Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-6100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+final/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-6100/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "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-6100/README.md

@@ -0,0 +1,488 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:100K<n<1M
+- loss:MultipleNegativesRankingLoss
+base_model: FacebookAI/xlm-roberta-large
+metrics:
+- cosine_accuracy
+- dot_accuracy
+- manhattan_accuracy
+- euclidean_accuracy
+- max_accuracy
+widget:
+- source_sentence: The boy scowls
+  sentences:
+  - A snowboarder jumps.
+  - Boy playing baseball.
+  - The men have blonde hair.
+- source_sentence: an eagle flies
+  sentences:
+  - A woman is sleeping.
+  - He is playing a song.
+  - It is a cold day.
+- source_sentence: A woman sings.
+  sentences:
+  - She checks her phone.
+  - the animal is running
+  - two women sit on a couch
+- source_sentence: A bird flying.
+  sentences:
+  - Nobody is kicking.
+  - A man is on his feet.
+  - The girl has brown hair.
+- source_sentence: There's a dock
+  sentences:
+  - People are shopping.
+  - Five people on a path
+  - The girls are watching tv
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on FacebookAI/xlm-roberta-large
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: all nli dev
+      type: all-nli-dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.479
+      name: Cosine Accuracy
+    - type: dot_accuracy
+      value: 0.378
+      name: Dot Accuracy
+    - type: manhattan_accuracy
+      value: 0.484
+      name: Manhattan Accuracy
+    - type: euclidean_accuracy
+      value: 0.479
+      name: Euclidean Accuracy
+    - type: max_accuracy
+      value: 0.484
+      name: Max Accuracy
+---
+
+# SentenceTransformer based on FacebookAI/xlm-roberta-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) dataset. It maps sentences & paragraphs to a 1024-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:** [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) <!-- at revision c23d21b0620b635a76227c604d44e43a9f0ee389 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    "There's a dock",
+    'People are shopping.',
+    'Five people on a path',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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
+
+#### Triplet
+* Dataset: `all-nli-dev`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric             | Value     |
+|:-------------------|:----------|
+| cosine_accuracy    | 0.479     |
+| dot_accuracy       | 0.378     |
+| manhattan_accuracy | 0.484     |
+| euclidean_accuracy | 0.479     |
+| **max_accuracy**   | **0.484** |
+
+<!--
+## 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
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 100,000 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                          | negative                                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 10.9 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.62 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.76 tokens</li><li>max: 55 tokens</li></ul> |
+* Samples:
+  | anchor                                                                     | positive                                         | negative                                                   |
+  |:---------------------------------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code>        | <code>A person is outdoors, on a horse.</code>   | <code>A person is at a diner, ordering an omelette.</code> |
+  | <code>Children smiling and waving at camera</code>                         | <code>There are children present</code>          | <code>The kids are frowning</code>                         |
+  | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>The boy skates down the sidewalk.</code>             |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 1,000 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 20.31 tokens</li><li>max: 83 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.71 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 11.39 tokens</li><li>max: 32 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                         | positive                                                    | negative                                                |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:--------------------------------------------------------|
+  | <code>Two women are embracing while holding to go packages.</code>                                                                                                             | <code>Two woman are holding packages.</code>                | <code>The men are fighting outside a deli.</code>       |
+  | <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code>        |
+  | <code>A man selling donuts to a customer during a world exhibition event held in the city of Angeles</code>                                                                    | <code>A man selling donuts to a customer.</code>            | <code>A woman drinks her coffee in a small cafe.</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `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`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `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`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `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
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch | Step | Training Loss | loss   | all-nli-dev_max_accuracy |
+|:-----:|:----:|:-------------:|:------:|:------------------------:|
+| 0     | 0    | -             | -      | 0.616                    |
+| 0.016 | 100  | 3.2768        | 1.8053 | 0.833                    |
+| 0.032 | 200  | 1.1697        | 1.2878 | 0.861                    |
+| 0.048 | 300  | 1.372         | 1.2466 | 0.861                    |
+| 0.064 | 400  | 1.0476        | 1.2291 | 0.863                    |
+| 0.08  | 500  | 0.8588        | 1.5259 | 0.838                    |
+| 0.096 | 600  | 2.9781        | 3.4309 | 0.463                    |
+| 0.112 | 700  | 3.4982        | 3.4309 | 0.457                    |
+| 0.128 | 800  | 3.467         | 3.4309 | 0.479                    |
+| 0.144 | 900  | 3.4665        | 3.4309 | 0.452                    |
+| 0.16  | 1000 | 3.4664        | 3.4309 | 0.477                    |
+| 0.176 | 1100 | 3.4663        | 3.4309 | 0.458                    |
+| 0.192 | 1200 | 3.4661        | 3.4309 | 0.462                    |
+| 0.208 | 1300 | 3.4658        | 3.4309 | 0.45                     |
+| 0.224 | 1400 | 3.4661        | 3.4309 | 0.481                    |
+| 0.24  | 1500 | 3.4877        | 3.4309 | 0.464                    |
+| 0.256 | 1600 | 3.4675        | 3.4309 | 0.462                    |
+| 0.272 | 1700 | 3.4665        | 3.4309 | 0.488                    |
+| 0.288 | 1800 | 3.4667        | 3.4309 | 0.492                    |
+| 0.304 | 1900 | 3.4664        | 3.4309 | 0.455                    |
+| 0.32  | 2000 | 3.4661        | 3.4309 | 0.453                    |
+| 0.336 | 2100 | 3.4666        | 3.4309 | 0.477                    |
+| 0.352 | 2200 | 3.4683        | 3.4309 | 0.48                     |
+| 0.368 | 2300 | 3.4663        | 3.4309 | 0.469                    |
+| 0.384 | 2400 | 3.4667        | 3.4309 | 0.448                    |
+| 0.4   | 2500 | 3.4669        | 3.4309 | 0.499                    |
+| 0.416 | 2600 | 3.4661        | 3.4309 | 0.453                    |
+| 0.432 | 2700 | 3.4656        | 3.4309 | 0.467                    |
+| 0.448 | 2800 | 3.4662        | 3.4309 | 0.507                    |
+| 0.464 | 2900 | 3.4902        | 3.4309 | 0.473                    |
+| 0.48  | 3000 | 3.4663        | 3.4309 | 0.469                    |
+| 0.496 | 3100 | 3.554         | 3.4309 | 0.46                     |
+| 0.512 | 3200 | 3.4664        | 3.4309 | 0.455                    |
+| 0.528 | 3300 | 3.4668        | 3.4309 | 0.46                     |
+| 0.544 | 3400 | 3.4661        | 3.4309 | 0.492                    |
+| 0.56  | 3500 | 3.4667        | 3.4309 | 0.432                    |
+| 0.576 | 3600 | 3.4668        | 3.4309 | 0.486                    |
+| 0.592 | 3700 | 3.4666        | 3.4309 | 0.469                    |
+| 0.608 | 3800 | 3.4669        | 3.4309 | 0.473                    |
+| 0.624 | 3900 | 3.4658        | 3.4309 | 0.487                    |
+| 0.64  | 4000 | 3.4663        | 3.4309 | 0.448                    |
+| 0.656 | 4100 | 3.4663        | 3.4309 | 0.465                    |
+| 0.672 | 4200 | 3.4664        | 3.4309 | 0.484                    |
+| 0.688 | 4300 | 3.4663        | 3.4309 | 0.469                    |
+| 0.704 | 4400 | 3.4661        | 3.4309 | 0.478                    |
+| 0.72  | 4500 | 3.4669        | 3.4309 | 0.467                    |
+| 0.736 | 4600 | 3.4664        | 3.4309 | 0.455                    |
+| 0.752 | 4700 | 3.4664        | 3.4309 | 0.481                    |
+| 0.768 | 4800 | 3.4659        | 3.4309 | 0.466                    |
+| 0.784 | 4900 | 3.466         | 3.4309 | 0.451                    |
+| 0.8   | 5000 | 3.466         | 3.4309 | 0.473                    |
+| 0.816 | 5100 | 3.4664        | 3.4309 | 0.44                     |
+| 0.832 | 5200 | 3.4658        | 3.4309 | 0.497                    |
+| 0.848 | 5300 | 3.4664        | 3.4309 | 0.474                    |
+| 0.864 | 5400 | 3.4658        | 3.4309 | 0.449                    |
+| 0.88  | 5500 | 3.4662        | 3.4309 | 0.466                    |
+| 0.896 | 5600 | 3.4663        | 3.4309 | 0.476                    |
+| 0.912 | 5700 | 3.4667        | 3.4309 | 0.455                    |
+| 0.928 | 5800 | 3.4669        | 3.4309 | 0.463                    |
+| 0.944 | 5900 | 3.4657        | 3.4309 | 0.467                    |
+| 0.96  | 6000 | 3.4671        | 3.4309 | 0.456                    |
+| 0.976 | 6100 | 2.9471        | 3.4309 | 0.484                    |
+
+
+### Framework Versions
+- Python: 3.9.10
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.2
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.26.1
+- Datasets: 2.16.1
+- 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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-6100/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-6100/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.3.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-6100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3536403d82a4189fc382006c2061918f0903f620db30288232b2b4c7041e944
+size 2239607176

checkpoint-6100/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-6100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b87a3155f4a6d52f539a56d8b3f15fa2ea1f8126f5e93a8574a1d90b9e616af
+size 4471055801

checkpoint-6100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e6b358371fd8a01e1bb5ff6f6b184506fd43d9339c62665ab41df623190081
+size 14244

checkpoint-6100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f843d945721c7a0fb1269619e679250a0fa0bc91699c6353d8e5e224f65b7c
+size 1064

checkpoint-6100/sentence_bert_config.json

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

checkpoint-6100/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

checkpoint-6100/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-6100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

checkpoint-6100/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-6100/trainer_state.json

