Training in progress, step 9823, checkpoint

last-checkpoint/1_Pooling/config.json

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

last-checkpoint/README.md

@@ -0,0 +1,653 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:100K<n<1M
+- loss:MultipleNegativesRankingLoss
+base_model: microsoft/deberta-v3-base
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+widget:
+- source_sentence: profit rather
+  sentences:
+  - Making money rather.
+  - A racecar is being watched.
+  - A man is standing in the doorway.
+- source_sentence: life track
+  sentences:
+  - There is.
+  - The man is wearing an apron.
+  - A man playing billiards at a bar.
+- source_sentence: Fiesta time!
+  sentences:
+  - It is a special day.
+  - The world is getting better.
+  - A man hammering nails on a shed.
+- source_sentence: 'The family. '
+  sentences:
+  - A man is at his sisters party.
+  - the man is training some guys
+  - Commuters wait for to cross a street.
+- source_sentence: I don't know.
+  sentences:
+  - I'm not sure about anything.
+  - A guy is outside in the snow
+  - The dogs run a race at the track.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on microsoft/deberta-v3-base
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: pearson_cosine
+      value: 0.35614155568929684
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.4042062369647017
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.44470114795339144
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.464389588301289
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.4073816956345048
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.42806381869427496
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: -0.033633706160895414
+      name: Pearson Dot
+    - type: spearman_dot
+      value: -0.026115764956036586
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.44470114795339144
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.464389588301289
+      name: Spearman Max
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy
+      value: 0.6648722420198651
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7642883062362671
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.7061340941512125
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.6351689100265503
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.5953693495038589
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8675332262304659
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.7283929467215002
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.6397755705512169
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 268.03167724609375
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.7021864211737631
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 216.1470947265625
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.5793221304471661
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.8911932233094786
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.6799114732445778
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.6606262794753204
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 248.9168701171875
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.703255925305243
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 306.02117919921875
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.5957813609167427
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.8580400175259237
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.7294072443461903
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.6580483736447039
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 12.722024917602539
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.7027586626880216
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 16.08021354675293
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.6026739085021935
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.8427048342339711
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.7268148607241872
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.6648722420198651
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 268.03167724609375
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.7061340941512125
+      name: Max F1
+    - type: max_f1_threshold
+      value: 306.02117919921875
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.6026739085021935
+      name: Max Precision
+    - type: max_recall
+      value: 0.8911932233094786
+      name: Max Recall
+    - type: max_ap
+      value: 0.7294072443461903
+      name: Max Ap
+---
+
+# SentenceTransformer based on microsoft/deberta-v3-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) <!-- at revision 8ccc9b6f36199bec6961081d44eb72fb3f7353f3 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DebertaV2Model 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("bobox/DeBERTaV3-large-SentenceTransformer-0.01n")
+# Run inference
+sentences = [
+    "I don't know.",
+    "I'm not sure about anything.",
+    'A guy is outside in the snow',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.3561     |
+| **spearman_cosine** | **0.4042** |
+| pearson_manhattan   | 0.4447     |
+| spearman_manhattan  | 0.4644     |
+| pearson_euclidean   | 0.4074     |
+| spearman_euclidean  | 0.4281     |
+| pearson_dot         | -0.0336    |
+| spearman_dot        | -0.0261    |
+| pearson_max         | 0.4447     |
+| spearman_max        | 0.4644     |
+
+#### Binary Classification
+
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.6649     |
+| cosine_accuracy_threshold    | 0.7643     |
+| cosine_f1                    | 0.7061     |
+| cosine_f1_threshold          | 0.6352     |
+| cosine_precision             | 0.5954     |
+| cosine_recall                | 0.8675     |
+| cosine_ap                    | 0.7284     |
+| dot_accuracy                 | 0.6398     |
+| dot_accuracy_threshold       | 268.0317   |
+| dot_f1                       | 0.7022     |
+| dot_f1_threshold             | 216.1471   |
+| dot_precision                | 0.5793     |
