Training in progress, step 208, checkpoint

checkpoint-208/1_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-208/README.md

@@ -0,0 +1,739 @@
+---
+base_model: bobox/DeBERTa-small-ST-v1-test-step3
+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
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:120849
+- loss:CachedGISTEmbedLoss
+widget:
+- source_sentence: '"Today I lost those who for 24 years I called...my family," said
+    Enes Kanter of the Oklahoma City Thunder.
+
+    Turkish President Recep Tayyip Erdogan blames Mr Gulen for inciting a failed coup
+    last month and is seeking the cleric''s extradition to Turkey.
+
+    Mr Gulen, who has a large following, denies being involved in the coup.
+
+    Kanter''s father, Mehmet, disowned his son in a letter published on Monday by
+    Sabah, a pro-government newspaper.
+
+    Mehmet Kanter wrote his son had been "hypnotised" by the Gulen movement.
+
+    "With a feeling of shame I apologise to our president and the Turkish people for
+    having such a son," the letter said.
+
+    Q&A on the Gulen movement
+
+    Mr Gulen is regarded by followers as a spiritual leader and sometimes described
+    as Turkey''s second most powerful man.
+
+    Enes Kanter has been a vocal supporter of Mr Gulen on Twitter.
+
+    The movement - known in Turkey as Hizmet, or service - runs schools all over Turkey
+    and around the world, including in Turkic former Soviet republics, Muslim countries
+    such as Pakistan and Western nations including Romania and the US, where it runs
+    more than 100 schools.
+
+    In May 2016, the Turkish government formally declared the Gulen movement a terrorist
+    organisation.
+
+    After the failed coup, suspected Gulen supporters in Turkey were purged in a wave
+    of arrests.
+
+    Western nations have been critical of the government''s response to the coup.
+    US officials have said they will extradite Mr Gulen only if Turkey provides evidence.'
+  sentences:
+  - 'The Thinker | Rodin Museum H. 189 cm ; W. 98 cm ; D. 140 cm S.2838 When conceived
+    in 1880 in its original size (approx. 70 cm) as the crowning element of The Gates
+    of Hell , seated on the tympanum , The Thinker was entitled The Poet. He represented
+    Dante, author of the Divine Comedy which had inspired The Gates, leaning forward
+    to observe the circles of Hell, while meditating on his work. The Thinker was
+    therefore initially both a being with a tortured body, almost a damned soul, and
+    a free-thinking man, determined to transcend his suffering through poetry. The
+    pose of this figure owes much to Carpeaux’s Ugolino (1861) and to the seated portrait
+    of Lorenzo de’ Medici carved by Michelangelo (1526-31).   While remaining in place
+    on the monumental Gates of Hell, The Thinker was exhibited individually in 1888
+    and thus became an independent work. Enlarged in 1904, its colossal version proved
+    even more popular: this image of a man lost in thought, but whose powerful body
+    suggests a great capacity for action, has became one of the most celebrated sculptures
+    ever known. Numerous casts exist worldwide, including the one now in the gardens
+    of the Musée Rodin, a gift to the City of Paris installed outside the Panthéon
+    in 1906, and another in the gardens of Rodin’s house in Meudon, on the tomb of
+    the sculptor and his wife. George Bernard Shaw in the Pose of "The Thinker" Rodin,
+    the Monument to Victor Hugo and The Thinker Rodin''s "Thinker" in Dr Linde''s
+    Garden in Lübeck'
+  - An American basketball player has cut ties with his Turkish family over his support
+    for Pennsylvania-based preacher Fethullah Gulen.
+  - Police are investigating a death at a bus stop in Fife.
+- source_sentence: Two adorable birds perched on a piece of bamboo.
+  sentences:
+  - Two birds are sitting perched on a tree limb
+  - A young boy with a spoon looking at a birthday cupcake.
+  - As part of his attempt to turn the Austrian right , Dessaix ordered a battalion
+    to move along the Aire stream near Tairier and Crache .
+- source_sentence: how do venom snake keepers make money?
+  sentences:
+  - "The USDA regulates who can buy and sell snake venom. It is very important to\
+    \ learn about these regulations so that you can operate properly. On average,\
+    \ snake milkers make around $2,500 per month, but snake venom is an expensive\
+    \ market. One gram of certain types of snake venom can sell for $2,000.If you\
+    \ are crazy enough to capture, milk, and breed snakes, please take the precaution\
+    \ to wear protective clothing and always have antivenom close at hand.nake milkers\
+    \ have an insane job. They â\x80\x9Cmilkâ\x80\x9D snakes for their venom. This\
+    \ means that every single day, a snake milker handles deadly, venomous snakes.\
+    \ Itâ\x80\x99s a hands on job where you put your fingers millimeters away from\
+    \ the sharp, fangs of asps, vipers, cobras, corals, mambas, kraits, and rattlesnakes."
+  - a greenhouse is used to protect plants by keeping them warm
+  - Nashville Mayor Megan Barry has said her 22-year-old son died of what appeared
+    to be a drug overdose, according to a family statement.
+- source_sentence: Adult bees include workers, a queen and what other type?
+  sentences:
+  - "matter vibrating can cause sound. Thus, sound is a wave in air . \n matter vibrating\
+    \ can cause a wave in air"
+  - His references in electronic music are Todd Terry , Armand Van Helden , Roger
+    Sanchez , Tiesto and the Epic Sax Guy.
+  - 'Look at the honeybees in Figure below . Honeybees live in colonies that may consist
+    of thousands of individual bees. Generally, there are three types of adult bees
+    in a colony: workers, a queen, and drones.'
+- source_sentence: can an object have constant non zero velocity and changing acceleration?
+  sentences:
+  - when an animal sheds its fur , its fur becomes less dense
+  - Acceleration is defined as the time derivative of the velocity; if the velocity
+    is unchanging the acceleration is zero. Velocity is a vector, speed is a scalar
+    magnitude of the vector. If the velocity vector changes direction you can have
+    constant speed (not velocity) with a non-zero acceleration.
+  - Acne treatment is individual and customized to the type of acne you have. On average,
+    mild acne responds in 1-2 months, moderate acne responds in 2-4 months and severe
+    acne can take 4-6 months to clear, granted that the most effective measures can
+    be used.
+model-index:
+- name: SentenceTransformer based on bobox/DeBERTa-small-ST-v1-test-step3
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.8742827064396023
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.9022449488282648
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.9078074095863298
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.9048224424793636
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.9072144921384091
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.9046033403035915
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8524658058205945
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8547093534556153
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.9078074095863298
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.9048224424793636
+      name: Spearman Max
+---
+
+# SentenceTransformer based on bobox/DeBERTa-small-ST-v1-test-step3
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [bobox/DeBERTa-small-ST-v1-test-step3](https://huggingface.co/bobox/DeBERTa-small-ST-v1-test-step3) 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:** [bobox/DeBERTa-small-ST-v1-test-step3](https://huggingface.co/bobox/DeBERTa-small-ST-v1-test-step3) <!-- at revision df9aaa75fe0c2791e5ed35ff33de1689d9a5f5ff -->
+- **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-v1-test-UnifiedDatasets-checkpoints-tmp")
+# Run inference
+sentences = [
+    'can an object have constant non zero velocity and changing acceleration?',
+    'Acceleration is defined as the time derivative of the velocity; if the velocity is unchanging the acceleration is zero. Velocity is a vector, speed is a scalar magnitude of the vector. If the velocity vector changes direction you can have constant speed (not velocity) with a non-zero acceleration.',
+    'Acne treatment is individual and customized to the type of acne you have. On average, mild acne responds in 1-2 months, moderate acne responds in 2-4 months and severe acne can take 4-6 months to clear, granted that the most effective measures can be used.',
+]
+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      | 0.8743     |
+| **spearman_cosine** | **0.9022** |
+| pearson_manhattan   | 0.9078     |
+| spearman_manhattan  | 0.9048     |
+| pearson_euclidean   | 0.9072     |
+| spearman_euclidean  | 0.9046     |
+| pearson_dot         | 0.8525     |
+| spearman_dot        | 0.8547     |
+| pearson_max         | 0.9078     |
+| spearman_max        | 0.9048     |
+
+<!--
+## 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: 120,849 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: 32.01 tokens</li><li>max: 336 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 60.45 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | sentence1                                                                        | sentence2                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+  |:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>A lady working in a kitchen with several different types of dishes.</code> | <code>A woman is cooking and cleaning in her kitchen.</code>                                                                                                                                                                                                                                                                                                                                                                                         |
+  | <code>can you renew your licence online sa?</code>                               | <code>You can renew your licence online for as long as your photo is valid. Renew your driver's licence online with a mySA GOV account. With a mySA GOV account, you can access a legally compliant digital licence through the mySA GOV app.</code>                                                                                                                                                                                                 |
+  | <code>how can coconut oil lower cholesterol</code>                               | <code>It has been shown that lauric acid increases the good HDL cholesterol in the blood to help improve cholesterol ratio levels. Coconut oil lowers cholesterol by promoting its conversion to pregnenolone, a molecule that is a precursor to many of the hormones our bodies need. Coconut can help restore normal thyroid function. When the thyroid does not function optimally, it can contribute to higher levels of bad cholesterol.</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: 3,052 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: 4 tokens</li><li>mean: 32.91 tokens</li><li>max: 342 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 60.3 tokens</li><li>max: 408 tokens</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 | sentence2                                                                                                                                                                                                                                                                                          |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>The body was found in the River Avon in Bath, Avon and Somerset Police said.<br>Officers said although formal identification had not yet taken place, Henry Burke's family had been told.<br>Earlier officers said they were looking for Mr Burke, who was last seen leaving a nightclub in George Street late on Thursday.<br>A force spokesman said the death was being treated as unexplained and inquiries were continuing.<br>Mr Burke's girlfriend, Em Comley, earlier said he had been texting her "throughout the night" but then the messages suddenly stopped just after midnight.</code> | <code>A man's body has been found in a river after search and rescue teams were called in to try and find a missing 19-year-old student.</code>                                                                                                                                                    |
