Upload folder using huggingface_hub

.gitattributes

@@ -48,3 +48,4 @@ checkpoint-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-2600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3200/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-3200/1_Pooling/config.json

@@ -0,0 +1,5 @@
+{
+    "embedding_dimension": 1024,
+    "pooling_mode": "lasttoken",
+    "include_prompt": true
+}

checkpoint-3200/README.md

@@ -0,0 +1,598 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:342061
+- loss:CachedMultipleNegativesRankingLoss
+base_model: prestoai/qwen3-embedding-0.6b-arabic-ecom
+widget:
+- source_sentence: 'Instruct: Given an Arabic e-commerce search query, retrieve the
+    product that best matches it
+
+    Query: نسونكس Spray'
+  sentences:
+  - Nasonex - Nasal Spray
+  - كابل شحن مايكرو XKIN - 2.4A
+  - حلوى الشوكولاتة - Choco Lapki
+- source_sentence: 'Instruct: Given an Arabic e-commerce search query, retrieve the
+    product that best matches it
+
+    Query: مكرونة رقم 42'
+  sentences:
+  - بنطلون رجالي - 0112
+  - حقيبة حزام خصر - 4862
+  - مكرونة الجيد معكوفة رقم 42 - 500 غ
+- source_sentence: 'Instruct: Given an Arabic e-commerce search query, retrieve the
+    product that best matches it
+
+    Query: سباغيتي'
+  sentences:
+  - ملعب كرة قدم - DD18
+  - مكرونة معكوفة - Favelli
+  - مكرونة سباغيتي - Favelli
+- source_sentence: 'Instruct: Given an Arabic e-commerce search query, retrieve the
+    product that best matches it
+
+    Query: جبنة هواء'
+  sentences:
+  - جبنة - ابو الولد
+  - جبنة - Hawaa
+  - كاني طعام كلاب البالغين دجاج - 3 ك
+- source_sentence: 'Instruct: Given an Arabic e-commerce search query, retrieve the
+    product that best matches it
+
+    Query: شاحن تايب سي للسيارة'
+  sentences:
+  - شاحن سيارة قرين ليون مدخلين 36 وات مع كابل تايب سي - CBK
+  - صوص المكرونة هاينز - 365 غ
+  - بسكويت جولون بدون سكر شكلاتة ساندوتش
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on prestoai/qwen3-embedding-0.6b-arabic-ecom
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [prestoai/qwen3-embedding-0.6b-arabic-ecom](https://huggingface.co/prestoai/qwen3-embedding-0.6b-arabic-ecom) on the pairs_with_negatives and positives datasets. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [prestoai/qwen3-embedding-0.6b-arabic-ecom](https://huggingface.co/prestoai/qwen3-embedding-0.6b-arabic-ecom) <!-- at revision 80f273fd53c6644d65e14a2ac1fbf74b8c924097 -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Supported Modality:** Text
+- **Training Datasets:**
+    - pairs_with_negatives
+    - positives
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'Qwen3Model'})
+  (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'lasttoken', 'include_prompt': True})
+  (2): Normalize({})
+)
+```
+
+## 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
+queries = [
+    'Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it\nQuery: شاحن تايب سي للسيارة',
+]
+documents = [
+    'شاحن سيارة قرين ليون مدخلين 36 وات مع كابل تايب سي - CBK',
+    'بسكويت جولون بدون سكر شكلاتة ساندوتش',
+    'صوص المكرونة هاينز - 365 غ',
+]
+query_embeddings = model.encode_query(queries)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings.shape)
+# [1, 1024] [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+# tensor([[ 0.5921, -0.0655, -0.0390]])
+```
+<!--
+### 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.*
+-->
+
+<!--
+## 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 Datasets
+
+#### pairs_with_negatives
+
+* Dataset: pairs_with_negatives
+* Size: 124,261 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: 23 tokens</li><li>mean: 29.44 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 15.95 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 14.87 tokens</li><li>max: 40 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                | positive                                                        | negative                                                           |
+  |:--------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------|:-------------------------------------------------------------------|
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: واقي للوجه دهني</code>   | <code>Anthelios Oil Control (Dry Touch) - La Roche Posay</code> | <code>Anthelios Invisible Mist (Dry Touch) - La Roche Posay</code> |
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: تن منارة زليتن</code>    | <code>تن منارة زليتن بزيت دوار الشمس - 160 غ</code>             | <code>تن فاني بزيت دوار الشمس - 160 غ</code>                       |
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: فانتا زجاجة صغيرة</code> | <code>مشروب فانتا برتقال زجاجة - 330 مل</code>                  | <code>مشروب فانتا - 1 ل (برتقال)</code>                            |
+* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "mini_batch_size": 8,
+      "gather_across_devices": false,
+      "directions": [
+          "query_to_doc"
+      ],
+      "partition_mode": "joint",
+      "hardness_mode": null,
+      "hardness_strength": 0.0
+  }
+  ```
+
+#### positives
+
+* Dataset: positives
+* Size: 217,800 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                             | positive                                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 23 tokens</li><li>mean: 29.61 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 13.81 tokens</li><li>max: 41 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                         | positive                                   |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------|
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: نحب جبنة القرية</code>            | <code>ميرسين جبنة القرية 200 جم</code>     |
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: كابل شحن مايكرو Moxom A2.4</code> | <code>كابل شحن مايكرو Moxom -  A2.4</code> |
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: dry idea</code>                   | <code>Dry idea (powder fresh)</code>       |
+* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "mini_batch_size": 8,
+      "gather_across_devices": false,
+      "directions": [
+          "query_to_doc"
+      ],
+      "partition_mode": "joint",
+      "hardness_mode": null,
+      "hardness_strength": 0.0
+  }
+  ```
+
+### Evaluation Datasets
+
+#### pairs_with_negatives
+
+* Dataset: pairs_with_negatives
+* Size: 1,256 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: 23 tokens</li><li>mean: 29.56 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 16.04 tokens</li><li>max: 43 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 15.05 tokens</li><li>max: 33 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                               | positive                                               | negative                              |