@@ -0,0 +1,1253 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.976,
+  "eval_steps": 100,
+  "global_step": 6100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016,
+      "grad_norm": 83.78450775146484,
+      "learning_rate": 7.44e-06,
+      "loss": 3.2768,
+      "step": 100
+    },
+    {
+      "epoch": 0.016,
+      "eval_all-nli-dev_cosine_accuracy": 0.815,
+      "eval_all-nli-dev_dot_accuracy": 0.316,
+      "eval_all-nli-dev_euclidean_accuracy": 0.804,
+      "eval_all-nli-dev_manhattan_accuracy": 0.833,
+      "eval_all-nli-dev_max_accuracy": 0.833,
+      "eval_loss": 1.8052657842636108,
+      "eval_runtime": 8.0216,
+      "eval_samples_per_second": 124.664,
+      "eval_steps_per_second": 7.854,
+      "step": 100
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 62.54200744628906,
+      "learning_rate": 1.544e-05,
+      "loss": 1.1697,
+      "step": 200
+    },
+    {
+      "epoch": 0.032,
+      "eval_all-nli-dev_cosine_accuracy": 0.842,
+      "eval_all-nli-dev_dot_accuracy": 0.171,
+      "eval_all-nli-dev_euclidean_accuracy": 0.838,
+      "eval_all-nli-dev_manhattan_accuracy": 0.861,
+      "eval_all-nli-dev_max_accuracy": 0.861,
+      "eval_loss": 1.2878086566925049,
+      "eval_runtime": 7.8831,
+      "eval_samples_per_second": 126.853,
+      "eval_steps_per_second": 7.992,
+      "step": 200
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 75.54035949707031,
+      "learning_rate": 2.344e-05,
+      "loss": 1.372,
+      "step": 300
+    },
+    {
+      "epoch": 0.048,
+      "eval_all-nli-dev_cosine_accuracy": 0.841,
+      "eval_all-nli-dev_dot_accuracy": 0.181,
+      "eval_all-nli-dev_euclidean_accuracy": 0.844,
+      "eval_all-nli-dev_manhattan_accuracy": 0.861,
+      "eval_all-nli-dev_max_accuracy": 0.861,
+      "eval_loss": 1.2466014623641968,
+      "eval_runtime": 7.8792,
+      "eval_samples_per_second": 126.916,
+      "eval_steps_per_second": 7.996,
+      "step": 300
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 33.85651779174805,
+      "learning_rate": 3.136e-05,
+      "loss": 1.0476,
+      "step": 400
+    },
+    {
+      "epoch": 0.064,
+      "eval_all-nli-dev_cosine_accuracy": 0.848,
+      "eval_all-nli-dev_dot_accuracy": 0.201,
+      "eval_all-nli-dev_euclidean_accuracy": 0.848,
+      "eval_all-nli-dev_manhattan_accuracy": 0.863,
+      "eval_all-nli-dev_max_accuracy": 0.863,
+      "eval_loss": 1.2291330099105835,
+      "eval_runtime": 7.8507,
+      "eval_samples_per_second": 127.378,
+      "eval_steps_per_second": 8.025,
+      "step": 400
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 27.536640167236328,
+      "learning_rate": 3.936e-05,
+      "loss": 0.8588,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "eval_all-nli-dev_cosine_accuracy": 0.821,
+      "eval_all-nli-dev_dot_accuracy": 0.213,
+      "eval_all-nli-dev_euclidean_accuracy": 0.828,
+      "eval_all-nli-dev_manhattan_accuracy": 0.838,
+      "eval_all-nli-dev_max_accuracy": 0.838,
+      "eval_loss": 1.5258921384811401,
+      "eval_runtime": 7.8331,
+      "eval_samples_per_second": 127.663,
+      "eval_steps_per_second": 8.043,
+      "step": 500
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.15947222709655762,
+      "learning_rate": 4.736000000000001e-05,
+      "loss": 2.9781,
+      "step": 600
+    },
+    {
+      "epoch": 0.096,
+      "eval_all-nli-dev_cosine_accuracy": 0.462,
+      "eval_all-nli-dev_dot_accuracy": 0.363,
+      "eval_all-nli-dev_euclidean_accuracy": 0.462,
+      "eval_all-nli-dev_manhattan_accuracy": 0.463,
+      "eval_all-nli-dev_max_accuracy": 0.463,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9535,
+      "eval_samples_per_second": 125.73,
+      "eval_steps_per_second": 7.921,
+      "step": 600
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.09273126721382141,
+      "learning_rate": 4.9404444444444447e-05,
+      "loss": 3.4982,
+      "step": 700
+    },
+    {
+      "epoch": 0.112,
+      "eval_all-nli-dev_cosine_accuracy": 0.449,
+      "eval_all-nli-dev_dot_accuracy": 0.381,
+      "eval_all-nli-dev_euclidean_accuracy": 0.449,
+      "eval_all-nli-dev_manhattan_accuracy": 0.457,
+      "eval_all-nli-dev_max_accuracy": 0.457,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.905,
+      "eval_samples_per_second": 126.501,
+      "eval_steps_per_second": 7.97,
+      "step": 700
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.047491393983364105,
+      "learning_rate": 4.851555555555556e-05,
+      "loss": 3.467,
+      "step": 800
+    },
+    {
+      "epoch": 0.128,
+      "eval_all-nli-dev_cosine_accuracy": 0.471,
+      "eval_all-nli-dev_dot_accuracy": 0.366,
+      "eval_all-nli-dev_euclidean_accuracy": 0.471,
+      "eval_all-nli-dev_manhattan_accuracy": 0.479,
+      "eval_all-nli-dev_max_accuracy": 0.479,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8623,
+      "eval_samples_per_second": 127.188,
+      "eval_steps_per_second": 8.013,
+      "step": 800
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.05457993969321251,
+      "learning_rate": 4.762666666666667e-05,
+      "loss": 3.4665,
+      "step": 900
+    },
+    {
+      "epoch": 0.144,
+      "eval_all-nli-dev_cosine_accuracy": 0.452,
+      "eval_all-nli-dev_dot_accuracy": 0.342,
+      "eval_all-nli-dev_euclidean_accuracy": 0.452,
+      "eval_all-nli-dev_manhattan_accuracy": 0.446,
+      "eval_all-nli-dev_max_accuracy": 0.452,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 8.0107,
+      "eval_samples_per_second": 124.832,
+      "eval_steps_per_second": 7.864,
+      "step": 900
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.03311806544661522,
+      "learning_rate": 4.673777777777778e-05,
+      "loss": 3.4664,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16,
+      "eval_all-nli-dev_cosine_accuracy": 0.477,
+      "eval_all-nli-dev_dot_accuracy": 0.352,
+      "eval_all-nli-dev_euclidean_accuracy": 0.477,
+      "eval_all-nli-dev_manhattan_accuracy": 0.468,
+      "eval_all-nli-dev_max_accuracy": 0.477,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9233,
+      "eval_samples_per_second": 126.21,
+      "eval_steps_per_second": 7.951,
+      "step": 1000
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.02707391045987606,
+      "learning_rate": 4.584888888888889e-05,
+      "loss": 3.4663,
+      "step": 1100
+    },
+    {
+      "epoch": 0.176,
+      "eval_all-nli-dev_cosine_accuracy": 0.458,
+      "eval_all-nli-dev_dot_accuracy": 0.376,
+      "eval_all-nli-dev_euclidean_accuracy": 0.458,
+      "eval_all-nli-dev_manhattan_accuracy": 0.452,
+      "eval_all-nli-dev_max_accuracy": 0.458,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8521,
+      "eval_samples_per_second": 127.354,
+      "eval_steps_per_second": 8.023,
+      "step": 1100
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.030668186023831367,
+      "learning_rate": 4.496e-05,
+      "loss": 3.4661,
+      "step": 1200
+    },
+    {
+      "epoch": 0.192,
+      "eval_all-nli-dev_cosine_accuracy": 0.46,
+      "eval_all-nli-dev_dot_accuracy": 0.39,
+      "eval_all-nli-dev_euclidean_accuracy": 0.46,
+      "eval_all-nli-dev_manhattan_accuracy": 0.462,
+      "eval_all-nli-dev_max_accuracy": 0.462,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 8.0488,
+      "eval_samples_per_second": 124.243,
+      "eval_steps_per_second": 7.827,
+      "step": 1200
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.04911087080836296,
+      "learning_rate": 4.4071111111111115e-05,
+      "loss": 3.4658,
+      "step": 1300
+    },
+    {
+      "epoch": 0.208,
+      "eval_all-nli-dev_cosine_accuracy": 0.441,
+      "eval_all-nli-dev_dot_accuracy": 0.338,
+      "eval_all-nli-dev_euclidean_accuracy": 0.441,
+      "eval_all-nli-dev_manhattan_accuracy": 0.45,
+      "eval_all-nli-dev_max_accuracy": 0.45,
+      "eval_loss": 3.4308857917785645,
+      "eval_runtime": 7.9015,
+      "eval_samples_per_second": 126.558,
+      "eval_steps_per_second": 7.973,
+      "step": 1300
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.02693816088140011,
+      "learning_rate": 4.3182222222222226e-05,
+      "loss": 3.4661,
+      "step": 1400
+    },
+    {
+      "epoch": 0.224,
+      "eval_all-nli-dev_cosine_accuracy": 0.475,
+      "eval_all-nli-dev_dot_accuracy": 0.31,
+      "eval_all-nli-dev_euclidean_accuracy": 0.475,
+      "eval_all-nli-dev_manhattan_accuracy": 0.481,
+      "eval_all-nli-dev_max_accuracy": 0.481,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.9424,
+      "eval_samples_per_second": 125.906,
+      "eval_steps_per_second": 7.932,
+      "step": 1400
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.17906944453716278,
+      "learning_rate": 4.229333333333334e-05,
+      "loss": 3.4877,
+      "step": 1500
+    },
+    {
+      "epoch": 0.24,
+      "eval_all-nli-dev_cosine_accuracy": 0.464,
+      "eval_all-nli-dev_dot_accuracy": 0.358,
+      "eval_all-nli-dev_euclidean_accuracy": 0.464,
+      "eval_all-nli-dev_manhattan_accuracy": 0.458,
+      "eval_all-nli-dev_max_accuracy": 0.464,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9335,
+      "eval_samples_per_second": 126.048,
+      "eval_steps_per_second": 7.941,
+      "step": 1500
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.07473237067461014,
+      "learning_rate": 4.140444444444445e-05,
+      "loss": 3.4675,
+      "step": 1600
+    },
+    {
+      "epoch": 0.256,
+      "eval_all-nli-dev_cosine_accuracy": 0.462,
+      "eval_all-nli-dev_dot_accuracy": 0.347,
+      "eval_all-nli-dev_euclidean_accuracy": 0.462,
+      "eval_all-nli-dev_manhattan_accuracy": 0.457,
+      "eval_all-nli-dev_max_accuracy": 0.462,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9155,
+      "eval_samples_per_second": 126.335,
+      "eval_steps_per_second": 7.959,
+      "step": 1600
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.06472893804311752,
+      "learning_rate": 4.051555555555556e-05,
+      "loss": 3.4665,
+      "step": 1700
+    },
+    {
+      "epoch": 0.272,
+      "eval_all-nli-dev_cosine_accuracy": 0.488,
+      "eval_all-nli-dev_dot_accuracy": 0.394,
+      "eval_all-nli-dev_euclidean_accuracy": 0.488,
+      "eval_all-nli-dev_manhattan_accuracy": 0.487,
+      "eval_all-nli-dev_max_accuracy": 0.488,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.7762,
+      "eval_samples_per_second": 128.597,
+      "eval_steps_per_second": 8.102,
+      "step": 1700
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.05817211791872978,
+      "learning_rate": 3.9626666666666664e-05,
+      "loss": 3.4667,
+      "step": 1800
+    },
+    {
+      "epoch": 0.288,
+      "eval_all-nli-dev_cosine_accuracy": 0.492,
+      "eval_all-nli-dev_dot_accuracy": 0.396,
+      "eval_all-nli-dev_euclidean_accuracy": 0.492,
+      "eval_all-nli-dev_manhattan_accuracy": 0.483,
+      "eval_all-nli-dev_max_accuracy": 0.492,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8429,
+      "eval_samples_per_second": 127.504,
+      "eval_steps_per_second": 8.033,
+      "step": 1800
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.06118469312787056,
+      "learning_rate": 3.8737777777777776e-05,
+      "loss": 3.4664,
+      "step": 1900
+    },
+    {
+      "epoch": 0.304,
+      "eval_all-nli-dev_cosine_accuracy": 0.452,
+      "eval_all-nli-dev_dot_accuracy": 0.377,
+      "eval_all-nli-dev_euclidean_accuracy": 0.452,
+      "eval_all-nli-dev_manhattan_accuracy": 0.455,
+      "eval_all-nli-dev_max_accuracy": 0.455,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8193,
+      "eval_samples_per_second": 127.888,
+      "eval_steps_per_second": 8.057,
+      "step": 1900
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.034288015216588974,
+      "learning_rate": 3.784888888888889e-05,
+      "loss": 3.4661,
+      "step": 2000
+    },
+    {
+      "epoch": 0.32,
+      "eval_all-nli-dev_cosine_accuracy": 0.446,
+      "eval_all-nli-dev_dot_accuracy": 0.35,
+      "eval_all-nli-dev_euclidean_accuracy": 0.446,
+      "eval_all-nli-dev_manhattan_accuracy": 0.453,
+      "eval_all-nli-dev_max_accuracy": 0.453,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8176,
+      "eval_samples_per_second": 127.916,
+      "eval_steps_per_second": 8.059,
+      "step": 2000
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.06111547723412514,
+      "learning_rate": 3.696e-05,
+      "loss": 3.4666,
+      "step": 2100
+    },
+    {
+      "epoch": 0.336,
+      "eval_all-nli-dev_cosine_accuracy": 0.469,
+      "eval_all-nli-dev_dot_accuracy": 0.39,
+      "eval_all-nli-dev_euclidean_accuracy": 0.469,
+      "eval_all-nli-dev_manhattan_accuracy": 0.477,
+      "eval_all-nli-dev_max_accuracy": 0.477,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.8728,
+      "eval_samples_per_second": 127.02,
+      "eval_steps_per_second": 8.002,
+      "step": 2100
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.06624756008386612,
+      "learning_rate": 3.607111111111111e-05,
+      "loss": 3.4683,
+      "step": 2200
+    },
+    {
+      "epoch": 0.352,
+      "eval_all-nli-dev_cosine_accuracy": 0.478,
+      "eval_all-nli-dev_dot_accuracy": 0.338,
+      "eval_all-nli-dev_euclidean_accuracy": 0.478,
+      "eval_all-nli-dev_manhattan_accuracy": 0.48,
+      "eval_all-nli-dev_max_accuracy": 0.48,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9247,
+      "eval_samples_per_second": 126.188,
+      "eval_steps_per_second": 7.95,
+      "step": 2200
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.031209247186779976,
+      "learning_rate": 3.518222222222222e-05,
+      "loss": 3.4663,
+      "step": 2300
+    },
+    {
+      "epoch": 0.368,
+      "eval_all-nli-dev_cosine_accuracy": 0.469,
+      "eval_all-nli-dev_dot_accuracy": 0.312,
+      "eval_all-nli-dev_euclidean_accuracy": 0.469,
+      "eval_all-nli-dev_manhattan_accuracy": 0.464,
+      "eval_all-nli-dev_max_accuracy": 0.469,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8393,
+      "eval_samples_per_second": 127.562,
+      "eval_steps_per_second": 8.036,
+      "step": 2300
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.133990079164505,
+      "learning_rate": 3.429333333333333e-05,
+      "loss": 3.4667,
+      "step": 2400
+    },
+    {
+      "epoch": 0.384,
+      "eval_all-nli-dev_cosine_accuracy": 0.448,
+      "eval_all-nli-dev_dot_accuracy": 0.404,
+      "eval_all-nli-dev_euclidean_accuracy": 0.448,
+      "eval_all-nli-dev_manhattan_accuracy": 0.445,
+      "eval_all-nli-dev_max_accuracy": 0.448,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 8.021,
+      "eval_samples_per_second": 124.672,
+      "eval_steps_per_second": 7.854,
+      "step": 2400
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.04892706498503685,
+      "learning_rate": 3.3404444444444444e-05,
+      "loss": 3.4669,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4,
+      "eval_all-nli-dev_cosine_accuracy": 0.499,
+      "eval_all-nli-dev_dot_accuracy": 0.365,
+      "eval_all-nli-dev_euclidean_accuracy": 0.499,
+      "eval_all-nli-dev_manhattan_accuracy": 0.492,
+      "eval_all-nli-dev_max_accuracy": 0.499,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.8451,
+      "eval_samples_per_second": 127.468,
+      "eval_steps_per_second": 8.03,
+      "step": 2500
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.053150493651628494,
+      "learning_rate": 3.2515555555555555e-05,
+      "loss": 3.4661,
+      "step": 2600
+    },
+    {
+      "epoch": 0.416,
+      "eval_all-nli-dev_cosine_accuracy": 0.453,
+      "eval_all-nli-dev_dot_accuracy": 0.349,
+      "eval_all-nli-dev_euclidean_accuracy": 0.453,
+      "eval_all-nli-dev_manhattan_accuracy": 0.45,
+      "eval_all-nli-dev_max_accuracy": 0.453,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9334,
+      "eval_samples_per_second": 126.05,
+      "eval_steps_per_second": 7.941,
+      "step": 2600
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.09555792808532715,
+      "learning_rate": 3.1626666666666667e-05,
+      "loss": 3.4656,
+      "step": 2700
+    },
+    {
+      "epoch": 0.432,
+      "eval_all-nli-dev_cosine_accuracy": 0.466,
+      "eval_all-nli-dev_dot_accuracy": 0.336,
+      "eval_all-nli-dev_euclidean_accuracy": 0.466,
+      "eval_all-nli-dev_manhattan_accuracy": 0.467,
+      "eval_all-nli-dev_max_accuracy": 0.467,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8562,
+      "eval_samples_per_second": 127.287,
+      "eval_steps_per_second": 8.019,
+      "step": 2700
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.01744948886334896,
+      "learning_rate": 3.0737777777777785e-05,
+      "loss": 3.4662,
+      "step": 2800
+    },
+    {
+      "epoch": 0.448,
+      "eval_all-nli-dev_cosine_accuracy": 0.506,
+      "eval_all-nli-dev_dot_accuracy": 0.4,
+      "eval_all-nli-dev_euclidean_accuracy": 0.506,
+      "eval_all-nli-dev_manhattan_accuracy": 0.507,
+      "eval_all-nli-dev_max_accuracy": 0.507,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8617,
+      "eval_samples_per_second": 127.199,
+      "eval_steps_per_second": 8.014,
+      "step": 2800
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.2527749538421631,
+      "learning_rate": 2.986666666666667e-05,
+      "loss": 3.4902,
+      "step": 2900
+    },
+    {
+      "epoch": 0.464,
+      "eval_all-nli-dev_cosine_accuracy": 0.463,
+      "eval_all-nli-dev_dot_accuracy": 0.338,
+      "eval_all-nli-dev_euclidean_accuracy": 0.463,
+      "eval_all-nli-dev_manhattan_accuracy": 0.473,
+      "eval_all-nli-dev_max_accuracy": 0.473,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8074,
+      "eval_samples_per_second": 128.083,
+      "eval_steps_per_second": 8.069,
+      "step": 2900
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.02826513536274433,
+      "learning_rate": 2.897777777777778e-05,
+      "loss": 3.4663,
+      "step": 3000
+    },
+    {
+      "epoch": 0.48,
+      "eval_all-nli-dev_cosine_accuracy": 0.454,
+      "eval_all-nli-dev_dot_accuracy": 0.338,
+      "eval_all-nli-dev_euclidean_accuracy": 0.454,
+      "eval_all-nli-dev_manhattan_accuracy": 0.469,
+      "eval_all-nli-dev_max_accuracy": 0.469,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8421,
+      "eval_samples_per_second": 127.516,
+      "eval_steps_per_second": 8.034,
+      "step": 3000
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.07985329627990723,
+      "learning_rate": 2.8088888888888893e-05,
+      "loss": 3.554,
+      "step": 3100
+    },
+    {
+      "epoch": 0.496,
+      "eval_all-nli-dev_cosine_accuracy": 0.456,
+      "eval_all-nli-dev_dot_accuracy": 0.359,
+      "eval_all-nli-dev_euclidean_accuracy": 0.456,