+  | <code>what happens when the president of united states is impeached?</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | <code>Parliament votes on the proposal by secret ballot, and if two thirds of all representatives agree, the president is impeached. Once impeached, the president's powers are suspended, and the Constitutional Court decides whether or not the President should be removed from office.</code> |
+  | <code>What can feed at more than one trophic level?</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | <code>Many consumers feed at more than one trophic level.. Nuts are also consumed by deer, turkey, foxes, wood ducks and squirrels. <br> wood ducks can feed at more than one trophic level</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`: 960
+- `per_device_eval_batch_size`: 128
+- `learning_rate`: 3.5e-05
+- `weight_decay`: 0.0001
+- `num_train_epochs`: 2
+- `lr_scheduler_type`: cosine_with_min_lr
+- `lr_scheduler_kwargs`: {'num_cycles': 0.5, 'min_lr': 5.833333333333333e-06}
+- `warmup_ratio`: 0.25
+- `save_safetensors`: False
+- `fp16`: True
+- `push_to_hub`: True
+- `hub_model_id`: bobox/DeBERTa-small-ST-v1-test-UnifiedDatasets-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`: 960
+- `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`: 3.5e-05
+- `weight_decay`: 0.0001
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 2
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine_with_min_lr
+- `lr_scheduler_kwargs`: {'num_cycles': 0.5, 'min_lr': 5.833333333333333e-06}
+- `warmup_ratio`: 0.25
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: False
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: True
+- `resume_from_checkpoint`: None
+- `hub_model_id`: bobox/DeBERTa-small-ST-v1-test-UnifiedDatasets-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
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step | Training Loss | loss   | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:------:|:------------------------:|
+| 0.0079 | 1    | 0.404         | -      | -                        |
+| 0.0159 | 2    | 0.3185        | -      | -                        |
+| 0.0238 | 3    | 0.2821        | -      | -                        |
+| 0.0317 | 4    | 0.4036        | -      | -                        |
+| 0.0397 | 5    | 0.3442        | 0.1253 | 0.9078                   |
+| 0.0476 | 6    | 0.4145        | -      | -                        |
+| 0.0556 | 7    | 0.4224        | -      | -                        |
+| 0.0635 | 8    | 0.4048        | -      | -                        |
+| 0.0714 | 9    | 0.3899        | -      | -                        |
+| 0.0794 | 10   | 0.4127        | 0.1237 | 0.9079                   |
+| 0.0873 | 11   | 0.3496        | -      | -                        |
+| 0.0952 | 12   | 0.3731        | -      | -                        |
+| 0.1032 | 13   | 0.3929        | -      | -                        |
+| 0.1111 | 14   | 0.2957        | -      | -                        |
+| 0.1190 | 15   | 0.3324        | 0.1206 | 0.9083                   |
+| 0.1270 | 16   | 0.3341        | -      | -                        |
+| 0.1349 | 17   | 0.3466        | -      | -                        |
+| 0.1429 | 18   | 0.3558        | -      | -                        |
+| 0.1508 | 19   | 0.2634        | -      | -                        |
+| 0.1587 | 20   | 0.3095        | 0.1156 | 0.9088                   |
+| 0.1667 | 21   | 0.2973        | -      | -                        |
+| 0.1746 | 22   | 0.2884        | -      | -                        |
+| 0.1825 | 23   | 0.3697        | -      | -                        |
+| 0.1905 | 24   | 0.2683        | -      | -                        |
+| 0.1984 | 25   | 0.3026        | 0.1096 | 0.9088                   |
+| 0.2063 | 26   | 0.2441        | -      | -                        |
+| 0.2143 | 27   | 0.3145        | -      | -                        |
+| 0.2222 | 28   | 0.3119        | -      | -                        |
+| 0.2302 | 29   | 0.2766        | -      | -                        |
+| 0.2381 | 30   | 0.3343        | 0.1054 | 0.9084                   |
+| 0.2460 | 31   | 0.344         | -      | -                        |
+| 0.2540 | 32   | 0.3005        | -      | -                        |
+| 0.2619 | 33   | 0.2526        | -      | -                        |
+| 0.2698 | 34   | 0.2422        | -      | -                        |
+| 0.2778 | 35   | 0.3447        | 0.1022 | 0.9072                   |
+| 0.2857 | 36   | 0.2809        | -      | -                        |
+| 0.2937 | 37   | 0.2836        | -      | -                        |
+| 0.3016 | 38   | 0.2878        | -      | -                        |
+| 0.3095 | 39   | 0.2738        | -      | -                        |
+| 0.3175 | 40   | 0.2806        | 0.1003 | 0.9065                   |
+| 0.3254 | 41   | 0.2797        | -      | -                        |
+| 0.3333 | 42   | 0.3217        | -      | -                        |
+| 0.3413 | 43   | 0.2544        | -      | -                        |
+| 0.3492 | 44   | 0.3203        | -      | -                        |
+| 0.3571 | 45   | 0.2987        | 0.0990 | 0.9064                   |
+| 0.3651 | 46   | 0.2765        | -      | -                        |
+| 0.3730 | 47   | 0.2716        | -      | -                        |
+| 0.3810 | 48   | 0.3726        | -      | -                        |
+| 0.3889 | 49   | 0.2963        | -      | -                        |
+| 0.3968 | 50   | 0.2784        | 0.0952 | 0.9072                   |
+| 0.4048 | 51   | 0.2437        | -      | -                        |
+| 0.4127 | 52   | 0.2258        | -      | -                        |
+| 0.4206 | 53   | 0.2821        | -      | -                        |
+| 0.4286 | 54   | 0.249         | -      | -                        |
+| 0.4365 | 55   | 0.2813        | 0.0928 | 0.9080                   |
+| 0.4444 | 56   | 0.3003        | -      | -                        |
+| 0.4524 | 57   | 0.2812        | -      | -                        |
+| 0.4603 | 58   | 0.2619        | -      | -                        |
+| 0.4683 | 59   | 0.299         | -      | -                        |
+| 0.4762 | 60   | 0.2706        | 0.0927 | 0.9088                   |
+| 0.4841 | 61   | 0.297         | -      | -                        |
+| 0.4921 | 62   | 0.2906        | -      | -                        |
+| 0.5    | 63   | 0.2914        | -      | -                        |
+| 0.5079 | 64   | 0.2669        | -      | -                        |
+| 0.5159 | 65   | 0.2723        | 0.0946 | 0.9093                   |
+| 0.5238 | 66   | 0.3194        | -      | -                        |
+| 0.5317 | 67   | 0.3585        | -      | -                        |
+| 0.5397 | 68   | 0.2843        | -      | -                        |
+| 0.5476 | 69   | 0.1916        | -      | -                        |
+| 0.5556 | 70   | 0.351         | 0.0971 | 0.9104                   |
+| 0.5635 | 71   | 0.3105        | -      | -                        |
+| 0.5714 | 72   | 0.2847        | -      | -                        |
+| 0.5794 | 73   | 0.2641        | -      | -                        |
+| 0.5873 | 74   | 0.3305        | -      | -                        |
+| 0.5952 | 75   | 0.2461        | 0.0965 | 0.9096                   |
+| 0.6032 | 76   | 0.259         | -      | -                        |
+| 0.6111 | 77   | 0.2506        | -      | -                        |
+| 0.6190 | 78   | 0.2832        | -      | -                        |
+| 0.6270 | 79   | 0.3322        | -      | -                        |
+| 0.6349 | 80   | 0.2533        | 0.1001 | 0.9089                   |
+| 0.6429 | 81   | 0.2349        | -      | -                        |
+| 0.6508 | 82   | 0.2748        | -      | -                        |
+| 0.6587 | 83   | 0.223         | -      | -                        |
+| 0.6667 | 84   | 0.2416        | -      | -                        |
+| 0.6746 | 85   | 0.2637        | 0.1034 | 0.9082                   |
+| 0.6825 | 86   | 0.2856        | -      | -                        |
+| 0.6905 | 87   | 0.2476        | -      | -                        |
+| 0.6984 | 88   | 0.2427        | -      | -                        |
+| 0.7063 | 89   | 0.2614        | -      | -                        |
+| 0.7143 | 90   | 0.26          | 0.1032 | 0.9088                   |
+| 0.7222 | 91   | 0.1862        | -      | -                        |
+| 0.7302 | 92   | 0.267         | -      | -                        |
+| 0.7381 | 93   | 0.2175        | -      | -                        |
+| 0.7460 | 94   | 0.2079        | -      | -                        |
+| 0.7540 | 95   | 0.2562        | 0.0999 | 0.9086                   |
+| 0.7619 | 96   | 0.2516        | -      | -                        |
+| 0.7698 | 97   | 0.2956        | -      | -                        |
+| 0.7778 | 98   | 0.2733        | -      | -                        |
+| 0.7857 | 99   | 0.2919        | -      | -                        |
+| 0.7937 | 100  | 0.2997        | 0.1032 | 0.9069                   |
+| 0.8016 | 101  | 0.2276        | -      | -                        |
+| 0.8095 | 102  | 0.2582        | -      | -                        |
+| 0.8175 | 103  | 0.2559        | -      | -                        |
+| 0.8254 | 104  | 0.2864        | -      | -                        |
+| 0.8333 | 105  | 0.2839        | 0.1074 | 0.9076                   |
+| 0.8413 | 106  | 0.2549        | -      | -                        |
+| 0.8492 | 107  | 0.2826        | -      | -                        |
+| 0.8571 | 108  | 0.2334        | -      | -                        |
+| 0.8651 | 109  | 0.2632        | -      | -                        |
+| 0.8730 | 110  | 0.2255        | 0.1090 | 0.9056                   |
+| 0.8810 | 111  | 0.2589        | -      | -                        |
+| 0.8889 | 112  | 0.2569        | -      | -                        |
+| 0.8968 | 113  | 0.2797        | -      | -                        |
+| 0.9048 | 114  | 0.2742        | -      | -                        |
+| 0.9127 | 115  | 0.2295        | 0.1070 | 0.9014                   |
+| 0.9206 | 116  | 0.2047        | -      | -                        |
+| 0.9286 | 117  | 0.2577        | -      | -                        |
+| 0.9365 | 118  | 0.2614        | -      | -                        |
+| 0.9444 | 119  | 0.2722        | -      | -                        |
+| 0.9524 | 120  | 0.1927        | 0.1024 | 0.9008                   |
+| 0.9603 | 121  | 0.2649        | -      | -                        |
+| 0.9683 | 122  | 0.2386        | -      | -                        |
+| 0.9762 | 123  | 0.2801        | -      | -                        |
+| 0.9841 | 124  | 0.2583        | -      | -                        |
+| 0.9921 | 125  | 0.3076        | 0.0949 | 0.9016                   |
+| 1.0    | 126  | 0.5477        | -      | -                        |
+| 1.0079 | 127  | 0.0031        | -      | -                        |
+| 1.0159 | 128  | 0.0           | -      | -                        |
+| 1.0238 | 129  | 0.0           | -      | -                        |
+| 1.0317 | 130  | 0.0           | 0.0955 | 0.9021                   |
+| 1.0397 | 131  | 0.0           | -      | -                        |
+| 1.0476 | 132  | 0.0           | -      | -                        |
+| 1.0556 | 133  | 0.0           | -      | -                        |
+| 1.0635 | 134  | 0.0           | -      | -                        |
+| 1.0714 | 135  | 0.0           | 0.0968 | 0.9023                   |
+| 1.0794 | 136  | 0.0           | -      | -                        |
+| 1.0873 | 137  | 0.0           | -      | -                        |