+| dot_recall                   | 0.8912     |
+| dot_ap                       | 0.6799     |
+| manhattan_accuracy           | 0.6606     |
+| manhattan_accuracy_threshold | 248.9169   |
+| manhattan_f1                 | 0.7033     |
+| manhattan_f1_threshold       | 306.0212   |
+| manhattan_precision          | 0.5958     |
+| manhattan_recall             | 0.858      |
+| manhattan_ap                 | 0.7294     |
+| euclidean_accuracy           | 0.658      |
+| euclidean_accuracy_threshold | 12.722     |
+| euclidean_f1                 | 0.7028     |
+| euclidean_f1_threshold       | 16.0802    |
+| euclidean_precision          | 0.6027     |
+| euclidean_recall             | 0.8427     |
+| euclidean_ap                 | 0.7268     |
+| max_accuracy                 | 0.6649     |
+| max_accuracy_threshold       | 268.0317   |
+| max_f1                       | 0.7061     |
+| max_f1_threshold             | 306.0212   |
+| max_precision                | 0.6027     |
+| max_recall                   | 0.8912     |
+| **max_ap**                   | **0.7294** |
+
+<!--
+## 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
+
+#### stanfordnlp/snli
+
+* Dataset: [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b)
+* Size: 314,315 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                        | label                        |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------|
+  | type    | string                                                                            | string                                                                           | int                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 16.62 tokens</li><li>max: 62 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.46 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>0: 100.00%</li></ul> |
+* Samples:
+  | sentence1                                                                  | sentence2                                        | label          |
+  |:---------------------------------------------------------------------------|:-------------------------------------------------|:---------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code>        | <code>A person is outdoors, on a horse.</code>   | <code>0</code> |
+  | <code>Children smiling and waving at camera</code>                         | <code>There are children present</code>          | <code>0</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>0</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/stsb
+
+* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
+* Size: 13,189 evaluation samples
+* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | premise                                                                           | hypothesis                                                                        | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 17.28 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.53 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>0: ~48.70%</li><li>1: ~51.30%</li></ul> |
+* Samples:
+  | premise                                                                                                 | hypothesis                                         | label          |
+  |:--------------------------------------------------------------------------------------------------------|:---------------------------------------------------|:---------------|
+  | <code>This church choir sings to the masses as they sing joyous songs from the book at a church.</code> | <code>The church has cracks in the ceiling.</code> | <code>0</code> |
+  | <code>This church choir sings to the masses as they sing joyous songs from the book at a church.</code> | <code>The church is filled with song.</code>       | <code>1</code> |
+  | <code>A woman with a green headscarf, blue shirt and a very big grin.</code>                            | <code>The woman is young.</code>                   | <code>0</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`: 32
+- `per_device_eval_batch_size`: 64
+- `num_train_epochs`: 5
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.25
+- `save_safetensors`: False
+- `fp16`: True
+- `push_to_hub`: True
+- `hub_model_id`: bobox/DeBERTaV3-large-SentenceTransformer-0.01n
+- `hub_strategy`: checkpoint
+- `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`: 32
+- `per_device_eval_batch_size`: 64
+- `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`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.25
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: False
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: True
+- `resume_from_checkpoint`: None
+- `hub_model_id`: bobox/DeBERTaV3-large-SentenceTransformer-0.01n
+- `hub_strategy`: checkpoint
+- `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   | max_ap | spearman_cosine |
+|:------:|:----:|:-------------:|:------:|:------:|:---------------:|
+| None   | 0    | -             | 3.2007 | 0.5917 | 0.4042          |
+| 0.1250 | 1228 | 2.3115        | 1.3295 | 0.6783 | -               |
+| 0.2500 | 2456 | 1.1344        | 1.0007 | 0.7048 | -               |
+| 0.3750 | 3684 | 0.9827        | 0.8551 | 0.7091 | -               |
+| 0.5001 | 4912 | 0.9045        | 0.7483 | 0.7148 | -               |
+| 0.6251 | 6140 | 0.6488        | 0.6057 | 0.7276 | -               |
+| 0.7501 | 7368 | 0.1224        | 0.6683 | 0.7358 | -               |
+| 0.8751 | 8596 | 0.1063        | 0.6895 | 0.7294 | -               |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.2
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- Datasets: 2.19.2
+- 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.*
+-->

last-checkpoint/added_tokens.json

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

last-checkpoint/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2Model"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

last-checkpoint/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
+}

last-checkpoint/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"
+  }
+]