+      "eval_all-nli-dev_manhattan_accuracy": 0.46,
+      "eval_all-nli-dev_max_accuracy": 0.46,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8756,
+      "eval_samples_per_second": 126.975,
+      "eval_steps_per_second": 7.999,
+      "step": 3100
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.1259102076292038,
+      "learning_rate": 2.7200000000000004e-05,
+      "loss": 3.4664,
+      "step": 3200
+    },
+    {
+      "epoch": 0.512,
+      "eval_all-nli-dev_cosine_accuracy": 0.455,
+      "eval_all-nli-dev_dot_accuracy": 0.257,
+      "eval_all-nli-dev_euclidean_accuracy": 0.455,
+      "eval_all-nli-dev_manhattan_accuracy": 0.454,
+      "eval_all-nli-dev_max_accuracy": 0.455,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9019,
+      "eval_samples_per_second": 126.552,
+      "eval_steps_per_second": 7.973,
+      "step": 3200
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.06493524461984634,
+      "learning_rate": 2.6311111111111115e-05,
+      "loss": 3.4668,
+      "step": 3300
+    },
+    {
+      "epoch": 0.528,
+      "eval_all-nli-dev_cosine_accuracy": 0.448,
+      "eval_all-nli-dev_dot_accuracy": 0.383,
+      "eval_all-nli-dev_euclidean_accuracy": 0.448,
+      "eval_all-nli-dev_manhattan_accuracy": 0.46,
+      "eval_all-nli-dev_max_accuracy": 0.46,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9333,
+      "eval_samples_per_second": 126.051,
+      "eval_steps_per_second": 7.941,
+      "step": 3300
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.0680716335773468,
+      "learning_rate": 2.5422222222222227e-05,
+      "loss": 3.4661,
+      "step": 3400
+    },
+    {
+      "epoch": 0.544,
+      "eval_all-nli-dev_cosine_accuracy": 0.492,
+      "eval_all-nli-dev_dot_accuracy": 0.407,
+      "eval_all-nli-dev_euclidean_accuracy": 0.492,
+      "eval_all-nli-dev_manhattan_accuracy": 0.481,
+      "eval_all-nli-dev_max_accuracy": 0.492,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9192,
+      "eval_samples_per_second": 126.276,
+      "eval_steps_per_second": 7.955,
+      "step": 3400
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.04947361350059509,
+      "learning_rate": 2.4533333333333334e-05,
+      "loss": 3.4667,
+      "step": 3500
+    },
+    {
+      "epoch": 0.56,
+      "eval_all-nli-dev_cosine_accuracy": 0.432,
+      "eval_all-nli-dev_dot_accuracy": 0.391,
+      "eval_all-nli-dev_euclidean_accuracy": 0.432,
+      "eval_all-nli-dev_manhattan_accuracy": 0.427,
+      "eval_all-nli-dev_max_accuracy": 0.432,
+      "eval_loss": 3.4308857917785645,
+      "eval_runtime": 7.8702,
+      "eval_samples_per_second": 127.061,
+      "eval_steps_per_second": 8.005,
+      "step": 3500
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.07287462800741196,
+      "learning_rate": 2.3644444444444446e-05,
+      "loss": 3.4668,
+      "step": 3600
+    },
+    {
+      "epoch": 0.576,
+      "eval_all-nli-dev_cosine_accuracy": 0.482,
+      "eval_all-nli-dev_dot_accuracy": 0.374,
+      "eval_all-nli-dev_euclidean_accuracy": 0.482,
+      "eval_all-nli-dev_manhattan_accuracy": 0.486,
+      "eval_all-nli-dev_max_accuracy": 0.486,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8562,
+      "eval_samples_per_second": 127.288,
+      "eval_steps_per_second": 8.019,
+      "step": 3600
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.028324555605649948,
+      "learning_rate": 2.2755555555555557e-05,
+      "loss": 3.4666,
+      "step": 3700
+    },
+    {
+      "epoch": 0.592,
+      "eval_all-nli-dev_cosine_accuracy": 0.469,
+      "eval_all-nli-dev_dot_accuracy": 0.351,
+      "eval_all-nli-dev_euclidean_accuracy": 0.469,
+      "eval_all-nli-dev_manhattan_accuracy": 0.46,
+      "eval_all-nli-dev_max_accuracy": 0.469,
+      "eval_loss": 3.4308865070343018,
+      "eval_runtime": 7.879,
+      "eval_samples_per_second": 126.919,
+      "eval_steps_per_second": 7.996,
+      "step": 3700
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.04251887649297714,
+      "learning_rate": 2.186666666666667e-05,
+      "loss": 3.4669,
+      "step": 3800
+    },
+    {
+      "epoch": 0.608,
+      "eval_all-nli-dev_cosine_accuracy": 0.473,
+      "eval_all-nli-dev_dot_accuracy": 0.369,
+      "eval_all-nli-dev_euclidean_accuracy": 0.473,
+      "eval_all-nli-dev_manhattan_accuracy": 0.467,
+      "eval_all-nli-dev_max_accuracy": 0.473,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9346,
+      "eval_samples_per_second": 126.031,
+      "eval_steps_per_second": 7.94,
+      "step": 3800
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.01685403846204281,
+      "learning_rate": 2.097777777777778e-05,
+      "loss": 3.4658,
+      "step": 3900
+    },
+    {
+      "epoch": 0.624,
+      "eval_all-nli-dev_cosine_accuracy": 0.487,
+      "eval_all-nli-dev_dot_accuracy": 0.333,
+      "eval_all-nli-dev_euclidean_accuracy": 0.487,
+      "eval_all-nli-dev_manhattan_accuracy": 0.486,
+      "eval_all-nli-dev_max_accuracy": 0.487,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 8.0469,
+      "eval_samples_per_second": 124.272,
+      "eval_steps_per_second": 7.829,
+      "step": 3900
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.16402187943458557,
+      "learning_rate": 2.008888888888889e-05,
+      "loss": 3.4663,
+      "step": 4000
+    },
+    {
+      "epoch": 0.64,
+      "eval_all-nli-dev_cosine_accuracy": 0.448,
+      "eval_all-nli-dev_dot_accuracy": 0.355,
+      "eval_all-nli-dev_euclidean_accuracy": 0.448,
+      "eval_all-nli-dev_manhattan_accuracy": 0.442,
+      "eval_all-nli-dev_max_accuracy": 0.448,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9755,
+      "eval_samples_per_second": 125.384,
+      "eval_steps_per_second": 7.899,
+      "step": 4000
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.08633382618427277,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 3.4663,
+      "step": 4100
+    },
+    {
+      "epoch": 0.656,
+      "eval_all-nli-dev_cosine_accuracy": 0.463,
+      "eval_all-nli-dev_dot_accuracy": 0.3,
+      "eval_all-nli-dev_euclidean_accuracy": 0.463,
+      "eval_all-nli-dev_manhattan_accuracy": 0.465,
+      "eval_all-nli-dev_max_accuracy": 0.465,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9722,
+      "eval_samples_per_second": 125.436,
+      "eval_steps_per_second": 7.902,
+      "step": 4100
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.08357453346252441,
+      "learning_rate": 1.8311111111111114e-05,
+      "loss": 3.4664,
+      "step": 4200
+    },
+    {
+      "epoch": 0.672,
+      "eval_all-nli-dev_cosine_accuracy": 0.48,
+      "eval_all-nli-dev_dot_accuracy": 0.343,
+      "eval_all-nli-dev_euclidean_accuracy": 0.48,
+      "eval_all-nli-dev_manhattan_accuracy": 0.484,
+      "eval_all-nli-dev_max_accuracy": 0.484,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9287,
+      "eval_samples_per_second": 126.125,
+      "eval_steps_per_second": 7.946,
+      "step": 4200
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.20162004232406616,
+      "learning_rate": 1.7422222222222222e-05,
+      "loss": 3.4663,
+      "step": 4300
+    },
+    {
+      "epoch": 0.688,
+      "eval_all-nli-dev_cosine_accuracy": 0.451,
+      "eval_all-nli-dev_dot_accuracy": 0.354,
+      "eval_all-nli-dev_euclidean_accuracy": 0.451,
+      "eval_all-nli-dev_manhattan_accuracy": 0.469,
+      "eval_all-nli-dev_max_accuracy": 0.469,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9242,
+      "eval_samples_per_second": 126.195,
+      "eval_steps_per_second": 7.95,
+      "step": 4300
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.17491748929023743,
+      "learning_rate": 1.6533333333333333e-05,
+      "loss": 3.4661,
+      "step": 4400
+    },
+    {
+      "epoch": 0.704,
+      "eval_all-nli-dev_cosine_accuracy": 0.47,
+      "eval_all-nli-dev_dot_accuracy": 0.367,
+      "eval_all-nli-dev_euclidean_accuracy": 0.47,
+      "eval_all-nli-dev_manhattan_accuracy": 0.478,
+      "eval_all-nli-dev_max_accuracy": 0.478,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.989,
+      "eval_samples_per_second": 125.172,
+      "eval_steps_per_second": 7.886,
+      "step": 4400
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.1597195565700531,
+      "learning_rate": 1.5644444444444444e-05,
+      "loss": 3.4669,
+      "step": 4500
+    },
+    {
+      "epoch": 0.72,
+      "eval_all-nli-dev_cosine_accuracy": 0.466,
+      "eval_all-nli-dev_dot_accuracy": 0.375,
+      "eval_all-nli-dev_euclidean_accuracy": 0.466,
+      "eval_all-nli-dev_manhattan_accuracy": 0.467,
+      "eval_all-nli-dev_max_accuracy": 0.467,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9327,
+      "eval_samples_per_second": 126.06,
+      "eval_steps_per_second": 7.942,
+      "step": 4500
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.08718598634004593,
+      "learning_rate": 1.4755555555555556e-05,
+      "loss": 3.4664,
+      "step": 4600
+    },
+    {
+      "epoch": 0.736,
+      "eval_all-nli-dev_cosine_accuracy": 0.44,
+      "eval_all-nli-dev_dot_accuracy": 0.307,
+      "eval_all-nli-dev_euclidean_accuracy": 0.44,
+      "eval_all-nli-dev_manhattan_accuracy": 0.455,
+      "eval_all-nli-dev_max_accuracy": 0.455,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.9594,
+      "eval_samples_per_second": 125.637,
+      "eval_steps_per_second": 7.915,
+      "step": 4600
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.03150181472301483,
+      "learning_rate": 1.3866666666666667e-05,
+      "loss": 3.4664,
+      "step": 4700
+    },
+    {
+      "epoch": 0.752,
+      "eval_all-nli-dev_cosine_accuracy": 0.469,
+      "eval_all-nli-dev_dot_accuracy": 0.336,
+      "eval_all-nli-dev_euclidean_accuracy": 0.469,
+      "eval_all-nli-dev_manhattan_accuracy": 0.481,
+      "eval_all-nli-dev_max_accuracy": 0.481,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9652,
+      "eval_samples_per_second": 125.546,
+      "eval_steps_per_second": 7.909,
+      "step": 4700
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.027570225298404694,
+      "learning_rate": 1.2977777777777777e-05,
+      "loss": 3.4659,
+      "step": 4800
+    },
+    {
+      "epoch": 0.768,
+      "eval_all-nli-dev_cosine_accuracy": 0.461,
+      "eval_all-nli-dev_dot_accuracy": 0.282,
+      "eval_all-nli-dev_euclidean_accuracy": 0.461,
+      "eval_all-nli-dev_manhattan_accuracy": 0.466,
+      "eval_all-nli-dev_max_accuracy": 0.466,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 8.0206,
+      "eval_samples_per_second": 124.678,
+      "eval_steps_per_second": 7.855,
+      "step": 4800
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.16807572543621063,
+      "learning_rate": 1.208888888888889e-05,
+      "loss": 3.466,
+      "step": 4900
+    },
+    {
+      "epoch": 0.784,
+      "eval_all-nli-dev_cosine_accuracy": 0.45,
+      "eval_all-nli-dev_dot_accuracy": 0.375,
+      "eval_all-nli-dev_euclidean_accuracy": 0.45,
+      "eval_all-nli-dev_manhattan_accuracy": 0.451,
+      "eval_all-nli-dev_max_accuracy": 0.451,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9772,
+      "eval_samples_per_second": 125.358,
+      "eval_steps_per_second": 7.898,
+      "step": 4900
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.03361041471362114,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 3.466,
+      "step": 5000
+    },
+    {
+      "epoch": 0.8,
+      "eval_all-nli-dev_cosine_accuracy": 0.464,
+      "eval_all-nli-dev_dot_accuracy": 0.374,
+      "eval_all-nli-dev_euclidean_accuracy": 0.464,
+      "eval_all-nli-dev_manhattan_accuracy": 0.473,
+      "eval_all-nli-dev_max_accuracy": 0.473,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9287,
+      "eval_samples_per_second": 126.123,
+      "eval_steps_per_second": 7.946,
+      "step": 5000
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.1332545429468155,
+      "learning_rate": 1.031111111111111e-05,
+      "loss": 3.4664,
+      "step": 5100
+    },
+    {
+      "epoch": 0.816,
+      "eval_all-nli-dev_cosine_accuracy": 0.44,
+      "eval_all-nli-dev_dot_accuracy": 0.341,
+      "eval_all-nli-dev_euclidean_accuracy": 0.44,
+      "eval_all-nli-dev_manhattan_accuracy": 0.44,
+      "eval_all-nli-dev_max_accuracy": 0.44,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9414,
+      "eval_samples_per_second": 125.922,
+      "eval_steps_per_second": 7.933,
+      "step": 5100
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.029825175181031227,
+      "learning_rate": 9.422222222222222e-06,
+      "loss": 3.4658,
+      "step": 5200
+    },
+    {
+      "epoch": 0.832,
+      "eval_all-nli-dev_cosine_accuracy": 0.496,
+      "eval_all-nli-dev_dot_accuracy": 0.356,
+      "eval_all-nli-dev_euclidean_accuracy": 0.496,
+      "eval_all-nli-dev_manhattan_accuracy": 0.497,
+      "eval_all-nli-dev_max_accuracy": 0.497,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9321,
+      "eval_samples_per_second": 126.07,
+      "eval_steps_per_second": 7.942,
+      "step": 5200
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.023120058700442314,
+      "learning_rate": 8.533333333333334e-06,
+      "loss": 3.4664,
+      "step": 5300
+    },
+    {
+      "epoch": 0.848,
+      "eval_all-nli-dev_cosine_accuracy": 0.464,
+      "eval_all-nli-dev_dot_accuracy": 0.321,
+      "eval_all-nli-dev_euclidean_accuracy": 0.464,
+      "eval_all-nli-dev_manhattan_accuracy": 0.474,
+      "eval_all-nli-dev_max_accuracy": 0.474,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9178,
+      "eval_samples_per_second": 126.297,
+      "eval_steps_per_second": 7.957,
+      "step": 5300
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.10328388214111328,
+      "learning_rate": 7.644444444444445e-06,
+      "loss": 3.4658,
+      "step": 5400
+    },
+    {
+      "epoch": 0.864,
+      "eval_all-nli-dev_cosine_accuracy": 0.446,
+      "eval_all-nli-dev_dot_accuracy": 0.309,
+      "eval_all-nli-dev_euclidean_accuracy": 0.446,
+      "eval_all-nli-dev_manhattan_accuracy": 0.449,
+      "eval_all-nli-dev_max_accuracy": 0.449,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 8.0066,
+      "eval_samples_per_second": 124.897,
+      "eval_steps_per_second": 7.869,
+      "step": 5400
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.03729160130023956,
+      "learning_rate": 6.755555555555555e-06,
+      "loss": 3.4662,
+      "step": 5500
+    },
+    {
+      "epoch": 0.88,
+      "eval_all-nli-dev_cosine_accuracy": 0.466,
+      "eval_all-nli-dev_dot_accuracy": 0.311,
+      "eval_all-nli-dev_euclidean_accuracy": 0.466,
+      "eval_all-nli-dev_manhattan_accuracy": 0.464,
+      "eval_all-nli-dev_max_accuracy": 0.466,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.964,
+      "eval_samples_per_second": 125.565,
+      "eval_steps_per_second": 7.911,
+      "step": 5500
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.02747642807662487,
+      "learning_rate": 5.866666666666667e-06,
+      "loss": 3.4663,
+      "step": 5600
+    },
+    {
+      "epoch": 0.896,
+      "eval_all-nli-dev_cosine_accuracy": 0.476,
+      "eval_all-nli-dev_dot_accuracy": 0.369,
+      "eval_all-nli-dev_euclidean_accuracy": 0.476,
+      "eval_all-nli-dev_manhattan_accuracy": 0.468,
+      "eval_all-nli-dev_max_accuracy": 0.476,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9426,
+      "eval_samples_per_second": 125.903,
+      "eval_steps_per_second": 7.932,
+      "step": 5600
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.053027376532554626,
+      "learning_rate": 4.977777777777778e-06,
+      "loss": 3.4667,
+      "step": 5700
+    },
+    {
+      "epoch": 0.912,
+      "eval_all-nli-dev_cosine_accuracy": 0.455,
+      "eval_all-nli-dev_dot_accuracy": 0.369,
+      "eval_all-nli-dev_euclidean_accuracy": 0.455,
+      "eval_all-nli-dev_manhattan_accuracy": 0.454,
+      "eval_all-nli-dev_max_accuracy": 0.455,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9874,
+      "eval_samples_per_second": 125.197,
+      "eval_steps_per_second": 7.887,
+      "step": 5700
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.02996170148253441,
+      "learning_rate": 4.088888888888889e-06,
+      "loss": 3.4669,
+      "step": 5800
+    },
+    {
+      "epoch": 0.928,
+      "eval_all-nli-dev_cosine_accuracy": 0.456,
+      "eval_all-nli-dev_dot_accuracy": 0.229,
+      "eval_all-nli-dev_euclidean_accuracy": 0.456,
+      "eval_all-nli-dev_manhattan_accuracy": 0.463,
+      "eval_all-nli-dev_max_accuracy": 0.463,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9568,
+      "eval_samples_per_second": 125.679,
+      "eval_steps_per_second": 7.918,
+      "step": 5800
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.05124541372060776,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 3.4657,
+      "step": 5900
+    },
+    {
+      "epoch": 0.944,
+      "eval_all-nli-dev_cosine_accuracy": 0.466,
+      "eval_all-nli-dev_dot_accuracy": 0.388,
+      "eval_all-nli-dev_euclidean_accuracy": 0.467,
+      "eval_all-nli-dev_manhattan_accuracy": 0.464,
+      "eval_all-nli-dev_max_accuracy": 0.467,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.9623,
+      "eval_samples_per_second": 125.591,
+      "eval_steps_per_second": 7.912,
+      "step": 5900
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.06664357334375381,
+      "learning_rate": 2.311111111111111e-06,
+      "loss": 3.4671,
+      "step": 6000
+    },
+    {
+      "epoch": 0.96,
+      "eval_all-nli-dev_cosine_accuracy": 0.452,
+      "eval_all-nli-dev_dot_accuracy": 0.33,
+      "eval_all-nli-dev_euclidean_accuracy": 0.452,
+      "eval_all-nli-dev_manhattan_accuracy": 0.456,
+      "eval_all-nli-dev_max_accuracy": 0.456,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.9667,
+      "eval_samples_per_second": 125.523,
+      "eval_steps_per_second": 7.908,
+      "step": 6000
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.18055689334869385,
+      "learning_rate": 1.4222222222222223e-06,
+      "loss": 2.9471,
+      "step": 6100
+    },
+    {
+      "epoch": 0.976,
+      "eval_all-nli-dev_cosine_accuracy": 0.479,
+      "eval_all-nli-dev_dot_accuracy": 0.378,
+      "eval_all-nli-dev_euclidean_accuracy": 0.479,
+      "eval_all-nli-dev_manhattan_accuracy": 0.484,
+      "eval_all-nli-dev_max_accuracy": 0.484,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9406,
+      "eval_samples_per_second": 125.936,
+      "eval_steps_per_second": 7.934,
+      "step": 6100
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 6250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e69823ce181dc26bc2db3e2da63ac6c5f79ba1c1c3395abb62624ff8fc42611
+size 5432