+| 1.0952 | 138  | 0.0           | -      | -                        |
+| 1.1032 | 139  | 0.0           | -      | -                        |
+| 1.1111 | 140  | 0.0           | 0.0978 | 0.9024                   |
+| 1.1190 | 141  | 0.0           | -      | -                        |
+| 1.1270 | 142  | 0.0           | -      | -                        |
+| 1.1349 | 143  | 0.0           | -      | -                        |
+| 1.1429 | 144  | 0.0           | -      | -                        |
+| 1.1508 | 145  | 0.0           | 0.0986 | 0.9024                   |
+| 1.1587 | 146  | 0.0           | -      | -                        |
+| 1.1667 | 147  | 0.0           | -      | -                        |
+| 1.1746 | 148  | 0.0           | -      | -                        |
+| 1.1825 | 149  | 0.0           | -      | -                        |
+| 1.1905 | 150  | 0.0           | 0.0991 | 0.9023                   |
+| 1.1984 | 151  | 0.0           | -      | -                        |
+| 1.2063 | 152  | 0.0           | -      | -                        |
+| 1.2143 | 153  | 0.0           | -      | -                        |
+| 1.2222 | 154  | 0.0           | -      | -                        |
+| 1.2302 | 155  | 0.0           | 0.0994 | 0.9023                   |
+| 1.2381 | 156  | 0.0           | -      | -                        |
+| 1.2460 | 157  | 0.0           | -      | -                        |
+| 1.2540 | 158  | 0.0           | -      | -                        |
+| 1.2619 | 159  | 0.0           | -      | -                        |
+| 1.2698 | 160  | 0.0           | 0.0995 | 0.9023                   |
+| 1.2778 | 161  | 0.0           | -      | -                        |
+| 1.2857 | 162  | 0.0           | -      | -                        |
+| 1.2937 | 163  | 0.0           | -      | -                        |
+| 1.3016 | 164  | 0.0           | -      | -                        |
+| 1.3095 | 165  | 0.0           | 0.0996 | 0.9023                   |
+| 1.3175 | 166  | 0.0           | -      | -                        |
+| 1.3254 | 167  | 0.0           | -      | -                        |
+| 1.3333 | 168  | 0.0           | -      | -                        |
+| 1.3413 | 169  | 0.0           | -      | -                        |
+| 1.3492 | 170  | 0.0           | 0.0997 | 0.9023                   |
+| 1.3571 | 171  | 0.0           | -      | -                        |
+| 1.3651 | 172  | 0.0           | -      | -                        |
+| 1.3730 | 173  | 0.0           | -      | -                        |
+| 1.3810 | 174  | 0.0           | -      | -                        |
+| 1.3889 | 175  | 0.0           | 0.0997 | 0.9023                   |
+| 1.3968 | 176  | 0.0           | -      | -                        |
+| 1.4048 | 177  | 0.0           | -      | -                        |
+| 1.4127 | 178  | 0.0           | -      | -                        |
+| 1.4206 | 179  | 0.0           | -      | -                        |
+| 1.4286 | 180  | 0.0           | 0.0997 | 0.9023                   |
+| 1.4365 | 181  | 0.0           | -      | -                        |
+| 1.4444 | 182  | 0.0           | -      | -                        |
+| 1.4524 | 183  | 0.0           | -      | -                        |
+| 1.4603 | 184  | 0.0           | -      | -                        |
+| 1.4683 | 185  | 0.0           | 0.0998 | 0.9023                   |
+| 1.4762 | 186  | 0.0           | -      | -                        |
+| 1.4841 | 187  | 0.0           | -      | -                        |
+| 1.4921 | 188  | 0.0           | -      | -                        |
+| 1.5    | 189  | 0.0           | -      | -                        |
+| 1.5079 | 190  | 0.0           | 0.0998 | 0.9023                   |
+| 1.5159 | 191  | 0.0           | -      | -                        |
+| 1.5238 | 192  | 0.0           | -      | -                        |
+| 1.5317 | 193  | 0.0           | -      | -                        |
+| 1.5397 | 194  | 0.0           | -      | -                        |
+| 1.5476 | 195  | 0.0           | 0.0998 | 0.9022                   |
+| 1.5556 | 196  | 0.0           | -      | -                        |
+| 1.5635 | 197  | 0.0           | -      | -                        |
+| 1.5714 | 198  | 0.0           | -      | -                        |
+| 1.5794 | 199  | 0.0           | -      | -                        |
+| 1.5873 | 200  | 0.0           | 0.0998 | 0.9022                   |
+| 1.5952 | 201  | 0.0           | -      | -                        |
+| 1.6032 | 202  | 0.0           | -      | -                        |
+| 1.6111 | 203  | 0.0           | -      | -                        |
+| 1.6190 | 204  | 0.0           | -      | -                        |
+| 1.6270 | 205  | 0.0           | 0.0998 | 0.9022                   |
+| 1.6349 | 206  | 0.0           | -      | -                        |
+| 1.6429 | 207  | 0.0           | -      | -                        |
+| 1.6508 | 208  | 0.0           | -      | -                        |
+
+</details>
+
+### 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-208/added_tokens.json

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

checkpoint-208/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "bobox/DeBERTa-small-ST-v1-test-step3",
+  "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-208/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-208/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-208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f3b86ff4c3efcebfc399dfd271fd1639a9b55c164e61648b7fc7122690538a5
+size 1130520122

checkpoint-208/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8260eefc98e996b63b68e71176685983c92c02b4f58e4ee350cdaf99e9dd71
+size 565251810

checkpoint-208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2512fc08615ffa6c7bb0033e5d7a5447bc04a8c002bfa327e13e989292c25b28
+size 14244

checkpoint-208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38510ab06b46572fec36821fc3b8a60274b14209e591c36397ec5ec60b192e9e
+size 1064

checkpoint-208/sentence_bert_config.json

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

checkpoint-208/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-208/spm.model

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

checkpoint-208/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "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]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

checkpoint-208/trainer_state.json

@@ -0,0 +1,2227 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6507936507936507,
+  "eval_steps": 5,
+  "global_step": 208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007936507936507936,
+      "grad_norm": 3.5297670364379883,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.404,
+      "step": 1
+    },
+    {
+      "epoch": 0.015873015873015872,
+      "grad_norm": 3.6838796138763428,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.3185,
+      "step": 2
+    },
+    {
+      "epoch": 0.023809523809523808,
+      "grad_norm": 3.5556721687316895,
+      "learning_rate": 1.6666666666666665e-06,
+      "loss": 0.2821,
+      "step": 3
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 3.922109842300415,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.4036,
+      "step": 4
+    },
+    {
+      "epoch": 0.03968253968253968,
+      "grad_norm": 3.9366657733917236,
+      "learning_rate": 2.7777777777777775e-06,
+      "loss": 0.3442,
+      "step": 5
+    },
+    {
+      "epoch": 0.03968253968253968,
+      "eval_loss": 0.12529698014259338,
+      "eval_runtime": 113.8002,
+      "eval_samples_per_second": 26.819,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.886081184413048,
+      "eval_sts-test_pearson_dot": 0.8767533438290611,
+      "eval_sts-test_pearson_euclidean": 0.9080817963557108,
+      "eval_sts-test_pearson_manhattan": 0.9087794191320873,
+      "eval_sts-test_pearson_max": 0.9087794191320873,
+      "eval_sts-test_spearman_cosine": 0.9077787555581409,
+      "eval_sts-test_spearman_dot": 0.8792746633711961,
+      "eval_sts-test_spearman_euclidean": 0.9039925750881216,
+      "eval_sts-test_spearman_manhattan": 0.904489537845873,
+      "eval_sts-test_spearman_max": 0.9077787555581409,
+      "step": 5
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 3.8135547637939453,
+      "learning_rate": 3.333333333333333e-06,
+      "loss": 0.4145,
+      "step": 6
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 4.132374286651611,
+      "learning_rate": 3.888888888888889e-06,
+      "loss": 0.4224,
+      "step": 7
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 3.9953386783599854,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.4048,
+      "step": 8
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 4.023675918579102,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 0.3899,
+      "step": 9
+    },
+    {
+      "epoch": 0.07936507936507936,
+      "grad_norm": 3.854191780090332,
+      "learning_rate": 5.555555555555555e-06,
+      "loss": 0.4127,
+      "step": 10
+    },
+    {
+      "epoch": 0.07936507936507936,
+      "eval_loss": 0.12369368970394135,
+      "eval_runtime": 113.6707,
+      "eval_samples_per_second": 26.849,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8860118050647048,
+      "eval_sts-test_pearson_dot": 0.8760605933678182,
+      "eval_sts-test_pearson_euclidean": 0.9086480781293332,
+      "eval_sts-test_pearson_manhattan": 0.9092897840847158,
+      "eval_sts-test_pearson_max": 0.9092897840847158,
+      "eval_sts-test_spearman_cosine": 0.9078577415344969,
+      "eval_sts-test_spearman_dot": 0.8791339654053815,
+      "eval_sts-test_spearman_euclidean": 0.9047648028546915,
+      "eval_sts-test_spearman_manhattan": 0.9052383607027356,
+      "eval_sts-test_spearman_max": 0.9078577415344969,
+      "step": 10
+    },
+    {
+      "epoch": 0.0873015873015873,
+      "grad_norm": 3.8079540729522705,
+      "learning_rate": 6.11111111111111e-06,
+      "loss": 0.3496,
+      "step": 11
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 3.929018259048462,
+      "learning_rate": 6.666666666666666e-06,
+      "loss": 0.3731,
+      "step": 12
+    },
+    {
+      "epoch": 0.10317460317460317,
+      "grad_norm": 4.284013271331787,
+      "learning_rate": 7.222222222222221e-06,
+      "loss": 0.3929,
+      "step": 13
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 3.3490402698516846,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 0.2957,
+      "step": 14
+    },
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": 3.553280830383301,
+      "learning_rate": 8.333333333333332e-06,
+      "loss": 0.3324,
+      "step": 15
+    },
+    {
+      "epoch": 0.11904761904761904,
+      "eval_loss": 0.12056715041399002,
+      "eval_runtime": 113.718,
+      "eval_samples_per_second": 26.838,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8856265458568289,
+      "eval_sts-test_pearson_dot": 0.8743050518330721,
+      "eval_sts-test_pearson_euclidean": 0.9095228583162331,
+      "eval_sts-test_pearson_manhattan": 0.9101600217218586,
+      "eval_sts-test_pearson_max": 0.9101600217218586,
+      "eval_sts-test_spearman_cosine": 0.908261263658463,
+      "eval_sts-test_spearman_dot": 0.87867141636764,
+      "eval_sts-test_spearman_euclidean": 0.9060734192402989,
+      "eval_sts-test_spearman_manhattan": 0.9066336155303966,
+      "eval_sts-test_spearman_max": 0.908261263658463,
+      "step": 15
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 3.6310322284698486,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.3341,
+      "step": 16
+    },
+    {
+      "epoch": 0.1349206349206349,
+      "grad_norm": 3.6535122394561768,
+      "learning_rate": 9.444444444444443e-06,
+      "loss": 0.3466,
+      "step": 17
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 3.6199331283569336,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 0.3558,
+      "step": 18
+    },
+    {
+      "epoch": 0.15079365079365079,
+      "grad_norm": 3.089895248413086,
+      "learning_rate": 1.0555555555555554e-05,
+      "loss": 0.2634,
+      "step": 19