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25831fee8a56126ffd94bd472a29dd638517430a70c9d55e5521916f42d41cd0
+size 1470818042

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964309fb41343f220f0134621218c2e95faf9b4c3b23ec32bf293a2c6dc0c7f2
+size 735393442

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f787d94dbd33f4586c396382ebc4b31f1eb9a7ff215e29da3f8f0beae15a8ce7
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5afa3d56abf40a30335967d6a0973486eb802f6a6a8af4dc50831b2b2486b3e8
+size 1064

last-checkpoint/sentence_bert_config.json

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

last-checkpoint/special_tokens_map.json

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

last-checkpoint/spm.model

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

last-checkpoint/tokenizer_config.json

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

last-checkpoint/trainer_state.json

@@ -0,0 +1,383 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 1228,
+  "global_step": 9823,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1250127252366894,
+      "grad_norm": 15.43435287475586,
+      "learning_rate": 4.984119227950159e-06,
+      "loss": 2.3115,
+      "step": 1228
+    },
+    {
+      "epoch": 0.1250127252366894,
+      "eval_cosine_accuracy": 0.6210478428993859,
+      "eval_cosine_accuracy_threshold": 0.848922610282898,
+      "eval_cosine_ap": 0.6734391704854221,
+      "eval_cosine_f1": 0.6875199829478844,
+      "eval_cosine_f1_threshold": 0.6612564921379089,
+      "eval_cosine_precision": 0.5412366809296082,
+      "eval_cosine_recall": 0.9421644515846356,
+      "eval_dot_accuracy": 0.5711577830009856,
+      "eval_dot_accuracy_threshold": 343.60479736328125,
+      "eval_dot_ap": 0.5947527693779144,
+      "eval_dot_f1": 0.6843559977888336,
+      "eval_dot_f1_threshold": 204.2578887939453,
+      "eval_dot_precision": 0.5216825007661661,
+      "eval_dot_recall": 0.99445012414196,
+      "eval_euclidean_accuracy": 0.6265827583592387,
+      "eval_euclidean_accuracy_threshold": 12.094720840454102,
+      "eval_euclidean_ap": 0.6783368773007193,
+      "eval_euclidean_f1": 0.6879386675305043,
+      "eval_euclidean_f1_threshold": 17.03110122680664,
+      "eval_euclidean_precision": 0.545695931477516,
+      "eval_euclidean_recall": 0.9304805024098145,
+      "eval_loss": 1.3295445442199707,
+      "eval_manhattan_accuracy": 0.628023352793995,
+      "eval_manhattan_accuracy_threshold": 217.5894012451172,
+      "eval_manhattan_ap": 0.6782312637044651,
+      "eval_manhattan_f1": 0.6873385012919898,
+      "eval_manhattan_f1_threshold": 288.74737548828125,
+      "eval_manhattan_precision": 0.5511373655439957,
+      "eval_manhattan_recall": 0.9129545786475829,
+      "eval_max_accuracy": 0.628023352793995,
+      "eval_max_accuracy_threshold": 343.60479736328125,
+      "eval_max_ap": 0.6783368773007193,
+      "eval_max_f1": 0.6879386675305043,
+      "eval_max_f1_threshold": 288.74737548828125,
+      "eval_max_precision": 0.5511373655439957,
+      "eval_max_recall": 0.99445012414196,
+      "eval_runtime": 37.2407,
+      "eval_samples_per_second": 354.156,
+      "eval_steps_per_second": 5.558,
+      "step": 1228
+    },
+    {
+      "epoch": 0.2500254504733788,
+      "grad_norm": 15.62058162689209,