checkpoint-6200/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "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-6200/README.md

@@ -0,0 +1,489 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:100K<n<1M
+- loss:MultipleNegativesRankingLoss
+base_model: FacebookAI/xlm-roberta-large
+metrics:
+- cosine_accuracy
+- dot_accuracy
+- manhattan_accuracy
+- euclidean_accuracy
+- max_accuracy
+widget:
+- source_sentence: The boy scowls
+  sentences:
+  - Women are rollerblading.
+  - Boy playing baseball.
+  - The girls are watching tv
+- source_sentence: an eagle flies
+  sentences:
+  - A man brushes his teeth.
+  - He is playing a song.
+  - the baby is eating
+- source_sentence: A woman sings.
+  sentences:
+  - A man is with an animal.
+  - the animal is running
+  - There is a crowd
+- source_sentence: A bird flying.
+  sentences:
+  - A boy makes a mud pie.
+  - A man is on his feet.
+  - The boy is sitting
+- source_sentence: There's a dock
+  sentences:
+  - The girls eat the paper
+  - Five people on a path
+  - A boy is blowing bubbles.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on FacebookAI/xlm-roberta-large
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: all nli dev
+      type: all-nli-dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.452
+      name: Cosine Accuracy
+    - type: dot_accuracy
+      value: 0.34
+      name: Dot Accuracy
+    - type: manhattan_accuracy
+      value: 0.456
+      name: Manhattan Accuracy
+    - type: euclidean_accuracy
+      value: 0.452
+      name: Euclidean Accuracy
+    - type: max_accuracy
+      value: 0.456
+      name: Max Accuracy
+---
+
+# SentenceTransformer based on FacebookAI/xlm-roberta-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) dataset. It maps sentences & paragraphs to a 1024-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:** [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) <!-- at revision c23d21b0620b635a76227c604d44e43a9f0ee389 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    "There's a dock",
+    'The girls eat the paper',
+    'Five people on a path',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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
+
+#### Triplet
+* Dataset: `all-nli-dev`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric             | Value     |
+|:-------------------|:----------|
+| cosine_accuracy    | 0.452     |
+| dot_accuracy       | 0.34      |
+| manhattan_accuracy | 0.456     |
+| euclidean_accuracy | 0.452     |
+| **max_accuracy**   | **0.456** |
+
+<!--
+## 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
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 100,000 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                          | negative                                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 10.9 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.62 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.76 tokens</li><li>max: 55 tokens</li></ul> |
+* Samples:
+  | anchor                                                                     | positive                                         | negative                                                   |
+  |:---------------------------------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code>        | <code>A person is outdoors, on a horse.</code>   | <code>A person is at a diner, ordering an omelette.</code> |
+  | <code>Children smiling and waving at camera</code>                         | <code>There are children present</code>          | <code>The kids are frowning</code>                         |
+  | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>The boy skates down the sidewalk.</code>             |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 1,000 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 20.31 tokens</li><li>max: 83 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.71 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 11.39 tokens</li><li>max: 32 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                         | positive                                                    | negative                                                |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:--------------------------------------------------------|
+  | <code>Two women are embracing while holding to go packages.</code>                                                                                                             | <code>Two woman are holding packages.</code>                | <code>The men are fighting outside a deli.</code>       |
+  | <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code>        |
+  | <code>A man selling donuts to a customer during a world exhibition event held in the city of Angeles</code>                                                                    | <code>A man selling donuts to a customer.</code>            | <code>A woman drinks her coffee in a small cafe.</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `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`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `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`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `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
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch | Step | Training Loss | loss   | all-nli-dev_max_accuracy |
+|:-----:|:----:|:-------------:|:------:|:------------------------:|
+| 0     | 0    | -             | -      | 0.616                    |
+| 0.016 | 100  | 3.2768        | 1.8053 | 0.833                    |
+| 0.032 | 200  | 1.1697        | 1.2878 | 0.861                    |
+| 0.048 | 300  | 1.372         | 1.2466 | 0.861                    |
+| 0.064 | 400  | 1.0476        | 1.2291 | 0.863                    |
+| 0.08  | 500  | 0.8588        | 1.5259 | 0.838                    |
+| 0.096 | 600  | 2.9781        | 3.4309 | 0.463                    |
+| 0.112 | 700  | 3.4982        | 3.4309 | 0.457                    |
+| 0.128 | 800  | 3.467         | 3.4309 | 0.479                    |
+| 0.144 | 900  | 3.4665        | 3.4309 | 0.452                    |
+| 0.16  | 1000 | 3.4664        | 3.4309 | 0.477                    |
+| 0.176 | 1100 | 3.4663        | 3.4309 | 0.458                    |
+| 0.192 | 1200 | 3.4661        | 3.4309 | 0.462                    |
+| 0.208 | 1300 | 3.4658        | 3.4309 | 0.45                     |
+| 0.224 | 1400 | 3.4661        | 3.4309 | 0.481                    |
+| 0.24  | 1500 | 3.4877        | 3.4309 | 0.464                    |
+| 0.256 | 1600 | 3.4675        | 3.4309 | 0.462                    |
+| 0.272 | 1700 | 3.4665        | 3.4309 | 0.488                    |
+| 0.288 | 1800 | 3.4667        | 3.4309 | 0.492                    |
+| 0.304 | 1900 | 3.4664        | 3.4309 | 0.455                    |
+| 0.32  | 2000 | 3.4661        | 3.4309 | 0.453                    |
+| 0.336 | 2100 | 3.4666        | 3.4309 | 0.477                    |
+| 0.352 | 2200 | 3.4683        | 3.4309 | 0.48                     |
+| 0.368 | 2300 | 3.4663        | 3.4309 | 0.469                    |
+| 0.384 | 2400 | 3.4667        | 3.4309 | 0.448                    |
+| 0.4   | 2500 | 3.4669        | 3.4309 | 0.499                    |
+| 0.416 | 2600 | 3.4661        | 3.4309 | 0.453                    |
+| 0.432 | 2700 | 3.4656        | 3.4309 | 0.467                    |
+| 0.448 | 2800 | 3.4662        | 3.4309 | 0.507                    |
+| 0.464 | 2900 | 3.4902        | 3.4309 | 0.473                    |
+| 0.48  | 3000 | 3.4663        | 3.4309 | 0.469                    |
+| 0.496 | 3100 | 3.554         | 3.4309 | 0.46                     |
+| 0.512 | 3200 | 3.4664        | 3.4309 | 0.455                    |
+| 0.528 | 3300 | 3.4668        | 3.4309 | 0.46                     |
+| 0.544 | 3400 | 3.4661        | 3.4309 | 0.492                    |
+| 0.56  | 3500 | 3.4667        | 3.4309 | 0.432                    |
+| 0.576 | 3600 | 3.4668        | 3.4309 | 0.486                    |
+| 0.592 | 3700 | 3.4666        | 3.4309 | 0.469                    |
+| 0.608 | 3800 | 3.4669        | 3.4309 | 0.473                    |
+| 0.624 | 3900 | 3.4658        | 3.4309 | 0.487                    |
+| 0.64  | 4000 | 3.4663        | 3.4309 | 0.448                    |
+| 0.656 | 4100 | 3.4663        | 3.4309 | 0.465                    |
+| 0.672 | 4200 | 3.4664        | 3.4309 | 0.484                    |
+| 0.688 | 4300 | 3.4663        | 3.4309 | 0.469                    |
+| 0.704 | 4400 | 3.4661        | 3.4309 | 0.478                    |
+| 0.72  | 4500 | 3.4669        | 3.4309 | 0.467                    |
+| 0.736 | 4600 | 3.4664        | 3.4309 | 0.455                    |
+| 0.752 | 4700 | 3.4664        | 3.4309 | 0.481                    |
+| 0.768 | 4800 | 3.4659        | 3.4309 | 0.466                    |
+| 0.784 | 4900 | 3.466         | 3.4309 | 0.451                    |
+| 0.8   | 5000 | 3.466         | 3.4309 | 0.473                    |
+| 0.816 | 5100 | 3.4664        | 3.4309 | 0.44                     |
+| 0.832 | 5200 | 3.4658        | 3.4309 | 0.497                    |
+| 0.848 | 5300 | 3.4664        | 3.4309 | 0.474                    |
+| 0.864 | 5400 | 3.4658        | 3.4309 | 0.449                    |
+| 0.88  | 5500 | 3.4662        | 3.4309 | 0.466                    |
+| 0.896 | 5600 | 3.4663        | 3.4309 | 0.476                    |
+| 0.912 | 5700 | 3.4667        | 3.4309 | 0.455                    |
+| 0.928 | 5800 | 3.4669        | 3.4309 | 0.463                    |
+| 0.944 | 5900 | 3.4657        | 3.4309 | 0.467                    |
+| 0.96  | 6000 | 3.4671        | 3.4309 | 0.456                    |
+| 0.976 | 6100 | 2.9471        | 3.4309 | 0.484                    |
+| 0.992 | 6200 | 0.6929        | 3.4309 | 0.456                    |
+
+
+### Framework Versions
+- Python: 3.9.10
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.2
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.26.1
+- Datasets: 2.16.1
+- 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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-6200/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-6200/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.3.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-6200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c144211a6d3ee9fecfbfdb406e7868e4f77b2170cd8583c7fb7048ddd4e9af7
+size 2239607176