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 3.320916175842285,
+      "learning_rate": 1.111111111111111e-05,
+      "loss": 0.3095,
+      "step": 20
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "eval_loss": 0.11563990265130997,
+      "eval_runtime": 113.5377,
+      "eval_samples_per_second": 26.881,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8848740042612456,
+      "eval_sts-test_pearson_dot": 0.8724689429546052,
+      "eval_sts-test_pearson_euclidean": 0.9104294765782397,
+      "eval_sts-test_pearson_manhattan": 0.9111381492292419,
+      "eval_sts-test_pearson_max": 0.9111381492292419,
+      "eval_sts-test_spearman_cosine": 0.9087803335393421,
+      "eval_sts-test_spearman_dot": 0.8777188410176626,
+      "eval_sts-test_spearman_euclidean": 0.9069791847708608,
+      "eval_sts-test_spearman_manhattan": 0.9078148698260838,
+      "eval_sts-test_spearman_max": 0.9087803335393421,
+      "step": 20
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 3.0193159580230713,
+      "learning_rate": 1.1666666666666665e-05,
+      "loss": 0.2973,
+      "step": 21
+    },
+    {
+      "epoch": 0.1746031746031746,
+      "grad_norm": 3.3553476333618164,
+      "learning_rate": 1.222222222222222e-05,
+      "loss": 0.2884,
+      "step": 22
+    },
+    {
+      "epoch": 0.18253968253968253,
+      "grad_norm": 3.5176496505737305,
+      "learning_rate": 1.2777777777777775e-05,
+      "loss": 0.3697,
+      "step": 23
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 3.2073943614959717,
+      "learning_rate": 1.3333333333333332e-05,
+      "loss": 0.2683,
+      "step": 24
+    },
+    {
+      "epoch": 0.1984126984126984,
+      "grad_norm": 3.2101964950561523,
+      "learning_rate": 1.3888888888888886e-05,
+      "loss": 0.3026,
+      "step": 25
+    },
+    {
+      "epoch": 0.1984126984126984,
+      "eval_loss": 0.10958973318338394,
+      "eval_runtime": 113.6214,
+      "eval_samples_per_second": 26.861,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8832622086480311,
+      "eval_sts-test_pearson_dot": 0.8697582354953435,
+      "eval_sts-test_pearson_euclidean": 0.9107566690862425,
+      "eval_sts-test_pearson_manhattan": 0.9115546986654615,
+      "eval_sts-test_pearson_max": 0.9115546986654615,
+      "eval_sts-test_spearman_cosine": 0.9087605087305455,
+      "eval_sts-test_spearman_dot": 0.8760767382321666,
+      "eval_sts-test_spearman_euclidean": 0.9073999361304628,
+      "eval_sts-test_spearman_manhattan": 0.9084107328715103,
+      "eval_sts-test_spearman_max": 0.9087605087305455,
+      "step": 25
+    },
+    {
+      "epoch": 0.20634920634920634,
+      "grad_norm": 2.84037709236145,
+      "learning_rate": 1.4444444444444442e-05,
+      "loss": 0.2441,
+      "step": 26
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 3.3099992275238037,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 0.3145,
+      "step": 27
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 3.061953067779541,
+      "learning_rate": 1.5555555555555555e-05,
+      "loss": 0.3119,
+      "step": 28
+    },
+    {
+      "epoch": 0.23015873015873015,
+      "grad_norm": 3.0163729190826416,
+      "learning_rate": 1.6111111111111108e-05,
+      "loss": 0.2766,
+      "step": 29
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 3.140418291091919,
+      "learning_rate": 1.6666666666666664e-05,
+      "loss": 0.3343,
+      "step": 30
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "eval_loss": 0.10535401105880737,
+      "eval_runtime": 113.5942,
+      "eval_samples_per_second": 26.868,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8819465403802665,
+      "eval_sts-test_pearson_dot": 0.866997957398371,
+      "eval_sts-test_pearson_euclidean": 0.9110501477101954,
+      "eval_sts-test_pearson_manhattan": 0.9119047974126511,
+      "eval_sts-test_pearson_max": 0.9119047974126511,
+      "eval_sts-test_spearman_cosine": 0.9084358383291508,
+      "eval_sts-test_spearman_dot": 0.8727757956894143,
+      "eval_sts-test_spearman_euclidean": 0.9077817538926543,
+      "eval_sts-test_spearman_manhattan": 0.9089103807049453,
+      "eval_sts-test_spearman_max": 0.9089103807049453,
+      "step": 30
+    },
+    {
+      "epoch": 0.24603174603174602,
+      "grad_norm": 3.1329221725463867,
+      "learning_rate": 1.722222222222222e-05,
+      "loss": 0.344,
+      "step": 31
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 2.9861748218536377,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.3005,
+      "step": 32
+    },
+    {
+      "epoch": 0.2619047619047619,
+      "grad_norm": 2.8316733837127686,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.2526,
+      "step": 33
+    },
+    {
+      "epoch": 0.2698412698412698,
+      "grad_norm": 2.8335487842559814,
+      "learning_rate": 1.8888888888888886e-05,
+      "loss": 0.2422,
+      "step": 34
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 3.0785422325134277,
+      "learning_rate": 1.9444444444444442e-05,
+      "loss": 0.3447,
+      "step": 35
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "eval_loss": 0.10223711282014847,
+      "eval_runtime": 113.9847,
+      "eval_samples_per_second": 26.776,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8812001280334643,
+      "eval_sts-test_pearson_dot": 0.8652746969985129,
+      "eval_sts-test_pearson_euclidean": 0.9105701789873448,
+      "eval_sts-test_pearson_manhattan": 0.9116177887236803,
+      "eval_sts-test_pearson_max": 0.9116177887236803,
+      "eval_sts-test_spearman_cosine": 0.9072243769320245,
+      "eval_sts-test_spearman_dot": 0.8716048789351082,
+      "eval_sts-test_spearman_euclidean": 0.9073166540330135,
+      "eval_sts-test_spearman_manhattan": 0.9081332302996223,
+      "eval_sts-test_spearman_max": 0.9081332302996223,
+      "step": 35
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 2.944396734237671,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 0.2809,
+      "step": 36
+    },
+    {
+      "epoch": 0.29365079365079366,
+      "grad_norm": 2.8323400020599365,
+      "learning_rate": 2.0555555555555555e-05,
+      "loss": 0.2836,
+      "step": 37
+    },
+    {
+      "epoch": 0.30158730158730157,
+      "grad_norm": 2.8760273456573486,
+      "learning_rate": 2.1111111111111107e-05,
+      "loss": 0.2878,
+      "step": 38
+    },
+    {
+      "epoch": 0.30952380952380953,
+      "grad_norm": 2.744379758834839,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 0.2738,
+      "step": 39
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 2.8519983291625977,
+      "learning_rate": 2.222222222222222e-05,
+      "loss": 0.2806,
+      "step": 40
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "eval_loss": 0.10033170133829117,
+      "eval_runtime": 113.5147,
+      "eval_samples_per_second": 26.886,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8802115569848467,
+      "eval_sts-test_pearson_dot": 0.8634798448575132,
+      "eval_sts-test_pearson_euclidean": 0.9094188438238102,
+      "eval_sts-test_pearson_manhattan": 0.9105849471172345,
+      "eval_sts-test_pearson_max": 0.9105849471172345,
+      "eval_sts-test_spearman_cosine": 0.9064710789490229,
+      "eval_sts-test_spearman_dot": 0.8693704037025742,
+      "eval_sts-test_spearman_euclidean": 0.9064271779615981,
+      "eval_sts-test_spearman_manhattan": 0.9073247092600637,
+      "eval_sts-test_spearman_max": 0.9073247092600637,
+      "step": 40
+    },
+    {
+      "epoch": 0.3253968253968254,
+      "grad_norm": 2.9139747619628906,
+      "learning_rate": 2.2777777777777776e-05,
+      "loss": 0.2797,
+      "step": 41
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 2.9206557273864746,
+      "learning_rate": 2.333333333333333e-05,
+      "loss": 0.3217,
+      "step": 42
+    },
+    {
+      "epoch": 0.3412698412698413,
+      "grad_norm": 2.755398988723755,
+      "learning_rate": 2.388888888888889e-05,
+      "loss": 0.2544,
+      "step": 43
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 3.0441982746124268,
+      "learning_rate": 2.444444444444444e-05,
+      "loss": 0.3203,
+      "step": 44
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 2.978891611099243,
+      "learning_rate": 2.4999999999999998e-05,
+      "loss": 0.2987,
+      "step": 45
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "eval_loss": 0.09902294725179672,
+      "eval_runtime": 113.6912,
+      "eval_samples_per_second": 26.845,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8796209948380269,
+      "eval_sts-test_pearson_dot": 0.8617122615494917,
+      "eval_sts-test_pearson_euclidean": 0.9092272396432914,
+      "eval_sts-test_pearson_manhattan": 0.9100341993020892,
+      "eval_sts-test_pearson_max": 0.9100341993020892,
+      "eval_sts-test_spearman_cosine": 0.9063911531961779,
+      "eval_sts-test_spearman_dot": 0.867835166929281,
+      "eval_sts-test_spearman_euclidean": 0.9066020658911155,
+      "eval_sts-test_spearman_manhattan": 0.9072894005148261,
+      "eval_sts-test_spearman_max": 0.9072894005148261,
+      "step": 45
+    },
+    {
+      "epoch": 0.36507936507936506,
+      "grad_norm": 2.9183595180511475,
+      "learning_rate": 2.555555555555555e-05,
+      "loss": 0.2765,
+      "step": 46
+    },
+    {
+      "epoch": 0.373015873015873,
+      "grad_norm": 2.960238456726074,
+      "learning_rate": 2.611111111111111e-05,
+      "loss": 0.2716,
+      "step": 47
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 3.23356294631958,
+      "learning_rate": 2.6666666666666663e-05,
+      "loss": 0.3726,
+      "step": 48
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 2.974705457687378,
+      "learning_rate": 2.722222222222222e-05,
+      "loss": 0.2963,
+      "step": 49
+    },
+    {
+      "epoch": 0.3968253968253968,
+      "grad_norm": 2.8041574954986572,
+      "learning_rate": 2.7777777777777772e-05,
+      "loss": 0.2784,
+      "step": 50
+    },
+    {
+      "epoch": 0.3968253968253968,
+      "eval_loss": 0.09521521627902985,
+      "eval_runtime": 113.6139,
+      "eval_samples_per_second": 26.863,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8802451373465323,
+      "eval_sts-test_pearson_dot": 0.8609764645232105,
+      "eval_sts-test_pearson_euclidean": 0.9103012041260427,
+      "eval_sts-test_pearson_manhattan": 0.9108880877390901,
+      "eval_sts-test_pearson_max": 0.9108880877390901,
+      "eval_sts-test_spearman_cosine": 0.9071928272927434,
+      "eval_sts-test_spearman_dot": 0.867374407941995,
+      "eval_sts-test_spearman_euclidean": 0.9083242734345022,
+      "eval_sts-test_spearman_manhattan": 0.9086424996542565,
+      "eval_sts-test_spearman_max": 0.9086424996542565,
+      "step": 50
+    },
+    {
+      "epoch": 0.40476190476190477,
+      "grad_norm": 2.6451456546783447,
+      "learning_rate": 2.8333333333333332e-05,
+      "loss": 0.2437,
+      "step": 51
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 2.7020044326782227,
+      "learning_rate": 2.8888888888888885e-05,
+      "loss": 0.2258,
+      "step": 52
+    },
+    {
+      "epoch": 0.42063492063492064,
+      "grad_norm": 2.7229156494140625,
+      "learning_rate": 2.944444444444444e-05,
+      "loss": 0.2821,
+      "step": 53
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 2.770799398422241,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 0.249,
+      "step": 54
+    },
+    {
+      "epoch": 0.4365079365079365,
+      "grad_norm": 2.762690305709839,
+      "learning_rate": 3.0555555555555554e-05,
+      "loss": 0.2813,
+      "step": 55
+    },
+    {
+      "epoch": 0.4365079365079365,
+      "eval_loss": 0.09280610829591751,
+      "eval_runtime": 113.4966,
+      "eval_samples_per_second": 26.891,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8804507408393794,
+      "eval_sts-test_pearson_dot": 0.8631869703781383,
+      "eval_sts-test_pearson_euclidean": 0.9108211341698824,
+      "eval_sts-test_pearson_manhattan": 0.9114068237803576,
+      "eval_sts-test_pearson_max": 0.9114068237803576,
+      "eval_sts-test_spearman_cosine": 0.9079720810073518,
+      "eval_sts-test_spearman_dot": 0.8709471248951776,