+      "learning_rate": 9.984526427233488e-06,
+      "loss": 1.1344,
+      "step": 2456
+    },
+    {
+      "epoch": 0.2500254504733788,
+      "eval_cosine_accuracy": 0.6382591553567367,
+      "eval_cosine_accuracy_threshold": 0.8384923934936523,
+      "eval_cosine_ap": 0.6979960206921748,
+      "eval_cosine_f1": 0.6956719817767655,
+      "eval_cosine_f1_threshold": 0.7339043617248535,
+      "eval_cosine_precision": 0.5701484178101373,
+      "eval_cosine_recall": 0.8920695194975902,
+      "eval_dot_accuracy": 0.5939040109181895,
+      "eval_dot_accuracy_threshold": 351.5899658203125,
+      "eval_dot_ap": 0.608546180214937,
+      "eval_dot_f1": 0.6888470841171728,
+      "eval_dot_f1_threshold": 282.84210205078125,
+      "eval_dot_precision": 0.5449906446674605,
+      "eval_dot_recall": 0.9358843289031693,
+      "eval_euclidean_accuracy": 0.6435666085374175,
+      "eval_euclidean_accuracy_threshold": 12.236141204833984,
+      "eval_euclidean_ap": 0.703382621150597,
+      "eval_euclidean_f1": 0.6971692663200463,
+      "eval_euclidean_f1_threshold": 15.051461219787598,
+      "eval_euclidean_precision": 0.5766988435439167,
+      "eval_euclidean_recall": 0.8812618665108807,
+      "eval_loss": 1.0007121562957764,
+      "eval_manhattan_accuracy": 0.6444764576541057,
+      "eval_manhattan_accuracy_threshold": 214.30072021484375,
+      "eval_manhattan_ap": 0.7047552016202201,
+      "eval_manhattan_f1": 0.6967445793320045,
+      "eval_manhattan_f1_threshold": 250.53140258789062,
+      "eval_manhattan_precision": 0.5940267765190526,
+      "eval_manhattan_recall": 0.8424127355046006,
+      "eval_max_accuracy": 0.6444764576541057,
+      "eval_max_accuracy_threshold": 351.5899658203125,
+      "eval_max_ap": 0.7047552016202201,
+      "eval_max_f1": 0.6971692663200463,
+      "eval_max_f1_threshold": 282.84210205078125,
+      "eval_max_precision": 0.5940267765190526,
+      "eval_max_recall": 0.9358843289031693,
+      "eval_runtime": 36.7273,
+      "eval_samples_per_second": 359.106,
+      "eval_steps_per_second": 5.636,
+      "step": 2456
+    },
+    {
+      "epoch": 0.3750381757100682,
+      "grad_norm": 11.62977123260498,
+      "learning_rate": 1.4984933626516816e-05,
+      "loss": 0.9827,
+      "step": 3684
+    },
+    {
+      "epoch": 0.3750381757100682,
+      "eval_cosine_accuracy": 0.6383349761164607,
+      "eval_cosine_accuracy_threshold": 0.8612147569656372,
+      "eval_cosine_ap": 0.7032393444334419,
+      "eval_cosine_f1": 0.6932498182428275,
+      "eval_cosine_f1_threshold": 0.7054703235626221,
+      "eval_cosine_precision": 0.5617183251767265,
+      "eval_cosine_recall": 0.9052139623192639,
+      "eval_dot_accuracy": 0.5945863977557055,
+      "eval_dot_accuracy_threshold": 339.2906188964844,
+      "eval_dot_ap": 0.6228302492866797,
+      "eval_dot_f1": 0.6876656472986747,
+      "eval_dot_f1_threshold": 224.48248291015625,
+      "eval_dot_precision": 0.528145306505911,
+      "eval_dot_recall": 0.9852490141667883,
+      "eval_euclidean_accuracy": 0.6429600424596255,
+      "eval_euclidean_accuracy_threshold": 12.074974060058594,
+      "eval_euclidean_ap": 0.7080982628872418,
+      "eval_euclidean_f1": 0.6952535685273297,
+      "eval_euclidean_f1_threshold": 15.344061851501465,
+      "eval_euclidean_precision": 0.576778665639742,