checkpoint-6200/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-6200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:505406a46b417fdcc3e006a51951b58c3a9383b12d64924f5eab975471c8ece6
+size 4471055801

checkpoint-6200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d48938e7adce189a12310181758cf3272e37b64a7b983a944da8dece26d7542a
+size 14244

checkpoint-6200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78525a6e10b9c5925f8336f7f8f26d7a6a28b1454f41dfa2b2beab77c11fff4
+size 1064

checkpoint-6200/sentence_bert_config.json

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

checkpoint-6200/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

checkpoint-6200/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-6200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

checkpoint-6200/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-6200/trainer_state.json

@@ -0,0 +1,1273 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.992,
+  "eval_steps": 100,
+  "global_step": 6200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016,
+      "grad_norm": 83.78450775146484,
+      "learning_rate": 7.44e-06,
+      "loss": 3.2768,
+      "step": 100
+    },
+    {
+      "epoch": 0.016,
+      "eval_all-nli-dev_cosine_accuracy": 0.815,
+      "eval_all-nli-dev_dot_accuracy": 0.316,
+      "eval_all-nli-dev_euclidean_accuracy": 0.804,
+      "eval_all-nli-dev_manhattan_accuracy": 0.833,
+      "eval_all-nli-dev_max_accuracy": 0.833,
+      "eval_loss": 1.8052657842636108,
+      "eval_runtime": 8.0216,
+      "eval_samples_per_second": 124.664,
+      "eval_steps_per_second": 7.854,
+      "step": 100
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 62.54200744628906,
+      "learning_rate": 1.544e-05,
+      "loss": 1.1697,
+      "step": 200
+    },
+    {
+      "epoch": 0.032,
+      "eval_all-nli-dev_cosine_accuracy": 0.842,
+      "eval_all-nli-dev_dot_accuracy": 0.171,
+      "eval_all-nli-dev_euclidean_accuracy": 0.838,
+      "eval_all-nli-dev_manhattan_accuracy": 0.861,
+      "eval_all-nli-dev_max_accuracy": 0.861,
+      "eval_loss": 1.2878086566925049,
+      "eval_runtime": 7.8831,
+      "eval_samples_per_second": 126.853,
+      "eval_steps_per_second": 7.992,
+      "step": 200
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 75.54035949707031,
+      "learning_rate": 2.344e-05,
+      "loss": 1.372,
+      "step": 300
+    },
+    {
+      "epoch": 0.048,
+      "eval_all-nli-dev_cosine_accuracy": 0.841,
+      "eval_all-nli-dev_dot_accuracy": 0.181,
+      "eval_all-nli-dev_euclidean_accuracy": 0.844,
+      "eval_all-nli-dev_manhattan_accuracy": 0.861,
+      "eval_all-nli-dev_max_accuracy": 0.861,
+      "eval_loss": 1.2466014623641968,
+      "eval_runtime": 7.8792,
+      "eval_samples_per_second": 126.916,
+      "eval_steps_per_second": 7.996,
+      "step": 300
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 33.85651779174805,
+      "learning_rate": 3.136e-05,
+      "loss": 1.0476,
+      "step": 400
+    },
+    {
+      "epoch": 0.064,
+      "eval_all-nli-dev_cosine_accuracy": 0.848,
+      "eval_all-nli-dev_dot_accuracy": 0.201,
+      "eval_all-nli-dev_euclidean_accuracy": 0.848,
+      "eval_all-nli-dev_manhattan_accuracy": 0.863,
+      "eval_all-nli-dev_max_accuracy": 0.863,
+      "eval_loss": 1.2291330099105835,
+      "eval_runtime": 7.8507,
+      "eval_samples_per_second": 127.378,
+      "eval_steps_per_second": 8.025,
+      "step": 400
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 27.536640167236328,
+      "learning_rate": 3.936e-05,
+      "loss": 0.8588,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "eval_all-nli-dev_cosine_accuracy": 0.821,
+      "eval_all-nli-dev_dot_accuracy": 0.213,
+      "eval_all-nli-dev_euclidean_accuracy": 0.828,
+      "eval_all-nli-dev_manhattan_accuracy": 0.838,
+      "eval_all-nli-dev_max_accuracy": 0.838,
+      "eval_loss": 1.5258921384811401,
+      "eval_runtime": 7.8331,
+      "eval_samples_per_second": 127.663,
+      "eval_steps_per_second": 8.043,
+      "step": 500
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.15947222709655762,
+      "learning_rate": 4.736000000000001e-05,
+      "loss": 2.9781,
+      "step": 600
+    },
+    {
+      "epoch": 0.096,
+      "eval_all-nli-dev_cosine_accuracy": 0.462,
+      "eval_all-nli-dev_dot_accuracy": 0.363,
+      "eval_all-nli-dev_euclidean_accuracy": 0.462,
+      "eval_all-nli-dev_manhattan_accuracy": 0.463,
+      "eval_all-nli-dev_max_accuracy": 0.463,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9535,
+      "eval_samples_per_second": 125.73,
+      "eval_steps_per_second": 7.921,
+      "step": 600
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.09273126721382141,
+      "learning_rate": 4.9404444444444447e-05,
+      "loss": 3.4982,
+      "step": 700
+    },
+    {
+      "epoch": 0.112,
+      "eval_all-nli-dev_cosine_accuracy": 0.449,
+      "eval_all-nli-dev_dot_accuracy": 0.381,
+      "eval_all-nli-dev_euclidean_accuracy": 0.449,
+      "eval_all-nli-dev_manhattan_accuracy": 0.457,
+      "eval_all-nli-dev_max_accuracy": 0.457,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.905,
+      "eval_samples_per_second": 126.501,
+      "eval_steps_per_second": 7.97,
+      "step": 700
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.047491393983364105,
+      "learning_rate": 4.851555555555556e-05,
+      "loss": 3.467,
+      "step": 800
+    },
+    {
+      "epoch": 0.128,
+      "eval_all-nli-dev_cosine_accuracy": 0.471,
+      "eval_all-nli-dev_dot_accuracy": 0.366,
+      "eval_all-nli-dev_euclidean_accuracy": 0.471,
+      "eval_all-nli-dev_manhattan_accuracy": 0.479,
+      "eval_all-nli-dev_max_accuracy": 0.479,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8623,
+      "eval_samples_per_second": 127.188,
+      "eval_steps_per_second": 8.013,
+      "step": 800
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.05457993969321251,
+      "learning_rate": 4.762666666666667e-05,
+      "loss": 3.4665,
+      "step": 900
+    },
+    {
+      "epoch": 0.144,
+      "eval_all-nli-dev_cosine_accuracy": 0.452,
+      "eval_all-nli-dev_dot_accuracy": 0.342,
+      "eval_all-nli-dev_euclidean_accuracy": 0.452,
+      "eval_all-nli-dev_manhattan_accuracy": 0.446,
+      "eval_all-nli-dev_max_accuracy": 0.452,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 8.0107,
+      "eval_samples_per_second": 124.832,
+      "eval_steps_per_second": 7.864,
+      "step": 900
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.03311806544661522,
+      "learning_rate": 4.673777777777778e-05,
+      "loss": 3.4664,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16,
+      "eval_all-nli-dev_cosine_accuracy": 0.477,
+      "eval_all-nli-dev_dot_accuracy": 0.352,
+      "eval_all-nli-dev_euclidean_accuracy": 0.477,
+      "eval_all-nli-dev_manhattan_accuracy": 0.468,
+      "eval_all-nli-dev_max_accuracy": 0.477,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9233,
+      "eval_samples_per_second": 126.21,
+      "eval_steps_per_second": 7.951,
+      "step": 1000
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.02707391045987606,
+      "learning_rate": 4.584888888888889e-05,
+      "loss": 3.4663,
+      "step": 1100
+    },
+    {
+      "epoch": 0.176,
+      "eval_all-nli-dev_cosine_accuracy": 0.458,
+      "eval_all-nli-dev_dot_accuracy": 0.376,
+      "eval_all-nli-dev_euclidean_accuracy": 0.458,
+      "eval_all-nli-dev_manhattan_accuracy": 0.452,
+      "eval_all-nli-dev_max_accuracy": 0.458,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8521,
+      "eval_samples_per_second": 127.354,
+      "eval_steps_per_second": 8.023,
+      "step": 1100
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.030668186023831367,
+      "learning_rate": 4.496e-05,
+      "loss": 3.4661,
+      "step": 1200
+    },
+    {
+      "epoch": 0.192,
+      "eval_all-nli-dev_cosine_accuracy": 0.46,
+      "eval_all-nli-dev_dot_accuracy": 0.39,
+      "eval_all-nli-dev_euclidean_accuracy": 0.46,
+      "eval_all-nli-dev_manhattan_accuracy": 0.462,
+      "eval_all-nli-dev_max_accuracy": 0.462,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 8.0488,
+      "eval_samples_per_second": 124.243,
+      "eval_steps_per_second": 7.827,
+      "step": 1200
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.04911087080836296,
+      "learning_rate": 4.4071111111111115e-05,
+      "loss": 3.4658,
+      "step": 1300
+    },
+    {
+      "epoch": 0.208,
+      "eval_all-nli-dev_cosine_accuracy": 0.441,
+      "eval_all-nli-dev_dot_accuracy": 0.338,
+      "eval_all-nli-dev_euclidean_accuracy": 0.441,
+      "eval_all-nli-dev_manhattan_accuracy": 0.45,
+      "eval_all-nli-dev_max_accuracy": 0.45,
+      "eval_loss": 3.4308857917785645,
+      "eval_runtime": 7.9015,
+      "eval_samples_per_second": 126.558,
+      "eval_steps_per_second": 7.973,
+      "step": 1300
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.02693816088140011,
+      "learning_rate": 4.3182222222222226e-05,
+      "loss": 3.4661,
+      "step": 1400
+    },
+    {
+      "epoch": 0.224,
+      "eval_all-nli-dev_cosine_accuracy": 0.475,
+      "eval_all-nli-dev_dot_accuracy": 0.31,
+      "eval_all-nli-dev_euclidean_accuracy": 0.475,
+      "eval_all-nli-dev_manhattan_accuracy": 0.481,
+      "eval_all-nli-dev_max_accuracy": 0.481,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.9424,
+      "eval_samples_per_second": 125.906,
+      "eval_steps_per_second": 7.932,
+      "step": 1400
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.17906944453716278,
+      "learning_rate": 4.229333333333334e-05,
+      "loss": 3.4877,
+      "step": 1500
+    },
+    {
+      "epoch": 0.24,
+      "eval_all-nli-dev_cosine_accuracy": 0.464,
+      "eval_all-nli-dev_dot_accuracy": 0.358,
+      "eval_all-nli-dev_euclidean_accuracy": 0.464,
+      "eval_all-nli-dev_manhattan_accuracy": 0.458,
+      "eval_all-nli-dev_max_accuracy": 0.464,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9335,
+      "eval_samples_per_second": 126.048,
+      "eval_steps_per_second": 7.941,
+      "step": 1500
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.07473237067461014,
+      "learning_rate": 4.140444444444445e-05,
+      "loss": 3.4675,
+      "step": 1600
+    },
+    {
+      "epoch": 0.256,
+      "eval_all-nli-dev_cosine_accuracy": 0.462,
+      "eval_all-nli-dev_dot_accuracy": 0.347,
+      "eval_all-nli-dev_euclidean_accuracy": 0.462,
+      "eval_all-nli-dev_manhattan_accuracy": 0.457,
+      "eval_all-nli-dev_max_accuracy": 0.462,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9155,
+      "eval_samples_per_second": 126.335,
+      "eval_steps_per_second": 7.959,
+      "step": 1600
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.06472893804311752,
+      "learning_rate": 4.051555555555556e-05,
+      "loss": 3.4665,
+      "step": 1700
+    },
+    {
+      "epoch": 0.272,
+      "eval_all-nli-dev_cosine_accuracy": 0.488,
+      "eval_all-nli-dev_dot_accuracy": 0.394,
+      "eval_all-nli-dev_euclidean_accuracy": 0.488,
+      "eval_all-nli-dev_manhattan_accuracy": 0.487,
+      "eval_all-nli-dev_max_accuracy": 0.488,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.7762,
+      "eval_samples_per_second": 128.597,
+      "eval_steps_per_second": 8.102,
+      "step": 1700
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.05817211791872978,
+      "learning_rate": 3.9626666666666664e-05,
+      "loss": 3.4667,
+      "step": 1800
+    },
+    {
+      "epoch": 0.288,
+      "eval_all-nli-dev_cosine_accuracy": 0.492,
+      "eval_all-nli-dev_dot_accuracy": 0.396,
+      "eval_all-nli-dev_euclidean_accuracy": 0.492,
+      "eval_all-nli-dev_manhattan_accuracy": 0.483,
+      "eval_all-nli-dev_max_accuracy": 0.492,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8429,
+      "eval_samples_per_second": 127.504,
+      "eval_steps_per_second": 8.033,
+      "step": 1800
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.06118469312787056,
+      "learning_rate": 3.8737777777777776e-05,
+      "loss": 3.4664,
+      "step": 1900
+    },
+    {
+      "epoch": 0.304,
+      "eval_all-nli-dev_cosine_accuracy": 0.452,
+      "eval_all-nli-dev_dot_accuracy": 0.377,
+      "eval_all-nli-dev_euclidean_accuracy": 0.452,
+      "eval_all-nli-dev_manhattan_accuracy": 0.455,
+      "eval_all-nli-dev_max_accuracy": 0.455,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8193,
+      "eval_samples_per_second": 127.888,
+      "eval_steps_per_second": 8.057,
+      "step": 1900
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.034288015216588974,
+      "learning_rate": 3.784888888888889e-05,
+      "loss": 3.4661,
+      "step": 2000
+    },
+    {
+      "epoch": 0.32,
+      "eval_all-nli-dev_cosine_accuracy": 0.446,
+      "eval_all-nli-dev_dot_accuracy": 0.35,
+      "eval_all-nli-dev_euclidean_accuracy": 0.446,
+      "eval_all-nli-dev_manhattan_accuracy": 0.453,