+      "eval_sts-test_spearman_euclidean": 0.9085633794241165,
+      "eval_sts-test_spearman_manhattan": 0.9093315348258998,
+      "eval_sts-test_spearman_max": 0.9093315348258998,
+      "step": 55
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 2.9767086505889893,
+      "learning_rate": 3.111111111111111e-05,
+      "loss": 0.3003,
+      "step": 56
+    },
+    {
+      "epoch": 0.4523809523809524,
+      "grad_norm": 2.816253185272217,
+      "learning_rate": 3.1666666666666666e-05,
+      "loss": 0.2812,
+      "step": 57
+    },
+    {
+      "epoch": 0.4603174603174603,
+      "grad_norm": 2.5184807777404785,
+      "learning_rate": 3.2222222222222216e-05,
+      "loss": 0.2619,
+      "step": 58
+    },
+    {
+      "epoch": 0.46825396825396826,
+      "grad_norm": 2.7500715255737305,
+      "learning_rate": 3.277777777777777e-05,
+      "loss": 0.299,
+      "step": 59
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 2.5309386253356934,
+      "learning_rate": 3.333333333333333e-05,
+      "loss": 0.2706,
+      "step": 60
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "eval_loss": 0.09274312108755112,
+      "eval_runtime": 113.479,
+      "eval_samples_per_second": 26.895,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8814996628266308,
+      "eval_sts-test_pearson_dot": 0.8647617194348185,
+      "eval_sts-test_pearson_euclidean": 0.9116395612568413,
+      "eval_sts-test_pearson_manhattan": 0.9121591417317261,
+      "eval_sts-test_pearson_max": 0.9121591417317261,
+      "eval_sts-test_spearman_cosine": 0.9087614932582961,
+      "eval_sts-test_spearman_dot": 0.8732032149869635,
+      "eval_sts-test_spearman_euclidean": 0.9101066714244602,
+      "eval_sts-test_spearman_manhattan": 0.9099515188012163,
+      "eval_sts-test_spearman_max": 0.9101066714244602,
+      "step": 60
+    },
+    {
+      "epoch": 0.48412698412698413,
+      "grad_norm": 2.7175261974334717,
+      "learning_rate": 3.3888888888888884e-05,
+      "loss": 0.297,
+      "step": 61
+    },
+    {
+      "epoch": 0.49206349206349204,
+      "grad_norm": 2.7492423057556152,
+      "learning_rate": 3.444444444444444e-05,
+      "loss": 0.2906,
+      "step": 62
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.815702438354492,
+      "learning_rate": 3.5e-05,
+      "loss": 0.2914,
+      "step": 63
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 2.9056921005249023,
+      "learning_rate": 3.499798538091195e-05,
+      "loss": 0.2669,
+      "step": 64
+    },
+    {
+      "epoch": 0.5158730158730159,
+      "grad_norm": 2.832461357116699,
+      "learning_rate": 3.4991942080268184e-05,
+      "loss": 0.2723,
+      "step": 65
+    },
+    {
+      "epoch": 0.5158730158730159,
+      "eval_loss": 0.09455278515815735,
+      "eval_runtime": 113.5618,
+      "eval_samples_per_second": 26.875,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8827592572843797,
+      "eval_sts-test_pearson_dot": 0.8655702748779494,
+      "eval_sts-test_pearson_euclidean": 0.9124138196335778,
+      "eval_sts-test_pearson_manhattan": 0.9124858955018784,
+      "eval_sts-test_pearson_max": 0.9124858955018784,
+      "eval_sts-test_spearman_cosine": 0.9092536676310787,
+      "eval_sts-test_spearman_dot": 0.87468645079452,
+      "eval_sts-test_spearman_euclidean": 0.910149408879089,
+      "eval_sts-test_spearman_manhattan": 0.9104867886387189,
+      "eval_sts-test_spearman_max": 0.9104867886387189,
+      "step": 65
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 2.834491729736328,
+      "learning_rate": 3.4981871767775944e-05,
+      "loss": 0.3194,
+      "step": 66
+    },
+    {
+      "epoch": 0.5317460317460317,
+      "grad_norm": 3.168403148651123,
+      "learning_rate": 3.496777722576811e-05,
+      "loss": 0.3585,
+      "step": 67
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 2.8590433597564697,
+      "learning_rate": 3.494966234843439e-05,
+      "loss": 0.2843,
+      "step": 68
+    },
+    {
+      "epoch": 0.5476190476190477,
+      "grad_norm": 2.4585649967193604,
+      "learning_rate": 3.4927532140745435e-05,
+      "loss": 0.1916,
+      "step": 69
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 3.0862460136413574,
+      "learning_rate": 3.490139271707e-05,
+      "loss": 0.351,
+      "step": 70
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "eval_loss": 0.09706800431013107,
+      "eval_runtime": 113.496,
+      "eval_samples_per_second": 26.891,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8816183440112817,
+      "eval_sts-test_pearson_dot": 0.863407251078466,
+      "eval_sts-test_pearson_euclidean": 0.9125994563651346,
+      "eval_sts-test_pearson_manhattan": 0.9121928260729458,
+      "eval_sts-test_pearson_max": 0.9125994563651346,
+      "eval_sts-test_spearman_cosine": 0.9103631836274073,
+      "eval_sts-test_spearman_dot": 0.8729154643762167,
+      "eval_sts-test_spearman_euclidean": 0.9106339755374351,
+      "eval_sts-test_spearman_manhattan": 0.9104940383430642,
+      "eval_sts-test_spearman_max": 0.9106339755374351,
+      "step": 70
+    },
+    {
+      "epoch": 0.5634920634920635,
+      "grad_norm": 2.948397636413574,
+      "learning_rate": 3.48712512994856e-05,
+      "loss": 0.3105,
+      "step": 71
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 2.904085159301758,
+      "learning_rate": 3.4837116215783116e-05,
+      "loss": 0.2847,
+      "step": 72
+    },
+    {
+      "epoch": 0.5793650793650794,
+      "grad_norm": 2.6948978900909424,
+      "learning_rate": 3.4798996897165926e-05,
+      "loss": 0.2641,
+      "step": 73
+    },
+    {
+      "epoch": 0.5873015873015873,
+      "grad_norm": 3.068554162979126,
+      "learning_rate": 3.475690387564411e-05,
+      "loss": 0.3305,
+      "step": 74
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 2.6903178691864014,
+      "learning_rate": 3.471084878112459e-05,
+      "loss": 0.2461,
+      "step": 75
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "eval_loss": 0.09646341949701309,
+      "eval_runtime": 113.5342,
+      "eval_samples_per_second": 26.882,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.879746728283104,
+      "eval_sts-test_pearson_dot": 0.85998475002447,
+      "eval_sts-test_pearson_euclidean": 0.9117602609729114,
+      "eval_sts-test_pearson_manhattan": 0.9111396965114745,
+      "eval_sts-test_pearson_max": 0.9117602609729114,
+      "eval_sts-test_spearman_cosine": 0.9096228207862964,
+      "eval_sts-test_spearman_dot": 0.8689540379665887,
+      "eval_sts-test_spearman_euclidean": 0.9099527718365351,
+      "eval_sts-test_spearman_manhattan": 0.9098263942743658,
+      "eval_sts-test_spearman_max": 0.9099527718365351,
+      "step": 75
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 2.81105637550354,
+      "learning_rate": 3.4660844338197886e-05,
+      "loss": 0.259,
+      "step": 76
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 2.629365921020508,
+      "learning_rate": 3.460690436262242e-05,
+      "loss": 0.2506,
+      "step": 77
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 2.6665291786193848,
+      "learning_rate": 3.454904375750738e-05,
+      "loss": 0.2832,
+      "step": 78
+    },
+    {
+      "epoch": 0.626984126984127,
+      "grad_norm": 2.916246175765991,
+      "learning_rate": 3.448727850919509e-05,
+      "loss": 0.3322,
+      "step": 79
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 2.4879415035247803,
+      "learning_rate": 3.442162568284416e-05,
+      "loss": 0.2533,
+      "step": 80
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "eval_loss": 0.10007175803184509,
+      "eval_runtime": 113.3295,
+      "eval_samples_per_second": 26.93,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.8791063595826033,
+      "eval_sts-test_pearson_dot": 0.8594763353424633,
+      "eval_sts-test_pearson_euclidean": 0.9109289279488433,
+      "eval_sts-test_pearson_manhattan": 0.9101783025650423,
+      "eval_sts-test_pearson_max": 0.9109289279488433,
+      "eval_sts-test_spearman_cosine": 0.9088725211378084,
+      "eval_sts-test_spearman_dot": 0.8680133664521414,
+      "eval_sts-test_spearman_euclidean": 0.9091277823327847,
+      "eval_sts-test_spearman_manhattan": 0.9091334209917199,
+      "eval_sts-test_spearman_max": 0.9091334209917199,
+      "step": 80
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 2.6558098793029785,
+      "learning_rate": 3.435210341771455e-05,
+      "loss": 0.2349,
+      "step": 81
+    },
+    {
+      "epoch": 0.6507936507936508,
+      "grad_norm": 2.690624475479126,
+      "learning_rate": 3.427873092215584e-05,
+      "loss": 0.2748,
+      "step": 82
+    },
+    {
+      "epoch": 0.6587301587301587,
+      "grad_norm": 2.451726198196411,
+      "learning_rate": 3.420152846830015e-05,
+      "loss": 0.223,
+      "step": 83
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.6376216411590576,
+      "learning_rate": 3.412051738646116e-05,
+      "loss": 0.2416,
+      "step": 84
+    },
+    {
+      "epoch": 0.6746031746031746,
+      "grad_norm": 2.8111939430236816,
+      "learning_rate": 3.403572005924071e-05,
+      "loss": 0.2637,
+      "step": 85
+    },
+    {
+      "epoch": 0.6746031746031746,
+      "eval_loss": 0.10335631668567657,
+      "eval_runtime": 113.4166,
+      "eval_samples_per_second": 26.91,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.8779388329417936,
+      "eval_sts-test_pearson_dot": 0.8608493769098732,
+      "eval_sts-test_pearson_euclidean": 0.9095252832629803,
+      "eval_sts-test_pearson_manhattan": 0.9090695197203245,
+      "eval_sts-test_pearson_max": 0.9095252832629803,
+      "eval_sts-test_spearman_cosine": 0.9082387985252446,
+      "eval_sts-test_spearman_dot": 0.8707913010030126,
+      "eval_sts-test_spearman_euclidean": 0.9083403391373417,
+      "eval_sts-test_spearman_manhattan": 0.9084906586243554,
+      "eval_sts-test_spearman_max": 0.9084906586243554,
+      "step": 85
+    },
+    {
+      "epoch": 0.6825396825396826,
+      "grad_norm": 2.859077215194702,
+      "learning_rate": 3.394715991534474e-05,
+      "loss": 0.2856,
+      "step": 86
+    },
+    {
+      "epoch": 0.6904761904761905,
+      "grad_norm": 2.433560371398926,
+      "learning_rate": 3.385486142311011e-05,
+      "loss": 0.2476,
+      "step": 87
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 2.6791834831237793,
+      "learning_rate": 3.375885008374425e-05,
+      "loss": 0.2427,
+      "step": 88
+    },
+    {
+      "epoch": 0.7063492063492064,
+      "grad_norm": 2.6574490070343018,
+      "learning_rate": 3.365915242427944e-05,
+      "loss": 0.2614,
+      "step": 89
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 2.5747766494750977,
+      "learning_rate": 3.355579599024361e-05,
+      "loss": 0.26,
+      "step": 90
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "eval_loss": 0.10315236449241638,
+      "eval_runtime": 113.4044,
+      "eval_samples_per_second": 26.913,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.8793659111713259,
+      "eval_sts-test_pearson_dot": 0.8641308245754843,
+      "eval_sts-test_pearson_euclidean": 0.9095961426218309,
+      "eval_sts-test_pearson_manhattan": 0.9093977382821561,
+      "eval_sts-test_pearson_max": 0.9095961426218309,
+      "eval_sts-test_spearman_cosine": 0.9087700407492219,
+      "eval_sts-test_spearman_dot": 0.8756799287974091,
+      "eval_sts-test_spearman_euclidean": 0.9084703415516837,
+      "eval_sts-test_spearman_manhattan": 0.908642678659302,
+      "eval_sts-test_spearman_max": 0.9087700407492219,
+      "step": 90
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 2.3570423126220703,
+      "learning_rate": 3.3448809338049753e-05,
+      "loss": 0.1862,
+      "step": 91
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 2.486401319503784,
+      "learning_rate": 3.333822202710612e-05,
+      "loss": 0.267,
+      "step": 92
+    },
+    {
+      "epoch": 0.7380952380952381,
+      "grad_norm": 2.436018705368042,
+      "learning_rate": 3.322406461164916e-05,
+      "loss": 0.2175,
+      "step": 93
+    },
+    {
+      "epoch": 0.746031746031746,