+      "eval_euclidean_recall": 0.8749817438294143,
+      "eval_loss": 0.8550812602043152,
+      "eval_manhattan_accuracy": 0.646523618166654,
+      "eval_manhattan_accuracy_threshold": 216.00611877441406,
+      "eval_manhattan_ap": 0.7091050987827672,
+      "eval_manhattan_f1": 0.6948782931573053,
+      "eval_manhattan_f1_threshold": 267.3834228515625,
+      "eval_manhattan_precision": 0.5825098814229249,
+      "eval_manhattan_recall": 0.860961004819629,
+      "eval_max_accuracy": 0.646523618166654,
+      "eval_max_accuracy_threshold": 339.2906188964844,
+      "eval_max_ap": 0.7091050987827672,
+      "eval_max_f1": 0.6952535685273297,
+      "eval_max_f1_threshold": 267.3834228515625,
+      "eval_max_precision": 0.5825098814229249,
+      "eval_max_recall": 0.9852490141667883,
+      "eval_runtime": 37.837,
+      "eval_samples_per_second": 348.574,
+      "eval_steps_per_second": 5.471,
+      "step": 3684
+    },
+    {
+      "epoch": 0.5000509009467576,
+      "grad_norm": 6.6275715827941895,
+      "learning_rate": 1.9985340825800148e-05,
+      "loss": 0.9045,
+      "step": 4912
+    },
+    {
+      "epoch": 0.5000509009467576,
+      "eval_cosine_accuracy": 0.64644779740693,
+      "eval_cosine_accuracy_threshold": 0.8346654772758484,
+      "eval_cosine_ap": 0.7120759823214882,
+      "eval_cosine_f1": 0.7009007975213725,
+      "eval_cosine_f1_threshold": 0.7283114790916443,
+      "eval_cosine_precision": 0.5772065772065772,
+      "eval_cosine_recall": 0.8920695194975902,
+      "eval_dot_accuracy": 0.6088407005838199,
+      "eval_dot_accuracy_threshold": 372.897705078125,
+      "eval_dot_ap": 0.648631541530839,
+      "eval_dot_f1": 0.6931595400837175,
+      "eval_dot_f1_threshold": 278.7884216308594,
+      "eval_dot_precision": 0.5439048727756528,
+      "eval_dot_recall": 0.9553088944063093,
+      "eval_euclidean_accuracy": 0.6481916748805823,
+      "eval_euclidean_accuracy_threshold": 12.667613983154297,
+      "eval_euclidean_ap": 0.7129650302942496,
+      "eval_euclidean_f1": 0.7006925449572251,
+      "eval_euclidean_f1_threshold": 15.448726654052734,
+      "eval_euclidean_precision": 0.5824303405572755,
+      "eval_euclidean_recall": 0.879217175405287,
+      "eval_loss": 0.7482573986053467,
+      "eval_manhattan_accuracy": 0.6497080900750626,
+      "eval_manhattan_accuracy_threshold": 228.42645263671875,
+      "eval_manhattan_ap": 0.7148163923267561,
+      "eval_manhattan_f1": 0.7008231143961029,
+      "eval_manhattan_f1_threshold": 289.23284912109375,
+      "eval_manhattan_precision": 0.5682891391209589,
+      "eval_manhattan_recall": 0.9139769242003797,
+      "eval_max_accuracy": 0.6497080900750626,
+      "eval_max_accuracy_threshold": 372.897705078125,
+      "eval_max_ap": 0.7148163923267561,
+      "eval_max_f1": 0.7009007975213725,
+      "eval_max_f1_threshold": 289.23284912109375,
+      "eval_max_precision": 0.5824303405572755,
+      "eval_max_recall": 0.9553088944063093,
+      "eval_runtime": 36.72,
+      "eval_samples_per_second": 359.178,
+      "eval_steps_per_second": 5.637,
+      "step": 4912
+    },
+    {
+      "epoch": 0.625063626183447,
+      "grad_norm": 8.070146560668945,
+      "learning_rate": 2.4985748025083476e-05,
+      "loss": 0.6488,
+      "step": 6140
