "eval_Qnli-dev_euclidean_ap": 0.6291519886215534,
+      "eval_Qnli-dev_euclidean_f1": 0.6337448559670782,
+      "eval_Qnli-dev_euclidean_f1_threshold": 14.391512870788574,
+      "eval_Qnli-dev_euclidean_precision": 0.4685598377281947,
+      "eval_Qnli-dev_euclidean_recall": 0.9788135593220338,
+      "eval_Qnli-dev_manhattan_accuracy": 0.650390625,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 189.05128479003906,
+      "eval_Qnli-dev_manhattan_ap": 0.6556822594753774,
+      "eval_Qnli-dev_manhattan_f1": 0.6430769230769231,
+      "eval_Qnli-dev_manhattan_f1_threshold": 233.51510620117188,
+      "eval_Qnli-dev_manhattan_precision": 0.5048309178743962,
+      "eval_Qnli-dev_manhattan_recall": 0.885593220338983,
+      "eval_Qnli-dev_max_accuracy": 0.650390625,
+      "eval_Qnli-dev_max_accuracy_threshold": 356.9898681640625,
+      "eval_Qnli-dev_max_ap": 0.6556822594753774,
+      "eval_Qnli-dev_max_f1": 0.6430769230769231,
+      "eval_Qnli-dev_max_f1_threshold": 291.1335754394531,
+      "eval_Qnli-dev_max_precision": 0.5048309178743962,
+      "eval_Qnli-dev_max_recall": 0.9788135593220338,
+      "eval_allNLI-dev_cosine_accuracy": 0.66796875,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.9755356907844543,
+      "eval_allNLI-dev_cosine_ap": 0.4066962429964717,
+      "eval_allNLI-dev_cosine_f1": 0.5179856115107913,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.8535807132720947,
+      "eval_allNLI-dev_cosine_precision": 0.37597911227154046,
+      "eval_allNLI-dev_cosine_recall": 0.8323699421965318,
+      "eval_allNLI-dev_dot_accuracy": 0.666015625,
+      "eval_allNLI-dev_dot_accuracy_threshold": 476.64141845703125,
+      "eval_allNLI-dev_dot_ap": 0.3666780883869565,
+      "eval_allNLI-dev_dot_f1": 0.5111821086261982,
+      "eval_allNLI-dev_dot_f1_threshold": 348.523193359375,
+      "eval_allNLI-dev_dot_precision": 0.35320088300220753,
+      "eval_allNLI-dev_dot_recall": 0.9248554913294798,
+      "eval_allNLI-dev_euclidean_accuracy": 0.669921875,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 4.862855911254883,
+      "eval_allNLI-dev_euclidean_ap": 0.405432241017242,
+      "eval_allNLI-dev_euclidean_f1": 0.5186567164179104,
+      "eval_allNLI-dev_euclidean_f1_threshold": 11.256525039672852,
+      "eval_allNLI-dev_euclidean_precision": 0.38292011019283745,
+      "eval_allNLI-dev_euclidean_recall": 0.8034682080924855,
+      "eval_allNLI-dev_manhattan_accuracy": 0.66796875,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 83.92739868164062,
+      "eval_allNLI-dev_manhattan_ap": 0.41593074876648894,
+      "eval_allNLI-dev_manhattan_f1": 0.5261194029850746,
+      "eval_allNLI-dev_manhattan_f1_threshold": 210.06704711914062,
+      "eval_allNLI-dev_manhattan_precision": 0.3884297520661157,
+      "eval_allNLI-dev_manhattan_recall": 0.815028901734104,
+      "eval_allNLI-dev_max_accuracy": 0.669921875,
+      "eval_allNLI-dev_max_accuracy_threshold": 476.64141845703125,
+      "eval_allNLI-dev_max_ap": 0.41593074876648894,
+      "eval_allNLI-dev_max_f1": 0.5261194029850746,
+      "eval_allNLI-dev_max_f1_threshold": 348.523193359375,
+      "eval_allNLI-dev_max_precision": 0.3884297520661157,
+      "eval_allNLI-dev_max_recall": 0.9248554913294798,
+      "eval_loss": 0.794283390045166,
+      "eval_runtime": 56.8695,
+      "eval_samples_per_second": 26.482,
+      "eval_sequential_score": 0.6556822594753774,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.24584625215267258,