+      "grad_norm": 2.2685282230377197,
+      "learning_rate": 3.310636863230172e-05,
+      "loss": 0.2079,
+      "step": 94
+    },
+    {
+      "epoch": 0.753968253968254,
+      "grad_norm": 2.564317464828491,
+      "learning_rate": 3.2985166607358637e-05,
+      "loss": 0.2562,
+      "step": 95
+    },
+    {
+      "epoch": 0.753968253968254,
+      "eval_loss": 0.09990089386701584,
+      "eval_runtime": 113.4641,
+      "eval_samples_per_second": 26.898,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.8795677625682299,
+      "eval_sts-test_pearson_dot": 0.8659349142313639,
+      "eval_sts-test_pearson_euclidean": 0.9099982334792637,
+      "eval_sts-test_pearson_manhattan": 0.9099098081017423,
+      "eval_sts-test_pearson_max": 0.9099982334792637,
+      "eval_sts-test_spearman_cosine": 0.9085842782631862,
+      "eval_sts-test_spearman_dot": 0.8767303751560495,
+      "eval_sts-test_spearman_euclidean": 0.9083879992307234,
+      "eval_sts-test_spearman_manhattan": 0.9084153422514337,
+      "eval_sts-test_spearman_max": 0.9085842782631862,
+      "step": 95
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 2.594452381134033,
+      "learning_rate": 3.286049202380226e-05,
+      "loss": 0.2516,
+      "step": 96
+    },
+    {
+      "epoch": 0.7698412698412699,
+      "grad_norm": 2.6356875896453857,
+      "learning_rate": 3.273237932805032e-05,
+      "loss": 0.2956,
+      "step": 97
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 2.6263818740844727,
+      "learning_rate": 3.260086391643865e-05,
+      "loss": 0.2733,
+      "step": 98
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 2.636934757232666,
+      "learning_rate": 3.246598212544159e-05,
+      "loss": 0.2919,
+      "step": 99
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 2.710754632949829,
+      "learning_rate": 3.2327771221632486e-05,
+      "loss": 0.2997,
+      "step": 100
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "eval_loss": 0.10318750143051147,
+      "eval_runtime": 113.3236,
+      "eval_samples_per_second": 26.932,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.8759700287215791,
+      "eval_sts-test_pearson_dot": 0.8604257798750153,
+      "eval_sts-test_pearson_euclidean": 0.9085309767938886,
+      "eval_sts-test_pearson_manhattan": 0.9086607224369581,
+      "eval_sts-test_pearson_max": 0.9086607224369581,
+      "eval_sts-test_spearman_cosine": 0.9069411909499396,
+      "eval_sts-test_spearman_dot": 0.8719651713405704,
+      "eval_sts-test_spearman_euclidean": 0.9080629260679763,
+      "eval_sts-test_spearman_manhattan": 0.907642129957113,
+      "eval_sts-test_spearman_max": 0.9080629260679763,
+      "step": 100
+    },
+    {
+      "epoch": 0.8015873015873016,
+      "grad_norm": 2.516517162322998,
+      "learning_rate": 3.218626939138736e-05,
+      "loss": 0.2276,
+      "step": 101
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 2.6900599002838135,
+      "learning_rate": 3.204151573033428e-05,
+      "loss": 0.2582,
+      "step": 102
+    },
+    {
+      "epoch": 0.8174603174603174,
+      "grad_norm": 2.5696845054626465,
+      "learning_rate": 3.189355023255171e-05,
+      "loss": 0.2559,
+      "step": 103
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 2.7647061347961426,
+      "learning_rate": 3.174241377951843e-05,
+      "loss": 0.2864,
+      "step": 104
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.7451863288879395,
+      "learning_rate": 3.1588148128818425e-05,
+      "loss": 0.2839,
+      "step": 105
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "eval_loss": 0.10743121802806854,
+      "eval_runtime": 113.407,
+      "eval_samples_per_second": 26.912,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.8767875416189156,
+      "eval_sts-test_pearson_dot": 0.8604239654952288,
+      "eval_sts-test_pearson_euclidean": 0.9092313999029703,
+      "eval_sts-test_pearson_manhattan": 0.9094243708597547,
+      "eval_sts-test_pearson_max": 0.9094243708597547,
+      "eval_sts-test_spearman_cosine": 0.9075548649973998,
+      "eval_sts-test_spearman_dot": 0.8721893304088798,
+      "eval_sts-test_spearman_euclidean": 0.9081462081654257,
+      "eval_sts-test_spearman_manhattan": 0.9082743310267892,
+      "eval_sts-test_spearman_max": 0.9082743310267892,
+      "step": 105
+    },
+    {
+      "epoch": 0.8412698412698413,
+      "grad_norm": 2.5484859943389893,
+      "learning_rate": 3.1430795902603625e-05,
+      "loss": 0.2549,
+      "step": 106
+    },
+    {
+      "epoch": 0.8492063492063492,
+      "grad_norm": 2.6235854625701904,
+      "learning_rate": 3.127040057581783e-05,
+      "loss": 0.2826,
+      "step": 107
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 2.5238397121429443,
+      "learning_rate": 3.110700646418496e-05,
+      "loss": 0.2334,
+      "step": 108
+    },
+    {
+      "epoch": 0.8650793650793651,
+      "grad_norm": 2.740260362625122,
+      "learning_rate": 3.0940658711965065e-05,
+      "loss": 0.2632,
+      "step": 109
+    },
+    {
+      "epoch": 0.873015873015873,
+      "grad_norm": 2.510667562484741,
+      "learning_rate": 3.077140327948137e-05,
+      "loss": 0.2255,
+      "step": 110
+    },
+    {
+      "epoch": 0.873015873015873,
+      "eval_loss": 0.10900076478719711,
+      "eval_runtime": 113.5509,
+      "eval_samples_per_second": 26.878,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8751607943383615,
+      "eval_sts-test_pearson_dot": 0.8589309347875178,
+      "eval_sts-test_pearson_euclidean": 0.9068514756772725,
+      "eval_sts-test_pearson_manhattan": 0.9076530218955405,
+      "eval_sts-test_pearson_max": 0.9076530218955405,
+      "eval_sts-test_spearman_cosine": 0.9056104674412049,
+      "eval_sts-test_spearman_dot": 0.8704153456560634,
+      "eval_sts-test_spearman_euclidean": 0.9057139771088031,
+      "eval_sts-test_spearman_manhattan": 0.9064273122153821,
+      "eval_sts-test_spearman_max": 0.9064273122153821,
+      "step": 110
+    },
+    {
+      "epoch": 0.8809523809523809,
+      "grad_norm": 2.552116632461548,
+      "learning_rate": 3.059928693042189e-05,
+      "loss": 0.2589,
+      "step": 111
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.5401554107666016,
+      "learning_rate": 3.0424357218919025e-05,
+      "loss": 0.2569,
+      "step": 112
+    },
+    {
+      "epoch": 0.8968253968253969,
+      "grad_norm": 2.695404291152954,
+      "learning_rate": 3.0246662476410844e-05,
+      "loss": 0.2797,
+      "step": 113
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 2.8901283740997314,
+      "learning_rate": 3.0066251798287526e-05,
+      "loss": 0.2742,
+      "step": 114
+    },
+    {
+      "epoch": 0.9126984126984127,
+      "grad_norm": 2.4771928787231445,
+      "learning_rate": 2.9883175030326795e-05,
+      "loss": 0.2295,
+      "step": 115
+    },
+    {
+      "epoch": 0.9126984126984127,
+      "eval_loss": 0.10703907907009125,
+      "eval_runtime": 113.456,
+      "eval_samples_per_second": 26.9,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.8721877249457892,
+      "eval_sts-test_pearson_dot": 0.8560616623137738,
+      "eval_sts-test_pearson_euclidean": 0.9030366016666834,
+      "eval_sts-test_pearson_manhattan": 0.9045537484069119,
+      "eval_sts-test_pearson_max": 0.9045537484069119,
+      "eval_sts-test_spearman_cosine": 0.9013517136508925,
+      "eval_sts-test_spearman_dot": 0.8659265703821992,
+      "eval_sts-test_spearman_euclidean": 0.9015738141611778,
+      "eval_sts-test_spearman_manhattan": 0.9030298859530699,
+      "eval_sts-test_spearman_max": 0.9030298859530699,
+      "step": 115
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 2.4024698734283447,
+      "learning_rate": 2.969748275492197e-05,
+      "loss": 0.2047,
+      "step": 116
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 2.7750799655914307,
+      "learning_rate": 2.9509226277106527e-05,
+      "loss": 0.2577,
+      "step": 117
+    },
+    {
+      "epoch": 0.9365079365079365,
+      "grad_norm": 2.545588731765747,
+      "learning_rate": 2.9318457610379043e-05,
+      "loss": 0.2614,
+      "step": 118
+    },
+    {
+      "epoch": 0.9444444444444444,
+      "grad_norm": 2.685835123062134,
+      "learning_rate": 2.9125229462332293e-05,
+      "loss": 0.2722,
+      "step": 119
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 2.3174188137054443,
+      "learning_rate": 2.892959522009068e-05,
+      "loss": 0.1927,
+      "step": 120
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "eval_loss": 0.10235559195280075,
+      "eval_runtime": 113.4984,
+      "eval_samples_per_second": 26.89,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.872488088039419,
+      "eval_sts-test_pearson_dot": 0.8563761302721377,
+      "eval_sts-test_pearson_euclidean": 0.9034767476820997,
+      "eval_sts-test_pearson_manhattan": 0.9044620383979292,
+      "eval_sts-test_pearson_max": 0.9044620383979292,
+      "eval_sts-test_spearman_cosine": 0.9008235592639511,
+      "eval_sts-test_spearman_dot": 0.864130657511301,
+      "eval_sts-test_spearman_euclidean": 0.9016059455668568,
+      "eval_sts-test_spearman_manhattan": 0.9027126890123276,
+      "eval_sts-test_spearman_max": 0.9027126890123276,
+      "step": 120
+    },
+    {
+      "epoch": 0.9603174603174603,
+      "grad_norm": 2.8979287147521973,
+      "learning_rate": 2.8731608935559857e-05,
+      "loss": 0.2649,
+      "step": 121
+    },
+    {
+      "epoch": 0.9682539682539683,
+      "grad_norm": 2.485367774963379,
+      "learning_rate": 2.8531325310492677e-05,
+      "loss": 0.2386,
+      "step": 122
+    },
+    {
+      "epoch": 0.9761904761904762,
+      "grad_norm": 2.662865400314331,
+      "learning_rate": 2.8328799681375657e-05,
+      "loss": 0.2801,
+      "step": 123
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 2.693284511566162,
+      "learning_rate": 2.812408800413997e-05,
+      "loss": 0.2583,
+      "step": 124
+    },
+    {
+      "epoch": 0.9920634920634921,
+      "grad_norm": 3.0903170108795166,
+      "learning_rate": 2.79172468387014e-05,
+      "loss": 0.3076,
+      "step": 125
+    },
+    {
+      "epoch": 0.9920634920634921,
+      "eval_loss": 0.09488630294799805,
+      "eval_runtime": 113.5341,
+      "eval_samples_per_second": 26.882,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8742114661417826,
+      "eval_sts-test_pearson_dot": 0.8564803125306033,
+      "eval_sts-test_pearson_euclidean": 0.905509251442753,
+      "eval_sts-test_pearson_manhattan": 0.9061976864024648,
+      "eval_sts-test_pearson_max": 0.9061976864024648,
+      "eval_sts-test_spearman_cosine": 0.901563655624842,
+      "eval_sts-test_spearman_dot": 0.8618259675496438,
+      "eval_sts-test_spearman_euclidean": 0.90313473815851,
+      "eval_sts-test_spearman_manhattan": 0.9041778900615435,
+      "eval_sts-test_spearman_max": 0.9041778900615435,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": NaN,
+      "learning_rate": 2.79172468387014e-05,
+      "loss": 0.5477,
+      "step": 126
+    },
+    {
+      "epoch": 1.007936507936508,
+      "grad_norm": 0.982935905456543,
+      "learning_rate": 2.7708333333333334e-05,
+      "loss": 0.0031,
+      "step": 127
+    },
+    {
+      "epoch": 1.0158730158730158,
+      "grad_norm": 7.32542133619063e-08,
+      "learning_rate": 2.7497405208877213e-05,
+      "loss": 0.0,
+      "step": 128
+    },
+    {
+      "epoch": 1.0238095238095237,
+      "grad_norm": 0.0,
+      "learning_rate": 2.7284520742794878e-05,
+      "loss": 0.0,
+      "step": 129
+    },
+    {
+      "epoch": 1.0317460317460319,
+      "grad_norm": 0.0,
+      "learning_rate": 2.706973875306696e-05,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.0317460317460319,
+      "eval_loss": 0.09545031189918518,
+      "eval_runtime": 114.0298,
+      "eval_samples_per_second": 26.765,
+      "eval_steps_per_second": 0.21,
+      "eval_sts-test_pearson_cosine": 0.874702030760496,
+      "eval_sts-test_pearson_dot": 0.8555439931828537,
+      "eval_sts-test_pearson_euclidean": 0.9065531106539271,
+      "eval_sts-test_pearson_manhattan": 0.9071871020121037,