+    },
+    {
+      "epoch": 0.625063626183447,
+      "eval_cosine_accuracy": 0.6679050724088256,
+      "eval_cosine_accuracy_threshold": 0.7640305757522583,
+      "eval_cosine_ap": 0.7260649988715485,
+      "eval_cosine_f1": 0.7124000968757568,
+      "eval_cosine_f1_threshold": 0.6364777088165283,
+      "eval_cosine_precision": 0.6084393422277381,
+      "eval_cosine_recall": 0.8592084124434058,
+      "eval_dot_accuracy": 0.6316627492607476,
+      "eval_dot_accuracy_threshold": 238.4151611328125,
+      "eval_dot_ap": 0.6571882757637728,
+      "eval_dot_f1": 0.7046040103058139,
+      "eval_dot_f1_threshold": 183.28378295898438,
+      "eval_dot_precision": 0.5714545289361316,
+      "eval_dot_recall": 0.9186505038703081,
+      "eval_euclidean_accuracy": 0.6656304496171052,
+      "eval_euclidean_accuracy_threshold": 12.852251052856445,
+      "eval_euclidean_ap": 0.7254103624891234,
+      "eval_euclidean_f1": 0.7062990731448138,
+      "eval_euclidean_f1_threshold": 16.455379486083984,
+      "eval_euclidean_precision": 0.5927467300832342,
+      "eval_euclidean_recall": 0.873667299547247,
+      "eval_loss": 0.6056942343711853,
+      "eval_manhattan_accuracy": 0.6666919402532413,
+      "eval_manhattan_accuracy_threshold": 238.08731079101562,
+      "eval_manhattan_ap": 0.7275797275536158,
+      "eval_manhattan_f1": 0.7068183230778792,
+      "eval_manhattan_f1_threshold": 281.99066162109375,
+      "eval_manhattan_precision": 0.6152347976628435,
+      "eval_manhattan_recall": 0.8304366876004089,
+      "eval_max_accuracy": 0.6679050724088256,
+      "eval_max_accuracy_threshold": 238.4151611328125,
+      "eval_max_ap": 0.7275797275536158,
+      "eval_max_f1": 0.7124000968757568,
+      "eval_max_f1_threshold": 281.99066162109375,
+      "eval_max_precision": 0.6152347976628435,
+      "eval_max_recall": 0.9186505038703081,
+      "eval_runtime": 36.5244,
+      "eval_samples_per_second": 361.101,
+      "eval_steps_per_second": 5.667,
+      "step": 6140
+    },
+    {
+      "epoch": 0.7500763514201364,
+      "grad_norm": 3.4847946166992188,
+      "learning_rate": 2.9986155224366808e-05,
+      "loss": 0.1224,
+      "step": 7368
+    },
+    {
+      "epoch": 0.7500763514201364,
+      "eval_cosine_accuracy": 0.6698005914019258,
+      "eval_cosine_accuracy_threshold": 0.766596794128418,
+      "eval_cosine_ap": 0.7285326578175677,
+      "eval_cosine_f1": 0.7130742480629613,
+      "eval_cosine_f1_threshold": 0.6729254722595215,
+      "eval_cosine_precision": 0.6123218776194468,
+      "eval_cosine_recall": 0.8535124872206806,
+      "eval_dot_accuracy": 0.6206687391007658,
+      "eval_dot_accuracy_threshold": 261.77471923828125,
+      "eval_dot_ap": 0.6459102507978051,
+      "eval_dot_f1": 0.7029659625697713,
+      "eval_dot_f1_threshold": 202.47332763671875,
+      "eval_dot_precision": 0.5620897873457601,
+      "eval_dot_recall": 0.9380750693734482,
+      "eval_euclidean_accuracy": 0.6688149215255137,
+      "eval_euclidean_accuracy_threshold": 12.95585823059082,
+      "eval_euclidean_ap": 0.732777449339851,
+      "eval_euclidean_f1": 0.7106249615928225,
+      "eval_euclidean_f1_threshold": 15.783571243286133,
+      "eval_euclidean_precision": 0.6134097178018247,
+      "eval_euclidean_recall": 0.8444574266101943,