+      "eval_sts-test_pearson_dot": 0.2940464136694855,
+      "eval_sts-test_pearson_euclidean": 0.2382635480850375,
+      "eval_sts-test_pearson_manhattan": 0.2536304588799789,
+      "eval_sts-test_pearson_max": 0.2940464136694855,
+      "eval_sts-test_spearman_cosine": 0.28663621483553026,
+      "eval_sts-test_spearman_dot": 0.3088057212212612,
+      "eval_sts-test_spearman_euclidean": 0.2572386189636446,
+      "eval_sts-test_spearman_manhattan": 0.27229562837139487,
+      "eval_sts-test_spearman_max": 0.3088057212212612,
+      "step": 50
+    },
+    {
+      "epoch": 0.2802197802197802,
+      "grad_norm": 9.770188331604004,
+      "learning_rate": 1.0566298342541435e-05,
+      "loss": 5.3831,
+      "step": 51
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 9.599061965942383,
+      "learning_rate": 1.0773480662983425e-05,
+      "loss": 4.9729,
+      "step": 52
+    },
+    {
+      "epoch": 0.29120879120879123,
+      "grad_norm": 10.340251922607422,
+      "learning_rate": 1.0980662983425412e-05,
+      "loss": 5.0425,
+      "step": 53
+    },
+    {
+      "epoch": 0.2967032967032967,
+      "grad_norm": 9.890629768371582,
+      "learning_rate": 1.1187845303867403e-05,
+      "loss": 4.9446,
+      "step": 54
+    },
+    {
+      "epoch": 0.3021978021978022,
+      "grad_norm": 10.401249885559082,
+      "learning_rate": 1.1395027624309392e-05,
+      "loss": 4.9288,
+      "step": 55
+    },
+    {
+      "epoch": 0.3021978021978022,
+      "eval_Qnli-dev_cosine_accuracy": 0.640625,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.8695281744003296,
+      "eval_Qnli-dev_cosine_ap": 0.6314640856589909,
+      "eval_Qnli-dev_cosine_f1": 0.6578512396694215,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.7936367988586426,
+      "eval_Qnli-dev_cosine_precision": 0.5392953929539296,
+      "eval_Qnli-dev_cosine_recall": 0.8432203389830508,
+      "eval_Qnli-dev_dot_accuracy": 0.609375,
+      "eval_Qnli-dev_dot_accuracy_threshold": 351.17626953125,
+      "eval_Qnli-dev_dot_ap": 0.5366456296706419,
+      "eval_Qnli-dev_dot_f1": 0.6501650165016502,
+      "eval_Qnli-dev_dot_f1_threshold": 316.48046875,
+      "eval_Qnli-dev_dot_precision": 0.5324324324324324,
+      "eval_Qnli-dev_dot_recall": 0.8347457627118644,
+      "eval_Qnli-dev_euclidean_accuracy": 0.65234375,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 10.764808654785156,
+      "eval_Qnli-dev_euclidean_ap": 0.6460602994393339,
+      "eval_Qnli-dev_euclidean_f1": 0.6393210749646393,
+      "eval_Qnli-dev_euclidean_f1_threshold": 15.096710205078125,
+      "eval_Qnli-dev_euclidean_precision": 0.47983014861995754,
+      "eval_Qnli-dev_euclidean_recall": 0.9576271186440678,
+      "eval_Qnli-dev_manhattan_accuracy": 0.658203125,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 206.32894897460938,
+      "eval_Qnli-dev_manhattan_ap": 0.6679289689394285,
+      "eval_Qnli-dev_manhattan_f1": 0.652373660030628,
+      "eval_Qnli-dev_manhattan_f1_threshold": 261.3590393066406,
+      "eval_Qnli-dev_manhattan_precision": 0.5107913669064749,
+      "eval_Qnli-dev_manhattan_recall": 0.902542372881356,
+      "eval_Qnli-dev_max_accuracy": 0.658203125,
+      "eval_Qnli-dev_max_accuracy_threshold": 351.17626953125,
+      "eval_Qnli-dev_max_ap": 0.6679289689394285,
+      "eval_Qnli-dev_max_f1": 0.6578512396694215,