+      "eval_sts-test_pearson_max": 0.9071871020121037,
+      "eval_sts-test_spearman_cosine": 0.9021036690960521,
+      "eval_sts-test_spearman_dot": 0.8598106392441436,
+      "eval_sts-test_spearman_euclidean": 0.9043656663543417,
+      "eval_sts-test_spearman_manhattan": 0.9048875555646884,
+      "eval_sts-test_spearman_max": 0.9048875555646884,
+      "step": 130
+    },
+    {
+      "epoch": 1.0396825396825398,
+      "grad_norm": 0.0,
+      "learning_rate": 2.6853118581942095e-05,
+      "loss": 0.0,
+      "step": 131
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 0.0,
+      "learning_rate": 2.66347200795412e-05,
+      "loss": 0.0,
+      "step": 132
+    },
+    {
+      "epoch": 1.0555555555555556,
+      "grad_norm": 0.0,
+      "learning_rate": 2.6414603587321415e-05,
+      "loss": 0.0,
+      "step": 133
+    },
+    {
+      "epoch": 1.0634920634920635,
+      "grad_norm": 0.0,
+      "learning_rate": 2.6192829921404365e-05,
+      "loss": 0.0,
+      "step": 134
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.0,
+      "learning_rate": 2.596946035577322e-05,
+      "loss": 0.0,
+      "step": 135
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "eval_loss": 0.09676523506641388,
+      "eval_runtime": 113.8781,
+      "eval_samples_per_second": 26.801,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8747276197594331,
+      "eval_sts-test_pearson_dot": 0.8544620877290974,
+      "eval_sts-test_pearson_euclidean": 0.9070156259790649,
+      "eval_sts-test_pearson_manhattan": 0.9076369642785601,
+      "eval_sts-test_pearson_max": 0.9076369642785601,
+      "eval_sts-test_spearman_cosine": 0.9022577924402841,
+      "eval_sts-test_spearman_dot": 0.8575864120504681,
+      "eval_sts-test_spearman_euclidean": 0.9046890144393489,
+      "eval_sts-test_spearman_manhattan": 0.9049111394794415,
+      "eval_sts-test_spearman_max": 0.9049111394794415,
+      "step": 135
+    },
+    {
+      "epoch": 1.0793650793650793,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5744556605343263e-05,
+      "loss": 0.0,
+      "step": 136
+    },
+    {
+      "epoch": 1.0873015873015872,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5518180808910628e-05,
+      "loss": 0.0,
+      "step": 137
+    },
+    {
+      "epoch": 1.0952380952380953,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5290395511983987e-05,
+      "loss": 0.0,
+      "step": 138
+    },
+    {
+      "epoch": 1.1031746031746033,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5061263649503735e-05,
+      "loss": 0.0,
+      "step": 139
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.0,
+      "learning_rate": 2.4830848528453706e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "eval_loss": 0.09783273935317993,
+      "eval_runtime": 113.4913,
+      "eval_samples_per_second": 26.892,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8746125563575086,
+      "eval_sts-test_pearson_dot": 0.8536822328210044,
+      "eval_sts-test_pearson_euclidean": 0.9071769017286274,
+      "eval_sts-test_pearson_manhattan": 0.9077849350046876,
+      "eval_sts-test_pearson_max": 0.9077849350046876,
+      "eval_sts-test_spearman_cosine": 0.9023702076088993,
+      "eval_sts-test_spearman_dot": 0.8566226041338817,
+      "eval_sts-test_spearman_euclidean": 0.9049979121752795,
+      "eval_sts-test_spearman_manhattan": 0.9049124372660218,
+      "eval_sts-test_spearman_max": 0.9049979121752795,
+      "step": 140
+    },
+    {
+      "epoch": 1.119047619047619,
+      "grad_norm": 0.0,
+      "learning_rate": 2.4599213810370067e-05,
+      "loss": 0.0,
+      "step": 141
+    },
+    {
+      "epoch": 1.126984126984127,
+      "grad_norm": 0.0,
+      "learning_rate": 2.4366423493752155e-05,
+      "loss": 0.0,
+      "step": 142
+    },
+    {
+      "epoch": 1.1349206349206349,
+      "grad_norm": 0.0,
+      "learning_rate": 2.4132541896380374e-05,
+      "loss": 0.0,
+      "step": 143
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.0,
+      "learning_rate": 2.3897633637545755e-05,
+      "loss": 0.0,
+      "step": 144
+    },
+    {
+      "epoch": 1.1507936507936507,
+      "grad_norm": 0.0,
+      "learning_rate": 2.366176362019625e-05,
+      "loss": 0.0,
+      "step": 145
+    },
+    {
+      "epoch": 1.1507936507936507,
+      "eval_loss": 0.09863892197608948,
+      "eval_runtime": 113.5886,
+      "eval_samples_per_second": 26.869,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8744759141501874,
+      "eval_sts-test_pearson_dot": 0.8531679877756508,
+      "eval_sts-test_pearson_euclidean": 0.9072042306444432,
+      "eval_sts-test_pearson_manhattan": 0.907805846396001,
+      "eval_sts-test_pearson_max": 0.907805846396001,
+      "eval_sts-test_spearman_cosine": 0.9023667170105107,
+      "eval_sts-test_spearman_dot": 0.8560352885793809,
+      "eval_sts-test_spearman_euclidean": 0.9048520230631434,
+      "eval_sts-test_spearman_manhattan": 0.9049029947498682,
+      "eval_sts-test_spearman_max": 0.9049029947498682,
+      "step": 145
+    },
+    {
+      "epoch": 1.1587301587301588,
+      "grad_norm": 0.0,
+      "learning_rate": 2.342499701300467e-05,
+      "loss": 0.0,
+      "step": 146
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 2.318739923236319e-05,
+      "loss": 0.0,
+      "step": 147
+    },
+    {
+      "epoch": 1.1746031746031746,
+      "grad_norm": 0.0,
+      "learning_rate": 2.29490359243094e-05,
+      "loss": 0.0,
+      "step": 148
+    },
+    {
+      "epoch": 1.1825396825396826,
+      "grad_norm": 0.0,
+      "learning_rate": 2.270997294638895e-05,
+      "loss": 0.0,
+      "step": 149
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.0,
+      "learning_rate": 2.24702763494597e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "eval_loss": 0.09906759858131409,
+      "eval_runtime": 113.5604,
+      "eval_samples_per_second": 26.876,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8744060293405248,
+      "eval_sts-test_pearson_dot": 0.8528829505611442,
+      "eval_sts-test_pearson_euclidean": 0.9072185184616055,
+      "eval_sts-test_pearson_manhattan": 0.9078100463432079,
+      "eval_sts-test_pearson_max": 0.9078100463432079,
+      "eval_sts-test_spearman_cosine": 0.9022761852087159,
+      "eval_sts-test_spearman_dot": 0.8555268694987131,
+      "eval_sts-test_spearman_euclidean": 0.9047365648087538,
+      "eval_sts-test_spearman_manhattan": 0.9048373894006686,
+      "eval_sts-test_spearman_max": 0.9048373894006686,
+      "step": 150
+    },
+    {
+      "epoch": 1.1984126984126984,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2230012359442495e-05,
+      "loss": 0.0,
+      "step": 151
+    },
+    {
+      "epoch": 1.2063492063492063,
+      "grad_norm": 0.0,
+      "learning_rate": 2.1989247359023566e-05,
+      "loss": 0.0,
+      "step": 152
+    },
+    {
+      "epoch": 1.2142857142857142,
+      "grad_norm": 0.0,
+      "learning_rate": 2.174804786931362e-05,
+      "loss": 0.0,
+      "step": 153
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.0,
+      "learning_rate": 2.150648053146869e-05,
+      "loss": 0.0,
+      "step": 154
+    },
+    {
+      "epoch": 1.2301587301587302,
+      "grad_norm": 0.0,
+      "learning_rate": 2.126461208827777e-05,
+      "loss": 0.0,
+      "step": 155
+    },
+    {
+      "epoch": 1.2301587301587302,
+      "eval_loss": 0.09936919808387756,
+      "eval_runtime": 113.5013,
+      "eval_samples_per_second": 26.89,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8743508789394699,
+      "eval_sts-test_pearson_dot": 0.8527007540947626,
+      "eval_sts-test_pearson_euclidean": 0.9072202919761476,
+      "eval_sts-test_pearson_manhattan": 0.9078091191041777,
+      "eval_sts-test_pearson_max": 0.9078091191041777,
+      "eval_sts-test_spearman_cosine": 0.9023025884529369,
+      "eval_sts-test_spearman_dot": 0.8550739867334323,
+      "eval_sts-test_spearman_euclidean": 0.9046202541246842,
+      "eval_sts-test_spearman_manhattan": 0.9049393775253795,
+      "eval_sts-test_spearman_max": 0.9049393775253795,
+      "step": 155
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 0.0,
+      "learning_rate": 2.102250936572247e-05,
+      "loss": 0.0,
+      "step": 156
+    },
+    {
+      "epoch": 1.246031746031746,
+      "grad_norm": 0.0,
+      "learning_rate": 2.0780239254513565e-05,
+      "loss": 0.0,
+      "step": 157
+    },
+    {
+      "epoch": 1.253968253968254,
+      "grad_norm": 0.0,
+      "learning_rate": 2.0537868691609745e-05,
+      "loss": 0.0,
+      "step": 158
+    },
+    {
+      "epoch": 1.2619047619047619,
+      "grad_norm": 0.0,
+      "learning_rate": 2.0295464641723583e-05,
+      "loss": 0.0,
+      "step": 159
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.0,
+      "learning_rate": 2.005309407881977e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "eval_loss": 0.09954561293125153,
+      "eval_runtime": 113.8237,
+      "eval_samples_per_second": 26.813,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8743232038160612,
+      "eval_sts-test_pearson_dot": 0.8526065970333739,
+      "eval_sts-test_pearson_euclidean": 0.9072152805749177,
+      "eval_sts-test_pearson_manhattan": 0.9078067984919014,
+      "eval_sts-test_pearson_max": 0.9078067984919014,
+      "eval_sts-test_spearman_cosine": 0.9022778857566487,
+      "eval_sts-test_spearman_dot": 0.8549482356889225,
+      "eval_sts-test_spearman_euclidean": 0.9046245971527523,
+      "eval_sts-test_spearman_manhattan": 0.9048685362785969,
+      "eval_sts-test_spearman_max": 0.9048685362785969,
+      "step": 160
+    },
+    {
+      "epoch": 1.2777777777777777,
+      "grad_norm": 0.0,
+      "learning_rate": 1.981082396761086e-05,
+      "loss": 0.0,
+      "step": 161
+    },
+    {
+      "epoch": 1.2857142857142858,
+      "grad_norm": 0.0,
+      "learning_rate": 1.956872124505556e-05,
+      "loss": 0.0,
+      "step": 162
+    },
+    {
+      "epoch": 1.2936507936507937,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9326852801864646e-05,
+      "loss": 0.0,
+      "step": 163
+    },
+    {
+      "epoch": 1.3015873015873016,
+      "grad_norm": 0.0,
+      "learning_rate": 1.908528546401971e-05,
+      "loss": 0.0,
+      "step": 164
+    },
+    {
+      "epoch": 1.3095238095238095,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8844085974309768e-05,
+      "loss": 0.0,
+      "step": 165
+    },
+    {
+      "epoch": 1.3095238095238095,
+      "eval_loss": 0.09964071214199066,
+      "eval_runtime": 113.5481,
+      "eval_samples_per_second": 26.878,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.874299456945445,
+      "eval_sts-test_pearson_dot": 0.8525374757432119,
+      "eval_sts-test_pearson_euclidean": 0.9072080565726848,
+      "eval_sts-test_pearson_manhattan": 0.907801820994878,
+      "eval_sts-test_pearson_max": 0.907801820994878,
+      "eval_sts-test_spearman_cosine": 0.9022729631178957,
+      "eval_sts-test_spearman_dot": 0.8546675557774756,
+      "eval_sts-test_spearman_euclidean": 0.9046749423218178,
+      "eval_sts-test_spearman_manhattan": 0.9047542415570032,
+      "eval_sts-test_spearman_max": 0.9047542415570032,
+      "step": 165
+    },
+    {
+      "epoch": 1.3174603174603174,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8603320973890842e-05,
+      "loss": 0.0,
+      "step": 166
+    },
+    {
+      "epoch": 1.3253968253968254,
+      "grad_norm": 0.0,
+      "learning_rate": 1.836305698387363e-05,
+      "loss": 0.0,
+      "step": 167
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 1.812336038694438e-05,
+      "loss": 0.0,
+      "step": 168
+    },
+    {
+      "epoch": 1.3412698412698412,
+      "grad_norm": 0.0,
+      "learning_rate": 1.7884297409023932e-05,
+      "loss": 0.0,
+      "step": 169
+    },
+    {
+      "epoch": 1.3492063492063493,
+      "grad_norm": 0.0,
+      "learning_rate": 1.7645934100970145e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.3492063492063493,
+      "eval_loss": 0.09969252347946167,
+      "eval_runtime": 113.9068,