+      "eval_all-nli-dev_max_accuracy": 0.453,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8176,
+      "eval_samples_per_second": 127.916,
+      "eval_steps_per_second": 8.059,
+      "step": 2000
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.06111547723412514,
+      "learning_rate": 3.696e-05,
+      "loss": 3.4666,
+      "step": 2100
+    },
+    {
+      "epoch": 0.336,
+      "eval_all-nli-dev_cosine_accuracy": 0.469,
+      "eval_all-nli-dev_dot_accuracy": 0.39,
+      "eval_all-nli-dev_euclidean_accuracy": 0.469,
+      "eval_all-nli-dev_manhattan_accuracy": 0.477,
+      "eval_all-nli-dev_max_accuracy": 0.477,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.8728,
+      "eval_samples_per_second": 127.02,
+      "eval_steps_per_second": 8.002,
+      "step": 2100
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.06624756008386612,
+      "learning_rate": 3.607111111111111e-05,
+      "loss": 3.4683,
+      "step": 2200
+    },
+    {
+      "epoch": 0.352,
+      "eval_all-nli-dev_cosine_accuracy": 0.478,
+      "eval_all-nli-dev_dot_accuracy": 0.338,
+      "eval_all-nli-dev_euclidean_accuracy": 0.478,
+      "eval_all-nli-dev_manhattan_accuracy": 0.48,
+      "eval_all-nli-dev_max_accuracy": 0.48,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9247,
+      "eval_samples_per_second": 126.188,
+      "eval_steps_per_second": 7.95,
+      "step": 2200
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.031209247186779976,
+      "learning_rate": 3.518222222222222e-05,
+      "loss": 3.4663,
+      "step": 2300
+    },
+    {
+      "epoch": 0.368,
+      "eval_all-nli-dev_cosine_accuracy": 0.469,
+      "eval_all-nli-dev_dot_accuracy": 0.312,
+      "eval_all-nli-dev_euclidean_accuracy": 0.469,
+      "eval_all-nli-dev_manhattan_accuracy": 0.464,
+      "eval_all-nli-dev_max_accuracy": 0.469,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8393,
+      "eval_samples_per_second": 127.562,
+      "eval_steps_per_second": 8.036,
+      "step": 2300
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.133990079164505,
+      "learning_rate": 3.429333333333333e-05,
+      "loss": 3.4667,
+      "step": 2400
+    },
+    {
+      "epoch": 0.384,
+      "eval_all-nli-dev_cosine_accuracy": 0.448,
+      "eval_all-nli-dev_dot_accuracy": 0.404,
+      "eval_all-nli-dev_euclidean_accuracy": 0.448,
+      "eval_all-nli-dev_manhattan_accuracy": 0.445,
+      "eval_all-nli-dev_max_accuracy": 0.448,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 8.021,
+      "eval_samples_per_second": 124.672,
+      "eval_steps_per_second": 7.854,
+      "step": 2400
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.04892706498503685,
+      "learning_rate": 3.3404444444444444e-05,
+      "loss": 3.4669,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4,
+      "eval_all-nli-dev_cosine_accuracy": 0.499,
+      "eval_all-nli-dev_dot_accuracy": 0.365,
+      "eval_all-nli-dev_euclidean_accuracy": 0.499,
+      "eval_all-nli-dev_manhattan_accuracy": 0.492,
+      "eval_all-nli-dev_max_accuracy": 0.499,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.8451,
+      "eval_samples_per_second": 127.468,
+      "eval_steps_per_second": 8.03,
+      "step": 2500
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.053150493651628494,
+      "learning_rate": 3.2515555555555555e-05,
+      "loss": 3.4661,
+      "step": 2600
+    },
+    {
+      "epoch": 0.416,
+      "eval_all-nli-dev_cosine_accuracy": 0.453,
+      "eval_all-nli-dev_dot_accuracy": 0.349,
+      "eval_all-nli-dev_euclidean_accuracy": 0.453,
+      "eval_all-nli-dev_manhattan_accuracy": 0.45,
+      "eval_all-nli-dev_max_accuracy": 0.453,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9334,
+      "eval_samples_per_second": 126.05,
+      "eval_steps_per_second": 7.941,
+      "step": 2600
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.09555792808532715,
+      "learning_rate": 3.1626666666666667e-05,
+      "loss": 3.4656,
+      "step": 2700
+    },
+    {
+      "epoch": 0.432,
+      "eval_all-nli-dev_cosine_accuracy": 0.466,
+      "eval_all-nli-dev_dot_accuracy": 0.336,
+      "eval_all-nli-dev_euclidean_accuracy": 0.466,
+      "eval_all-nli-dev_manhattan_accuracy": 0.467,
+      "eval_all-nli-dev_max_accuracy": 0.467,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8562,
+      "eval_samples_per_second": 127.287,
+      "eval_steps_per_second": 8.019,
+      "step": 2700
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.01744948886334896,
+      "learning_rate": 3.0737777777777785e-05,
+      "loss": 3.4662,
+      "step": 2800
+    },
+    {
+      "epoch": 0.448,
+      "eval_all-nli-dev_cosine_accuracy": 0.506,
+      "eval_all-nli-dev_dot_accuracy": 0.4,
+      "eval_all-nli-dev_euclidean_accuracy": 0.506,
+      "eval_all-nli-dev_manhattan_accuracy": 0.507,
+      "eval_all-nli-dev_max_accuracy": 0.507,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8617,
+      "eval_samples_per_second": 127.199,
+      "eval_steps_per_second": 8.014,
+      "step": 2800
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.2527749538421631,
+      "learning_rate": 2.986666666666667e-05,
+      "loss": 3.4902,
+      "step": 2900
+    },
+    {
+      "epoch": 0.464,
+      "eval_all-nli-dev_cosine_accuracy": 0.463,
+      "eval_all-nli-dev_dot_accuracy": 0.338,
+      "eval_all-nli-dev_euclidean_accuracy": 0.463,
+      "eval_all-nli-dev_manhattan_accuracy": 0.473,
+      "eval_all-nli-dev_max_accuracy": 0.473,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8074,
+      "eval_samples_per_second": 128.083,
+      "eval_steps_per_second": 8.069,
+      "step": 2900
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.02826513536274433,
+      "learning_rate": 2.897777777777778e-05,
+      "loss": 3.4663,
+      "step": 3000
+    },
+    {
+      "epoch": 0.48,
+      "eval_all-nli-dev_cosine_accuracy": 0.454,
+      "eval_all-nli-dev_dot_accuracy": 0.338,
+      "eval_all-nli-dev_euclidean_accuracy": 0.454,
+      "eval_all-nli-dev_manhattan_accuracy": 0.469,
+      "eval_all-nli-dev_max_accuracy": 0.469,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8421,
+      "eval_samples_per_second": 127.516,
+      "eval_steps_per_second": 8.034,
+      "step": 3000
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.07985329627990723,
+      "learning_rate": 2.8088888888888893e-05,
+      "loss": 3.554,
+      "step": 3100
+    },
+    {
+      "epoch": 0.496,
+      "eval_all-nli-dev_cosine_accuracy": 0.456,
+      "eval_all-nli-dev_dot_accuracy": 0.359,
+      "eval_all-nli-dev_euclidean_accuracy": 0.456,
+      "eval_all-nli-dev_manhattan_accuracy": 0.46,
+      "eval_all-nli-dev_max_accuracy": 0.46,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8756,
+      "eval_samples_per_second": 126.975,
+      "eval_steps_per_second": 7.999,
+      "step": 3100
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.1259102076292038,
+      "learning_rate": 2.7200000000000004e-05,
+      "loss": 3.4664,
+      "step": 3200
+    },
+    {
+      "epoch": 0.512,
+      "eval_all-nli-dev_cosine_accuracy": 0.455,
+      "eval_all-nli-dev_dot_accuracy": 0.257,
+      "eval_all-nli-dev_euclidean_accuracy": 0.455,
+      "eval_all-nli-dev_manhattan_accuracy": 0.454,
+      "eval_all-nli-dev_max_accuracy": 0.455,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9019,
+      "eval_samples_per_second": 126.552,
+      "eval_steps_per_second": 7.973,
+      "step": 3200
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.06493524461984634,
+      "learning_rate": 2.6311111111111115e-05,
+      "loss": 3.4668,
+      "step": 3300
+    },
+    {
+      "epoch": 0.528,
+      "eval_all-nli-dev_cosine_accuracy": 0.448,
+      "eval_all-nli-dev_dot_accuracy": 0.383,
+      "eval_all-nli-dev_euclidean_accuracy": 0.448,
+      "eval_all-nli-dev_manhattan_accuracy": 0.46,
+      "eval_all-nli-dev_max_accuracy": 0.46,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9333,
+      "eval_samples_per_second": 126.051,
+      "eval_steps_per_second": 7.941,
+      "step": 3300
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.0680716335773468,
+      "learning_rate": 2.5422222222222227e-05,
+      "loss": 3.4661,
+      "step": 3400
+    },
+    {
+      "epoch": 0.544,
+      "eval_all-nli-dev_cosine_accuracy": 0.492,
+      "eval_all-nli-dev_dot_accuracy": 0.407,
+      "eval_all-nli-dev_euclidean_accuracy": 0.492,
+      "eval_all-nli-dev_manhattan_accuracy": 0.481,
+      "eval_all-nli-dev_max_accuracy": 0.492,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9192,
+      "eval_samples_per_second": 126.276,
+      "eval_steps_per_second": 7.955,
+      "step": 3400
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.04947361350059509,
+      "learning_rate": 2.4533333333333334e-05,
+      "loss": 3.4667,
+      "step": 3500
+    },
+    {
+      "epoch": 0.56,
+      "eval_all-nli-dev_cosine_accuracy": 0.432,
+      "eval_all-nli-dev_dot_accuracy": 0.391,
+      "eval_all-nli-dev_euclidean_accuracy": 0.432,
+      "eval_all-nli-dev_manhattan_accuracy": 0.427,
+      "eval_all-nli-dev_max_accuracy": 0.432,
+      "eval_loss": 3.4308857917785645,
+      "eval_runtime": 7.8702,
+      "eval_samples_per_second": 127.061,
+      "eval_steps_per_second": 8.005,
+      "step": 3500
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.07287462800741196,
+      "learning_rate": 2.3644444444444446e-05,
+      "loss": 3.4668,
+      "step": 3600
+    },
+    {
+      "epoch": 0.576,
+      "eval_all-nli-dev_cosine_accuracy": 0.482,
+      "eval_all-nli-dev_dot_accuracy": 0.374,
+      "eval_all-nli-dev_euclidean_accuracy": 0.482,
+      "eval_all-nli-dev_manhattan_accuracy": 0.486,
+      "eval_all-nli-dev_max_accuracy": 0.486,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.8562,
+      "eval_samples_per_second": 127.288,
+      "eval_steps_per_second": 8.019,
+      "step": 3600
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.028324555605649948,
+      "learning_rate": 2.2755555555555557e-05,
+      "loss": 3.4666,
+      "step": 3700
+    },
+    {
+      "epoch": 0.592,
+      "eval_all-nli-dev_cosine_accuracy": 0.469,
+      "eval_all-nli-dev_dot_accuracy": 0.351,
+      "eval_all-nli-dev_euclidean_accuracy": 0.469,
+      "eval_all-nli-dev_manhattan_accuracy": 0.46,
+      "eval_all-nli-dev_max_accuracy": 0.469,
+      "eval_loss": 3.4308865070343018,
+      "eval_runtime": 7.879,
+      "eval_samples_per_second": 126.919,
+      "eval_steps_per_second": 7.996,
+      "step": 3700
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.04251887649297714,
+      "learning_rate": 2.186666666666667e-05,
+      "loss": 3.4669,
+      "step": 3800
+    },
+    {
+      "epoch": 0.608,
+      "eval_all-nli-dev_cosine_accuracy": 0.473,
+      "eval_all-nli-dev_dot_accuracy": 0.369,
+      "eval_all-nli-dev_euclidean_accuracy": 0.473,
+      "eval_all-nli-dev_manhattan_accuracy": 0.467,
+      "eval_all-nli-dev_max_accuracy": 0.473,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9346,
+      "eval_samples_per_second": 126.031,
+      "eval_steps_per_second": 7.94,
+      "step": 3800
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.01685403846204281,
+      "learning_rate": 2.097777777777778e-05,
+      "loss": 3.4658,
+      "step": 3900
+    },
+    {
+      "epoch": 0.624,
+      "eval_all-nli-dev_cosine_accuracy": 0.487,
+      "eval_all-nli-dev_dot_accuracy": 0.333,
+      "eval_all-nli-dev_euclidean_accuracy": 0.487,
+      "eval_all-nli-dev_manhattan_accuracy": 0.486,
+      "eval_all-nli-dev_max_accuracy": 0.487,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 8.0469,
+      "eval_samples_per_second": 124.272,
+      "eval_steps_per_second": 7.829,
+      "step": 3900
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.16402187943458557,
+      "learning_rate": 2.008888888888889e-05,
+      "loss": 3.4663,
+      "step": 4000
+    },
+    {
+      "epoch": 0.64,
+      "eval_all-nli-dev_cosine_accuracy": 0.448,
+      "eval_all-nli-dev_dot_accuracy": 0.355,
+      "eval_all-nli-dev_euclidean_accuracy": 0.448,
+      "eval_all-nli-dev_manhattan_accuracy": 0.442,
+      "eval_all-nli-dev_max_accuracy": 0.448,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9755,
+      "eval_samples_per_second": 125.384,
+      "eval_steps_per_second": 7.899,
+      "step": 4000
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.08633382618427277,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 3.4663,
+      "step": 4100
+    },
+    {
+      "epoch": 0.656,
+      "eval_all-nli-dev_cosine_accuracy": 0.463,
+      "eval_all-nli-dev_dot_accuracy": 0.3,
+      "eval_all-nli-dev_euclidean_accuracy": 0.463,
+      "eval_all-nli-dev_manhattan_accuracy": 0.465,
+      "eval_all-nli-dev_max_accuracy": 0.465,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9722,
+      "eval_samples_per_second": 125.436,
+      "eval_steps_per_second": 7.902,
+      "step": 4100