+      "eval_Qnli-dev_max_f1_threshold": 316.48046875,
+      "eval_Qnli-dev_max_precision": 0.5392953929539296,
+      "eval_Qnli-dev_max_recall": 0.9576271186440678,
+      "eval_allNLI-dev_cosine_accuracy": 0.66796875,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.9721465110778809,
+      "eval_allNLI-dev_cosine_ap": 0.4140638596370657,
+      "eval_allNLI-dev_cosine_f1": 0.5343511450381679,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.85741126537323,
+      "eval_allNLI-dev_cosine_precision": 0.39886039886039887,
+      "eval_allNLI-dev_cosine_recall": 0.8092485549132948,
+      "eval_allNLI-dev_dot_accuracy": 0.666015625,
+      "eval_allNLI-dev_dot_accuracy_threshold": 518.88671875,
+      "eval_allNLI-dev_dot_ap": 0.3781233337023534,
+      "eval_allNLI-dev_dot_f1": 0.514018691588785,
+      "eval_allNLI-dev_dot_f1_threshold": 323.9651184082031,
+      "eval_allNLI-dev_dot_precision": 0.35181236673773986,
+      "eval_allNLI-dev_dot_recall": 0.953757225433526,
+      "eval_allNLI-dev_euclidean_accuracy": 0.671875,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 5.084325790405273,
+      "eval_allNLI-dev_euclidean_ap": 0.41769294415599645,
+      "eval_allNLI-dev_euclidean_f1": 0.5404339250493098,
+      "eval_allNLI-dev_euclidean_f1_threshold": 11.333902359008789,
+      "eval_allNLI-dev_euclidean_precision": 0.4101796407185629,
+      "eval_allNLI-dev_euclidean_recall": 0.791907514450867,
+      "eval_allNLI-dev_manhattan_accuracy": 0.671875,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 114.41839599609375,
+      "eval_allNLI-dev_manhattan_ap": 0.4272864144491257,
+      "eval_allNLI-dev_manhattan_f1": 0.5384615384615384,
+      "eval_allNLI-dev_manhattan_f1_threshold": 226.82566833496094,
+      "eval_allNLI-dev_manhattan_precision": 0.3941018766756032,
+      "eval_allNLI-dev_manhattan_recall": 0.8497109826589595,
+      "eval_allNLI-dev_max_accuracy": 0.671875,
+      "eval_allNLI-dev_max_accuracy_threshold": 518.88671875,
+      "eval_allNLI-dev_max_ap": 0.4272864144491257,
+      "eval_allNLI-dev_max_f1": 0.5404339250493098,
+      "eval_allNLI-dev_max_f1_threshold": 323.9651184082031,
+      "eval_allNLI-dev_max_precision": 0.4101796407185629,
+      "eval_allNLI-dev_max_recall": 0.953757225433526,
+      "eval_loss": 0.7178329229354858,
+      "eval_runtime": 56.8366,
+      "eval_samples_per_second": 26.497,
+      "eval_sequential_score": 0.6679289689394285,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.2589065791031549,
+      "eval_sts-test_pearson_dot": 0.28511212645281553,
+      "eval_sts-test_pearson_euclidean": 0.2585939429800171,
+      "eval_sts-test_pearson_manhattan": 0.27236487282828553,
+      "eval_sts-test_pearson_max": 0.28511212645281553,
+      "eval_sts-test_spearman_cosine": 0.31323211323674593,
+      "eval_sts-test_spearman_dot": 0.2967423026930272,
+      "eval_sts-test_spearman_euclidean": 0.2833925986586202,
+      "eval_sts-test_spearman_manhattan": 0.29656486394161036,
+      "eval_sts-test_spearman_max": 0.31323211323674593,
+      "step": 55
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 546,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 55,
+  "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": 640,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-55/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b50a4a92b5eb29f5d9b19f9e1060fdd6af0a02268cb16ba6bb85ab82bb7ddd6b
+size 5752