+      "eval_samples_per_second": 26.794,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8742791376017494,
+      "eval_sts-test_pearson_dot": 0.8524863854057724,
+      "eval_sts-test_pearson_euclidean": 0.9072037622211908,
+      "eval_sts-test_pearson_manhattan": 0.9077955012591168,
+      "eval_sts-test_pearson_max": 0.9077955012591168,
+      "eval_sts-test_spearman_cosine": 0.9022626703277757,
+      "eval_sts-test_spearman_dot": 0.8547057286034424,
+      "eval_sts-test_spearman_euclidean": 0.9046214198131936,
+      "eval_sts-test_spearman_manhattan": 0.904806332025263,
+      "eval_sts-test_spearman_max": 0.904806332025263,
+      "step": 170
+    },
+    {
+      "epoch": 1.3571428571428572,
+      "grad_norm": 0.0,
+      "learning_rate": 1.740833632032866e-05,
+      "loss": 0.0,
+      "step": 171
+    },
+    {
+      "epoch": 1.3650793650793651,
+      "grad_norm": 0.0,
+      "learning_rate": 1.717156971313708e-05,
+      "loss": 0.0,
+      "step": 172
+    },
+    {
+      "epoch": 1.373015873015873,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6935699695787573e-05,
+      "loss": 0.0,
+      "step": 173
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6700791436952954e-05,
+      "loss": 0.0,
+      "step": 174
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6466909839581176e-05,
+      "loss": 0.0,
+      "step": 175
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "eval_loss": 0.09972869604825974,
+      "eval_runtime": 113.3507,
+      "eval_samples_per_second": 26.925,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.8742756437676581,
+      "eval_sts-test_pearson_dot": 0.852466650373626,
+      "eval_sts-test_pearson_euclidean": 0.9072071674153375,
+      "eval_sts-test_pearson_manhattan": 0.9077967797332845,
+      "eval_sts-test_pearson_max": 0.9077967797332845,
+      "eval_sts-test_spearman_cosine": 0.9022777962541261,
+      "eval_sts-test_spearman_dot": 0.8546733734414563,
+      "eval_sts-test_spearman_euclidean": 0.9045410465477347,
+      "eval_sts-test_spearman_manhattan": 0.9047774674616654,
+      "eval_sts-test_spearman_max": 0.9047774674616654,
+      "step": 175
+    },
+    {
+      "epoch": 1.3968253968253967,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6234119522963267e-05,
+      "loss": 0.0,
+      "step": 176
+    },
+    {
+      "epoch": 1.4047619047619047,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6002484804879622e-05,
+      "loss": 0.0,
+      "step": 177
+    },
+    {
+      "epoch": 1.4126984126984128,
+      "grad_norm": 0.0,
+      "learning_rate": 1.5772069683829603e-05,
+      "loss": 0.0,
+      "step": 178
+    },
+    {
+      "epoch": 1.4206349206349207,
+      "grad_norm": 0.0,
+      "learning_rate": 1.5542937821349347e-05,
+      "loss": 0.0,
+      "step": 179
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.0,
+      "learning_rate": 1.5315152524422703e-05,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "eval_loss": 0.09972812980413437,
+      "eval_runtime": 113.3751,
+      "eval_samples_per_second": 26.919,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.874267739156544,
+      "eval_sts-test_pearson_dot": 0.8524562621509095,
+      "eval_sts-test_pearson_euclidean": 0.9072067299928095,
+      "eval_sts-test_pearson_manhattan": 0.907793793015005,
+      "eval_sts-test_pearson_max": 0.907793793015005,
+      "eval_sts-test_spearman_cosine": 0.902276095706193,
+      "eval_sts-test_spearman_dot": 0.8546634834126889,
+      "eval_sts-test_spearman_euclidean": 0.9045989546799751,
+      "eval_sts-test_spearman_manhattan": 0.904807495558059,
+      "eval_sts-test_spearman_max": 0.904807495558059,
+      "step": 180
+    },
+    {
+      "epoch": 1.4365079365079365,
+      "grad_norm": 0.0,
+      "learning_rate": 1.508877672799007e-05,
+      "loss": 0.0,
+      "step": 181
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.0,
+      "learning_rate": 1.486387297756011e-05,
+      "loss": 0.0,
+      "step": 182
+    },
+    {
+      "epoch": 1.4523809523809523,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4640503411928961e-05,
+      "loss": 0.0,
+      "step": 183
+    },
+    {
+      "epoch": 1.4603174603174602,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4418729746011916e-05,
+      "loss": 0.0,
+      "step": 184
+    },
+    {
+      "epoch": 1.4682539682539681,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4198613253792132e-05,
+      "loss": 0.0,
+      "step": 185
+    },
+    {
+      "epoch": 1.4682539682539681,
+      "eval_loss": 0.09976483881473541,
+      "eval_runtime": 113.7822,
+      "eval_samples_per_second": 26.823,
+      "eval_steps_per_second": 0.211,
+      "eval_sts-test_pearson_cosine": 0.8742870531942544,
+      "eval_sts-test_pearson_dot": 0.8524755889148932,
+      "eval_sts-test_pearson_euclidean": 0.907218239020885,
+      "eval_sts-test_pearson_manhattan": 0.9078067867399013,
+      "eval_sts-test_pearson_max": 0.9078067867399013,
+      "eval_sts-test_spearman_cosine": 0.9022592692319099,
+      "eval_sts-test_spearman_dot": 0.854695972828459,
+      "eval_sts-test_spearman_euclidean": 0.9046065623944117,
+      "eval_sts-test_spearman_manhattan": 0.9048098673749128,
+      "eval_sts-test_spearman_max": 0.9048098673749128,
+      "step": 185
+    },
+    {
+      "epoch": 1.4761904761904763,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3980214751391232e-05,
+      "loss": 0.0,
+      "step": 186
+    },
+    {
+      "epoch": 1.4841269841269842,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3763594580266373e-05,
+      "loss": 0.0,
+      "step": 187
+    },
+    {
+      "epoch": 1.492063492063492,
+      "grad_norm": 0.0,
+      "learning_rate": 1.354881259053846e-05,
+      "loss": 0.0,
+      "step": 188
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3335928124456112e-05,
+      "loss": 0.0,
+      "step": 189
+    },
+    {
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3125000000000002e-05,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.507936507936508,
+      "eval_loss": 0.09976605325937271,
+      "eval_runtime": 113.3826,
+      "eval_samples_per_second": 26.918,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.874263623361507,
+      "eval_sts-test_pearson_dot": 0.8524433275217005,
+      "eval_sts-test_pearson_euclidean": 0.9072030414821628,
+      "eval_sts-test_pearson_manhattan": 0.9077920475707721,
+      "eval_sts-test_pearson_max": 0.9077920475707721,
+      "eval_sts-test_spearman_cosine": 0.9022537200754974,
+      "eval_sts-test_spearman_dot": 0.8545940742062709,
+      "eval_sts-test_spearman_euclidean": 0.9046282667561865,
+      "eval_sts-test_spearman_manhattan": 0.9047952337124378,
+      "eval_sts-test_spearman_max": 0.9047952337124378,
+      "step": 190
+    },
+    {
+      "epoch": 1.5158730158730158,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2916086494631928e-05,
+      "loss": 0.0,
+      "step": 191
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 0.0,
+      "learning_rate": 1.270924532919336e-05,
+      "loss": 0.0,
+      "step": 192
+    },
+    {
+      "epoch": 1.5317460317460319,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2504533651957674e-05,
+      "loss": 0.0,
+      "step": 193
+    },
+    {
+      "epoch": 1.5396825396825398,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2302008022840655e-05,
+      "loss": 0.0,
+      "step": 194
+    },
+    {
+      "epoch": 1.5476190476190477,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2101724397773472e-05,
+      "loss": 0.0,
+      "step": 195
+    },
+    {
+      "epoch": 1.5476190476190477,
+      "eval_loss": 0.0997559204697609,
+      "eval_runtime": 113.435,
+      "eval_samples_per_second": 26.905,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.8742609202554884,
+      "eval_sts-test_pearson_dot": 0.8524475712791351,
+      "eval_sts-test_pearson_euclidean": 0.9071965067276254,
+      "eval_sts-test_pearson_manhattan": 0.9077883011236819,
+      "eval_sts-test_pearson_max": 0.9077883011236819,
+      "eval_sts-test_spearman_cosine": 0.9022419952450129,
+      "eval_sts-test_spearman_dot": 0.8546614696059263,
+      "eval_sts-test_spearman_euclidean": 0.9045798011400996,
+      "eval_sts-test_spearman_manhattan": 0.9047780939793248,
+      "eval_sts-test_spearman_max": 0.9047780939793248,
+      "step": 195
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1903738113242652e-05,
+      "loss": 0.0,
+      "step": 196
+    },
+    {
+      "epoch": 1.5634920634920635,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1708103871001038e-05,
+      "loss": 0.0,
+      "step": 197
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1514875722954288e-05,
+      "loss": 0.0,
+      "step": 198
+    },
+    {
+      "epoch": 1.5793650793650793,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1324107056226802e-05,
+      "loss": 0.0,
+      "step": 199
+    },
+    {
+      "epoch": 1.5873015873015872,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1135850578411364e-05,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.5873015873015872,
+      "eval_loss": 0.09975530952215195,
+      "eval_runtime": 113.4016,
+      "eval_samples_per_second": 26.913,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.8742691362759177,
+      "eval_sts-test_pearson_dot": 0.8524477872044587,
+      "eval_sts-test_pearson_euclidean": 0.9072012894574042,
+      "eval_sts-test_pearson_manhattan": 0.9077892471366175,
+      "eval_sts-test_pearson_max": 0.9077892471366175,
+      "eval_sts-test_spearman_cosine": 0.9022147864780868,
+      "eval_sts-test_spearman_dot": 0.8547034910403729,
+      "eval_sts-test_spearman_euclidean": 0.904585216042728,
+      "eval_sts-test_spearman_manhattan": 0.9047465890913055,
+      "eval_sts-test_spearman_max": 0.9047465890913055,
+      "step": 200
+    },
+    {
+      "epoch": 1.5952380952380953,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0950158303006534e-05,
+      "loss": 0.0,
+      "step": 201
+    },
+    {
+      "epoch": 1.6031746031746033,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0767081535045804e-05,
+      "loss": 0.0,
+      "step": 202
+    },
+    {
+      "epoch": 1.6111111111111112,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0586670856922482e-05,
+      "loss": 0.0,
+      "step": 203
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0408976114414303e-05,
+      "loss": 0.0,
+      "step": 204
+    },
+    {
+      "epoch": 1.626984126984127,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0234046402911438e-05,
+      "loss": 0.0,
+      "step": 205
+    },
+    {
+      "epoch": 1.626984126984127,
+      "eval_loss": 0.09976042062044144,
+      "eval_runtime": 113.351,
+      "eval_samples_per_second": 26.925,
+      "eval_steps_per_second": 0.212,
+      "eval_sts-test_pearson_cosine": 0.8742827064396023,
+      "eval_sts-test_pearson_dot": 0.8524658058205945,
+      "eval_sts-test_pearson_euclidean": 0.9072144921384091,
+      "eval_sts-test_pearson_manhattan": 0.9078074095863298,
+      "eval_sts-test_pearson_max": 0.9078074095863298,
+      "eval_sts-test_spearman_cosine": 0.9022449488282648,
+      "eval_sts-test_spearman_dot": 0.8547093534556153,
+      "eval_sts-test_spearman_euclidean": 0.9046033403035915,
+      "eval_sts-test_spearman_manhattan": 0.9048224424793636,
+      "eval_sts-test_spearman_max": 0.9048224424793636,
+      "step": 205
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0061930053851954e-05,
+      "loss": 0.0,
+      "step": 206
+    },
+    {
+      "epoch": 1.6428571428571428,
+      "grad_norm": 0.0,
+      "learning_rate": 9.892674621368259e-06,
+      "loss": 0.0,
+      "step": 207
+    },
+    {
+      "epoch": 1.6507936507936507,
+      "grad_norm": 0.0,
+      "learning_rate": 9.72632686914837e-06,
+      "loss": 0.0,
+      "step": 208
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 252,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 26,
+  "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": 960,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee09b1db931d465aec016b4dfd4ea584c8c7e7c02278d7fcac63d526c4d30767
+size 5752