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.08357453346252441,
+      "learning_rate": 1.8311111111111114e-05,
+      "loss": 3.4664,
+      "step": 4200
+    },
+    {
+      "epoch": 0.672,
+      "eval_all-nli-dev_cosine_accuracy": 0.48,
+      "eval_all-nli-dev_dot_accuracy": 0.343,
+      "eval_all-nli-dev_euclidean_accuracy": 0.48,
+      "eval_all-nli-dev_manhattan_accuracy": 0.484,
+      "eval_all-nli-dev_max_accuracy": 0.484,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9287,
+      "eval_samples_per_second": 126.125,
+      "eval_steps_per_second": 7.946,
+      "step": 4200
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.20162004232406616,
+      "learning_rate": 1.7422222222222222e-05,
+      "loss": 3.4663,
+      "step": 4300
+    },
+    {
+      "epoch": 0.688,
+      "eval_all-nli-dev_cosine_accuracy": 0.451,
+      "eval_all-nli-dev_dot_accuracy": 0.354,
+      "eval_all-nli-dev_euclidean_accuracy": 0.451,
+      "eval_all-nli-dev_manhattan_accuracy": 0.469,
+      "eval_all-nli-dev_max_accuracy": 0.469,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9242,
+      "eval_samples_per_second": 126.195,
+      "eval_steps_per_second": 7.95,
+      "step": 4300
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.17491748929023743,
+      "learning_rate": 1.6533333333333333e-05,
+      "loss": 3.4661,
+      "step": 4400
+    },
+    {
+      "epoch": 0.704,
+      "eval_all-nli-dev_cosine_accuracy": 0.47,
+      "eval_all-nli-dev_dot_accuracy": 0.367,
+      "eval_all-nli-dev_euclidean_accuracy": 0.47,
+      "eval_all-nli-dev_manhattan_accuracy": 0.478,
+      "eval_all-nli-dev_max_accuracy": 0.478,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.989,
+      "eval_samples_per_second": 125.172,
+      "eval_steps_per_second": 7.886,
+      "step": 4400
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.1597195565700531,
+      "learning_rate": 1.5644444444444444e-05,
+      "loss": 3.4669,
+      "step": 4500
+    },
+    {
+      "epoch": 0.72,
+      "eval_all-nli-dev_cosine_accuracy": 0.466,
+      "eval_all-nli-dev_dot_accuracy": 0.375,
+      "eval_all-nli-dev_euclidean_accuracy": 0.466,
+      "eval_all-nli-dev_manhattan_accuracy": 0.467,
+      "eval_all-nli-dev_max_accuracy": 0.467,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9327,
+      "eval_samples_per_second": 126.06,
+      "eval_steps_per_second": 7.942,
+      "step": 4500
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.08718598634004593,
+      "learning_rate": 1.4755555555555556e-05,
+      "loss": 3.4664,
+      "step": 4600
+    },
+    {
+      "epoch": 0.736,
+      "eval_all-nli-dev_cosine_accuracy": 0.44,
+      "eval_all-nli-dev_dot_accuracy": 0.307,
+      "eval_all-nli-dev_euclidean_accuracy": 0.44,
+      "eval_all-nli-dev_manhattan_accuracy": 0.455,
+      "eval_all-nli-dev_max_accuracy": 0.455,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.9594,
+      "eval_samples_per_second": 125.637,
+      "eval_steps_per_second": 7.915,
+      "step": 4600
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.03150181472301483,
+      "learning_rate": 1.3866666666666667e-05,
+      "loss": 3.4664,
+      "step": 4700
+    },
+    {
+      "epoch": 0.752,
+      "eval_all-nli-dev_cosine_accuracy": 0.469,
+      "eval_all-nli-dev_dot_accuracy": 0.336,
+      "eval_all-nli-dev_euclidean_accuracy": 0.469,
+      "eval_all-nli-dev_manhattan_accuracy": 0.481,
+      "eval_all-nli-dev_max_accuracy": 0.481,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9652,
+      "eval_samples_per_second": 125.546,
+      "eval_steps_per_second": 7.909,
+      "step": 4700
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.027570225298404694,
+      "learning_rate": 1.2977777777777777e-05,
+      "loss": 3.4659,
+      "step": 4800
+    },
+    {
+      "epoch": 0.768,
+      "eval_all-nli-dev_cosine_accuracy": 0.461,
+      "eval_all-nli-dev_dot_accuracy": 0.282,
+      "eval_all-nli-dev_euclidean_accuracy": 0.461,
+      "eval_all-nli-dev_manhattan_accuracy": 0.466,
+      "eval_all-nli-dev_max_accuracy": 0.466,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 8.0206,
+      "eval_samples_per_second": 124.678,
+      "eval_steps_per_second": 7.855,
+      "step": 4800
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.16807572543621063,
+      "learning_rate": 1.208888888888889e-05,
+      "loss": 3.466,
+      "step": 4900
+    },
+    {
+      "epoch": 0.784,
+      "eval_all-nli-dev_cosine_accuracy": 0.45,
+      "eval_all-nli-dev_dot_accuracy": 0.375,
+      "eval_all-nli-dev_euclidean_accuracy": 0.45,
+      "eval_all-nli-dev_manhattan_accuracy": 0.451,
+      "eval_all-nli-dev_max_accuracy": 0.451,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9772,
+      "eval_samples_per_second": 125.358,
+      "eval_steps_per_second": 7.898,
+      "step": 4900
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.03361041471362114,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 3.466,
+      "step": 5000
+    },
+    {
+      "epoch": 0.8,
+      "eval_all-nli-dev_cosine_accuracy": 0.464,
+      "eval_all-nli-dev_dot_accuracy": 0.374,
+      "eval_all-nli-dev_euclidean_accuracy": 0.464,
+      "eval_all-nli-dev_manhattan_accuracy": 0.473,
+      "eval_all-nli-dev_max_accuracy": 0.473,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9287,
+      "eval_samples_per_second": 126.123,
+      "eval_steps_per_second": 7.946,
+      "step": 5000
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.1332545429468155,
+      "learning_rate": 1.031111111111111e-05,
+      "loss": 3.4664,
+      "step": 5100
+    },
+    {
+      "epoch": 0.816,
+      "eval_all-nli-dev_cosine_accuracy": 0.44,
+      "eval_all-nli-dev_dot_accuracy": 0.341,
+      "eval_all-nli-dev_euclidean_accuracy": 0.44,
+      "eval_all-nli-dev_manhattan_accuracy": 0.44,
+      "eval_all-nli-dev_max_accuracy": 0.44,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9414,
+      "eval_samples_per_second": 125.922,
+      "eval_steps_per_second": 7.933,
+      "step": 5100
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.029825175181031227,
+      "learning_rate": 9.422222222222222e-06,
+      "loss": 3.4658,
+      "step": 5200
+    },
+    {
+      "epoch": 0.832,
+      "eval_all-nli-dev_cosine_accuracy": 0.496,
+      "eval_all-nli-dev_dot_accuracy": 0.356,
+      "eval_all-nli-dev_euclidean_accuracy": 0.496,
+      "eval_all-nli-dev_manhattan_accuracy": 0.497,
+      "eval_all-nli-dev_max_accuracy": 0.497,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9321,
+      "eval_samples_per_second": 126.07,
+      "eval_steps_per_second": 7.942,
+      "step": 5200
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.023120058700442314,
+      "learning_rate": 8.533333333333334e-06,
+      "loss": 3.4664,
+      "step": 5300
+    },
+    {
+      "epoch": 0.848,
+      "eval_all-nli-dev_cosine_accuracy": 0.464,
+      "eval_all-nli-dev_dot_accuracy": 0.321,
+      "eval_all-nli-dev_euclidean_accuracy": 0.464,
+      "eval_all-nli-dev_manhattan_accuracy": 0.474,
+      "eval_all-nli-dev_max_accuracy": 0.474,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9178,
+      "eval_samples_per_second": 126.297,
+      "eval_steps_per_second": 7.957,
+      "step": 5300
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.10328388214111328,
+      "learning_rate": 7.644444444444445e-06,
+      "loss": 3.4658,
+      "step": 5400
+    },
+    {
+      "epoch": 0.864,
+      "eval_all-nli-dev_cosine_accuracy": 0.446,
+      "eval_all-nli-dev_dot_accuracy": 0.309,
+      "eval_all-nli-dev_euclidean_accuracy": 0.446,
+      "eval_all-nli-dev_manhattan_accuracy": 0.449,
+      "eval_all-nli-dev_max_accuracy": 0.449,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 8.0066,
+      "eval_samples_per_second": 124.897,
+      "eval_steps_per_second": 7.869,
+      "step": 5400
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.03729160130023956,
+      "learning_rate": 6.755555555555555e-06,
+      "loss": 3.4662,
+      "step": 5500
+    },
+    {
+      "epoch": 0.88,
+      "eval_all-nli-dev_cosine_accuracy": 0.466,
+      "eval_all-nli-dev_dot_accuracy": 0.311,
+      "eval_all-nli-dev_euclidean_accuracy": 0.466,
+      "eval_all-nli-dev_manhattan_accuracy": 0.464,
+      "eval_all-nli-dev_max_accuracy": 0.466,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.964,
+      "eval_samples_per_second": 125.565,
+      "eval_steps_per_second": 7.911,
+      "step": 5500
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.02747642807662487,
+      "learning_rate": 5.866666666666667e-06,
+      "loss": 3.4663,
+      "step": 5600
+    },
+    {
+      "epoch": 0.896,
+      "eval_all-nli-dev_cosine_accuracy": 0.476,
+      "eval_all-nli-dev_dot_accuracy": 0.369,
+      "eval_all-nli-dev_euclidean_accuracy": 0.476,
+      "eval_all-nli-dev_manhattan_accuracy": 0.468,
+      "eval_all-nli-dev_max_accuracy": 0.476,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9426,
+      "eval_samples_per_second": 125.903,
+      "eval_steps_per_second": 7.932,
+      "step": 5600
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.053027376532554626,
+      "learning_rate": 4.977777777777778e-06,
+      "loss": 3.4667,
+      "step": 5700
+    },
+    {
+      "epoch": 0.912,
+      "eval_all-nli-dev_cosine_accuracy": 0.455,
+      "eval_all-nli-dev_dot_accuracy": 0.369,
+      "eval_all-nli-dev_euclidean_accuracy": 0.455,
+      "eval_all-nli-dev_manhattan_accuracy": 0.454,
+      "eval_all-nli-dev_max_accuracy": 0.455,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9874,
+      "eval_samples_per_second": 125.197,
+      "eval_steps_per_second": 7.887,
+      "step": 5700
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.02996170148253441,
+      "learning_rate": 4.088888888888889e-06,
+      "loss": 3.4669,
+      "step": 5800
+    },
+    {
+      "epoch": 0.928,
+      "eval_all-nli-dev_cosine_accuracy": 0.456,
+      "eval_all-nli-dev_dot_accuracy": 0.229,
+      "eval_all-nli-dev_euclidean_accuracy": 0.456,
+      "eval_all-nli-dev_manhattan_accuracy": 0.463,
+      "eval_all-nli-dev_max_accuracy": 0.463,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9568,
+      "eval_samples_per_second": 125.679,
+      "eval_steps_per_second": 7.918,
+      "step": 5800
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.05124541372060776,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 3.4657,
+      "step": 5900
+    },
+    {
+      "epoch": 0.944,
+      "eval_all-nli-dev_cosine_accuracy": 0.466,
+      "eval_all-nli-dev_dot_accuracy": 0.388,
+      "eval_all-nli-dev_euclidean_accuracy": 0.467,
+      "eval_all-nli-dev_manhattan_accuracy": 0.464,
+      "eval_all-nli-dev_max_accuracy": 0.467,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.9623,
+      "eval_samples_per_second": 125.591,
+      "eval_steps_per_second": 7.912,
+      "step": 5900
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.06664357334375381,
+      "learning_rate": 2.311111111111111e-06,
+      "loss": 3.4671,
+      "step": 6000
+    },
+    {
+      "epoch": 0.96,
+      "eval_all-nli-dev_cosine_accuracy": 0.452,
+      "eval_all-nli-dev_dot_accuracy": 0.33,
+      "eval_all-nli-dev_euclidean_accuracy": 0.452,
+      "eval_all-nli-dev_manhattan_accuracy": 0.456,
+      "eval_all-nli-dev_max_accuracy": 0.456,
+      "eval_loss": 3.4308862686157227,
+      "eval_runtime": 7.9667,
+      "eval_samples_per_second": 125.523,
+      "eval_steps_per_second": 7.908,
+      "step": 6000
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.18055689334869385,
+      "learning_rate": 1.4222222222222223e-06,
+      "loss": 2.9471,
+      "step": 6100
+    },
+    {
+      "epoch": 0.976,
+      "eval_all-nli-dev_cosine_accuracy": 0.479,
+      "eval_all-nli-dev_dot_accuracy": 0.378,
+      "eval_all-nli-dev_euclidean_accuracy": 0.479,
+      "eval_all-nli-dev_manhattan_accuracy": 0.484,
+      "eval_all-nli-dev_max_accuracy": 0.484,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9406,
+      "eval_samples_per_second": 125.936,
+      "eval_steps_per_second": 7.934,
+      "step": 6100
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.10885396599769592,
+      "learning_rate": 5.333333333333333e-07,
+      "loss": 0.6929,
+      "step": 6200
+    },
+    {
+      "epoch": 0.992,
+      "eval_all-nli-dev_cosine_accuracy": 0.452,
+      "eval_all-nli-dev_dot_accuracy": 0.34,
+      "eval_all-nli-dev_euclidean_accuracy": 0.452,
+      "eval_all-nli-dev_manhattan_accuracy": 0.456,
+      "eval_all-nli-dev_max_accuracy": 0.456,
+      "eval_loss": 3.4308860301971436,
+      "eval_runtime": 7.9933,
+      "eval_samples_per_second": 125.105,
+      "eval_steps_per_second": 7.882,
+      "step": 6200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 6250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e69823ce181dc26bc2db3e2da63ac6c5f79ba1c1c3395abb62624ff8fc42611
+size 5432