+      "eval_loss": 0.6682662963867188,
+      "eval_manhattan_accuracy": 0.6737432709075745,
+      "eval_manhattan_accuracy_threshold": 239.43251037597656,
+      "eval_manhattan_ap": 0.7357876112808931,
+      "eval_manhattan_f1": 0.7108785592601606,
+      "eval_manhattan_f1_threshold": 293.34881591796875,
+      "eval_manhattan_precision": 0.6092397538846595,
+      "eval_manhattan_recall": 0.8532203884913101,
+      "eval_max_accuracy": 0.6737432709075745,
+      "eval_max_accuracy_threshold": 261.77471923828125,
+      "eval_max_ap": 0.7357876112808931,
+      "eval_max_f1": 0.7130742480629613,
+      "eval_max_f1_threshold": 293.34881591796875,
+      "eval_max_precision": 0.6134097178018247,
+      "eval_max_recall": 0.9380750693734482,
+      "eval_runtime": 36.5369,
+      "eval_samples_per_second": 360.977,
+      "eval_steps_per_second": 5.666,
+      "step": 7368
+    },
+    {
+      "epoch": 0.8750890766568258,
+      "grad_norm": 7.982311725616455,
+      "learning_rate": 3.498656242365014e-05,
+      "loss": 0.1063,
+      "step": 8596
+    },
+    {
+      "epoch": 0.8750890766568258,
+      "eval_cosine_accuracy": 0.6648722420198651,
+      "eval_cosine_accuracy_threshold": 0.7642883062362671,
+      "eval_cosine_ap": 0.7283929467215002,
+      "eval_cosine_f1": 0.7061340941512125,
+      "eval_cosine_f1_threshold": 0.6351689100265503,
+      "eval_cosine_precision": 0.5953693495038589,
+      "eval_cosine_recall": 0.8675332262304659,
+      "eval_dot_accuracy": 0.6397755705512169,
+      "eval_dot_accuracy_threshold": 268.03167724609375,
+      "eval_dot_ap": 0.6799114732445778,
+      "eval_dot_f1": 0.7021864211737631,
+      "eval_dot_f1_threshold": 216.1470947265625,
+      "eval_dot_precision": 0.5793221304471661,
+      "eval_dot_recall": 0.8911932233094786,
+      "eval_euclidean_accuracy": 0.6580483736447039,
+      "eval_euclidean_accuracy_threshold": 12.722024917602539,
+      "eval_euclidean_ap": 0.7268148607241872,
+      "eval_euclidean_f1": 0.7027586626880216,
+      "eval_euclidean_f1_threshold": 16.08021354675293,
+      "eval_euclidean_precision": 0.6026739085021935,
+      "eval_euclidean_recall": 0.8427048342339711,
+      "eval_loss": 0.6895074248313904,
+      "eval_manhattan_accuracy": 0.6606262794753204,
+      "eval_manhattan_accuracy_threshold": 248.9168701171875,
+      "eval_manhattan_ap": 0.7294072443461903,
+      "eval_manhattan_f1": 0.703255925305243,
+      "eval_manhattan_f1_threshold": 306.02117919921875,
+      "eval_manhattan_precision": 0.5957813609167427,
+      "eval_manhattan_recall": 0.8580400175259237,
+      "eval_max_accuracy": 0.6648722420198651,
+      "eval_max_accuracy_threshold": 268.03167724609375,
+      "eval_max_ap": 0.7294072443461903,
+      "eval_max_f1": 0.7061340941512125,
+      "eval_max_f1_threshold": 306.02117919921875,
+      "eval_max_precision": 0.6026739085021935,
+      "eval_max_recall": 0.8911932233094786,
+      "eval_runtime": 36.5151,
+      "eval_samples_per_second": 361.193,
+      "eval_steps_per_second": 5.669,
+      "step": 8596
+    }
+  ],
+  "logging_steps": 1228,
+  "max_steps": 49115,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 9823,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f3a4722bf017fa7a86c21655fdafd309cec23645bee218eafdd9a69e1939ff7
+size 5560