final/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "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
+}

final/README.md

@@ -0,0 +1,524 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:100K<n<1M
+- loss:MultipleNegativesRankingLoss
+base_model: FacebookAI/xlm-roberta-large
+metrics:
+- cosine_accuracy
+- dot_accuracy
+- manhattan_accuracy
+- euclidean_accuracy
+- max_accuracy
+widget:
+- source_sentence: The boy scowls
+  sentences:
+  - People are around a fire
+  - Boy playing baseball.
+  - The girls are at school.
+- source_sentence: an eagle flies
+  sentences:
+  - A man floats up a ladder.
+  - He is playing a song.
+  - The t-shirt is white.
+- source_sentence: A woman sings.
+  sentences:
+  - The woman is outdoors.
+  - the animal is running
+  - A man is playing indoors.
+- source_sentence: A bird flying.
+  sentences:
+  - No one is on a canoe.
+  - A man is on his feet.
+  - Two men listen to music.
+- source_sentence: There's a dock
+  sentences:
+  - The man is performing.
+  - Five people on a path
+  - The elephant sits on a dog
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on FacebookAI/xlm-roberta-large
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: all nli dev
+      type: all-nli-dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.452
+      name: Cosine Accuracy
+    - type: dot_accuracy
+      value: 0.34
+      name: Dot Accuracy
+    - type: manhattan_accuracy
+      value: 0.456
+      name: Manhattan Accuracy
+    - type: euclidean_accuracy
+      value: 0.452
+      name: Euclidean Accuracy
+    - type: max_accuracy
+      value: 0.456
+      name: Max Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: all nli test
+      type: all-nli-test
+    metrics:
+    - type: cosine_accuracy
+      value: 0.481
+      name: Cosine Accuracy
+    - type: dot_accuracy
+      value: 0.364
+      name: Dot Accuracy
+    - type: manhattan_accuracy
+      value: 0.48
+      name: Manhattan Accuracy
+    - type: euclidean_accuracy
+      value: 0.481
+      name: Euclidean Accuracy
+    - type: max_accuracy
+      value: 0.481
+      name: Max Accuracy
+---
+
+# SentenceTransformer based on FacebookAI/xlm-roberta-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) dataset. It maps sentences & paragraphs to a 1024-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:** [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) <!-- at revision c23d21b0620b635a76227c604d44e43a9f0ee389 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    "There's a dock",
+    'The man is performing.',
+    'Five people on a path',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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
+
+#### Triplet
+* Dataset: `all-nli-dev`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric             | Value     |
+|:-------------------|:----------|
+| cosine_accuracy    | 0.452     |
+| dot_accuracy       | 0.34      |
+| manhattan_accuracy | 0.456     |
+| euclidean_accuracy | 0.452     |
+| **max_accuracy**   | **0.456** |
+
+#### Triplet
+* Dataset: `all-nli-test`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric             | Value     |
+|:-------------------|:----------|
+| cosine_accuracy    | 0.481     |
+| dot_accuracy       | 0.364     |
+| manhattan_accuracy | 0.48      |
+| euclidean_accuracy | 0.481     |
+| **max_accuracy**   | **0.481** |
+
+<!--
+## 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
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 100,000 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                          | negative                                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 10.9 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.62 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.76 tokens</li><li>max: 55 tokens</li></ul> |
+* Samples:
+  | anchor                                                                     | positive                                         | negative                                                   |
+  |:---------------------------------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code>        | <code>A person is outdoors, on a horse.</code>   | <code>A person is at a diner, ordering an omelette.</code> |
+  | <code>Children smiling and waving at camera</code>                         | <code>There are children present</code>          | <code>The kids are frowning</code>                         |
+  | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>The boy skates down the sidewalk.</code>             |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 1,000 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 20.31 tokens</li><li>max: 83 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.71 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 11.39 tokens</li><li>max: 32 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                         | positive                                                    | negative                                                |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:--------------------------------------------------------|
+  | <code>Two women are embracing while holding to go packages.</code>                                                                                                             | <code>Two woman are holding packages.</code>                | <code>The men are fighting outside a deli.</code>       |
+  | <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code>        |
+  | <code>A man selling donuts to a customer during a world exhibition event held in the city of Angeles</code>                                                                    | <code>A man selling donuts to a customer.</code>            | <code>A woman drinks her coffee in a small cafe.</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `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`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `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`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `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
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch | Step | Training Loss | loss   | all-nli-dev_max_accuracy | all-nli-test_max_accuracy |
+|:-----:|:----:|:-------------:|:------:|:------------------------:|:-------------------------:|
+| 0     | 0    | -             | -      | 0.616                    | -                         |
+| 0.016 | 100  | 3.2768        | 1.8053 | 0.833                    | -                         |
+| 0.032 | 200  | 1.1697        | 1.2878 | 0.861                    | -                         |
+| 0.048 | 300  | 1.372         | 1.2466 | 0.861                    | -                         |
+| 0.064 | 400  | 1.0476        | 1.2291 | 0.863                    | -                         |
+| 0.08  | 500  | 0.8588        | 1.5259 | 0.838                    | -                         |
+| 0.096 | 600  | 2.9781        | 3.4309 | 0.463                    | -                         |
+| 0.112 | 700  | 3.4982        | 3.4309 | 0.457                    | -                         |
+| 0.128 | 800  | 3.467         | 3.4309 | 0.479                    | -                         |
+| 0.144 | 900  | 3.4665        | 3.4309 | 0.452                    | -                         |
+| 0.16  | 1000 | 3.4664        | 3.4309 | 0.477                    | -                         |
+| 0.176 | 1100 | 3.4663        | 3.4309 | 0.458                    | -                         |
+| 0.192 | 1200 | 3.4661        | 3.4309 | 0.462                    | -                         |
+| 0.208 | 1300 | 3.4658        | 3.4309 | 0.45                     | -                         |
+| 0.224 | 1400 | 3.4661        | 3.4309 | 0.481                    | -                         |
+| 0.24  | 1500 | 3.4877        | 3.4309 | 0.464                    | -                         |
+| 0.256 | 1600 | 3.4675        | 3.4309 | 0.462                    | -                         |
+| 0.272 | 1700 | 3.4665        | 3.4309 | 0.488                    | -                         |
+| 0.288 | 1800 | 3.4667        | 3.4309 | 0.492                    | -                         |
+| 0.304 | 1900 | 3.4664        | 3.4309 | 0.455                    | -                         |
+| 0.32  | 2000 | 3.4661        | 3.4309 | 0.453                    | -                         |
+| 0.336 | 2100 | 3.4666        | 3.4309 | 0.477                    | -                         |
+| 0.352 | 2200 | 3.4683        | 3.4309 | 0.48                     | -                         |
+| 0.368 | 2300 | 3.4663        | 3.4309 | 0.469                    | -                         |
+| 0.384 | 2400 | 3.4667        | 3.4309 | 0.448                    | -                         |
+| 0.4   | 2500 | 3.4669        | 3.4309 | 0.499                    | -                         |
+| 0.416 | 2600 | 3.4661        | 3.4309 | 0.453                    | -                         |
+| 0.432 | 2700 | 3.4656        | 3.4309 | 0.467                    | -                         |
+| 0.448 | 2800 | 3.4662        | 3.4309 | 0.507                    | -                         |
+| 0.464 | 2900 | 3.4902        | 3.4309 | 0.473                    | -                         |
+| 0.48  | 3000 | 3.4663        | 3.4309 | 0.469                    | -                         |
+| 0.496 | 3100 | 3.554         | 3.4309 | 0.46                     | -                         |
+| 0.512 | 3200 | 3.4664        | 3.4309 | 0.455                    | -                         |
+| 0.528 | 3300 | 3.4668        | 3.4309 | 0.46                     | -                         |
+| 0.544 | 3400 | 3.4661        | 3.4309 | 0.492                    | -                         |
+| 0.56  | 3500 | 3.4667        | 3.4309 | 0.432                    | -                         |
+| 0.576 | 3600 | 3.4668        | 3.4309 | 0.486                    | -                         |
+| 0.592 | 3700 | 3.4666        | 3.4309 | 0.469                    | -                         |
+| 0.608 | 3800 | 3.4669        | 3.4309 | 0.473                    | -                         |
+| 0.624 | 3900 | 3.4658        | 3.4309 | 0.487                    | -                         |
+| 0.64  | 4000 | 3.4663        | 3.4309 | 0.448                    | -                         |
+| 0.656 | 4100 | 3.4663        | 3.4309 | 0.465                    | -                         |
+| 0.672 | 4200 | 3.4664        | 3.4309 | 0.484                    | -                         |
+| 0.688 | 4300 | 3.4663        | 3.4309 | 0.469                    | -                         |
+| 0.704 | 4400 | 3.4661        | 3.4309 | 0.478                    | -                         |
+| 0.72  | 4500 | 3.4669        | 3.4309 | 0.467                    | -                         |
+| 0.736 | 4600 | 3.4664        | 3.4309 | 0.455                    | -                         |
+| 0.752 | 4700 | 3.4664        | 3.4309 | 0.481                    | -                         |
+| 0.768 | 4800 | 3.4659        | 3.4309 | 0.466                    | -                         |
+| 0.784 | 4900 | 3.466         | 3.4309 | 0.451                    | -                         |
+| 0.8   | 5000 | 3.466         | 3.4309 | 0.473                    | -                         |
+| 0.816 | 5100 | 3.4664        | 3.4309 | 0.44                     | -                         |
+| 0.832 | 5200 | 3.4658        | 3.4309 | 0.497                    | -                         |
+| 0.848 | 5300 | 3.4664        | 3.4309 | 0.474                    | -                         |
+| 0.864 | 5400 | 3.4658        | 3.4309 | 0.449                    | -                         |
+| 0.88  | 5500 | 3.4662        | 3.4309 | 0.466                    | -                         |
+| 0.896 | 5600 | 3.4663        | 3.4309 | 0.476                    | -                         |
+| 0.912 | 5700 | 3.4667        | 3.4309 | 0.455                    | -                         |
+| 0.928 | 5800 | 3.4669        | 3.4309 | 0.463                    | -                         |
+| 0.944 | 5900 | 3.4657        | 3.4309 | 0.467                    | -                         |
+| 0.96  | 6000 | 3.4671        | 3.4309 | 0.456                    | -                         |
+| 0.976 | 6100 | 2.9471        | 3.4309 | 0.484                    | -                         |
+| 0.992 | 6200 | 0.6929        | 3.4309 | 0.456                    | -                         |
+| 1.0   | 6250 | -             | -      | -                        | 0.481                     |
+
+
+### Framework Versions
+- Python: 3.9.10
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.2
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.26.1
+- Datasets: 2.16.1
+- 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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.*
+-->

final/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

final/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.3.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

final/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c35c8055250a476dc32b87c601f3abe4bc9aa87098c4d6976e79dc6094a3af3
+size 2239607176

final/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"
+  }
+]

final/sentence_bert_config.json

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

final/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

final/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

final/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

final/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

runs/Jun03_19-02-48_ruche-gpu14.cluster/events.out.tfevents.1717434207.ruche-gpu14.cluster.27296.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25f73693ca5403fb975d98ec3e3589e1d219cdbede86b355c4441284579d1c3
+size 56493