+  |:-------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------|:--------------------------------------|
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: هيبوتك بوزن</code>      | <code>عطر Hypnotic Poison - PERFECTO COLLECTION</code> | <code>عطر Poison Girl - Dior</code>   |
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: شاحن مايكرو 2.4A</code> | <code>شحن مايكرو Smila - 2.4A</code>                   | <code>شحن تايب سي Smila - 2.4A</code> |
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: تمر صعيدي</code>        | <code>تمر صعيدي مشفوط</code>                           | <code>تمر قصيم مشفوط</code>           |
+* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "mini_batch_size": 8,
+      "gather_across_devices": false,
+      "directions": [
+          "query_to_doc"
+      ],
+      "partition_mode": "joint",
+      "hardness_mode": null,
+      "hardness_strength": 0.0
+  }
+  ```
+
+#### positives
+
+* Dataset: positives
+* Size: 2,200 evaluation samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                             | positive                                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 24 tokens</li><li>mean: 29.27 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 13.61 tokens</li><li>max: 44 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                           | positive                                                     |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------|
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: حاملة أدوات القطط</code>            | <code>حاملة أدوات القطة - AA04</code>                        |
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: كريم شمس أطفال</code>               | <code>واقي شمس كريمي - Chicco</code>                         |
+  | <code>Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it<br>Query: كانديسارتان هيدروكلوروثيازيد</code> | <code>Candesartan and Hydrochlorothiazide 16mg/12.5mg</code> |
+* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "mini_batch_size": 8,
+      "gather_across_devices": false,
+      "directions": [
+          "query_to_doc"
+      ],
+      "partition_mode": "joint",
+      "hardness_mode": null,
+      "hardness_strength": 0.0
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 32
+- `learning_rate`: 0.0001
+- `num_train_epochs`: 1
+- `warmup_steps`: 0.05
+- `fp16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `do_predict`: False
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 8
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 0.0001
+- `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`: None
+- `warmup_ratio`: None
+- `warmup_steps`: 0.05
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `enable_jit_checkpoint`: False
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `use_cpu`: False
+- `seed`: 42
+- `data_seed`: None
+- `bf16`: False
+- `fp16`: True
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: -1
+- `ddp_backend`: None
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `parallelism_config`: None
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `group_by_length`: False
+- `length_column_name`: length
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `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
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `hub_revision`: None
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_num_input_tokens_seen`: no
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: True
+- `use_cache`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step | Training Loss | pairs with negatives loss | positives loss |
+|:------:|:----:|:-------------:|:-------------------------:|:--------------:|
+| 0.0023 | 25   | 0.4772        | -                         | -              |
+| 0.0047 | 50   | 0.4593        | -                         | -              |
+| 0.0070 | 75   | 0.3945        | -                         | -              |
+| 0.0094 | 100  | 0.3752        | -                         | -              |
+| 0.0117 | 125  | 0.4048        | -                         | -              |
+| 0.0140 | 150  | 0.4563        | -                         | -              |
+| 0.0164 | 175  | 0.3492        | -                         | -              |
+| 0.0187 | 200  | 0.4171        | 0.3915                    | 0.1481         |
+| 0.0210 | 225  | 0.4297        | -                         | -              |
+| 0.0234 | 250  | 0.4365        | -                         | -              |
+| 0.0257 | 275  | 0.4344        | -                         | -              |
+| 0.0281 | 300  | 0.4184        | -                         | -              |
+| 0.0304 | 325  | 0.4198        | -                         | -              |
+| 0.0327 | 350  | 0.4293        | -                         | -              |
+| 0.0351 | 375  | 0.4759        | -                         | -              |
+| 0.0374 | 400  | 0.3312        | 0.3695                    | 0.1180         |
+| 0.0398 | 425  | 0.3887        | -                         | -              |
+| 0.0421 | 450  | 0.4402        | -                         | -              |
+| 0.0444 | 475  | 0.4105        | -                         | -              |
+| 0.0468 | 500  | 0.3923        | -                         | -              |
+| 0.0491 | 525  | 0.3163        | -                         | -              |
+| 0.0514 | 550  | 0.3565        | -                         | -              |
+| 0.0538 | 575  | 0.3707        | -                         | -              |
+| 0.0561 | 600  | 0.3008        | 0.3388                    | 0.1086         |
+| 0.0585 | 625  | 0.3594        | -                         | -              |
+| 0.0608 | 650  | 0.3936        | -                         | -              |
+| 0.0631 | 675  | 0.3207        | -                         | -              |
+| 0.0655 | 700  | 0.3371        | -                         | -              |
+| 0.0678 | 725  | 0.3385        | -                         | -              |
+| 0.0702 | 750  | 0.2718        | -                         | -              |
+| 0.0725 | 775  | 0.4429        | -                         | -              |
+| 0.0748 | 800  | 0.2684        | 0.3453                    | 0.1043         |
+| 0.0772 | 825  | 0.2539        | -                         | -              |
+| 0.0795 | 850  | 0.3239        | -                         | -              |
+| 0.0818 | 875  | 0.2944        | -                         | -              |
+| 0.0842 | 900  | 0.3067        | -                         | -              |
+| 0.0865 | 925  | 0.3113        | -                         | -              |
+| 0.0889 | 950  | 0.3387        | -                         | -              |
+| 0.0912 | 975  | 0.2735        | -                         | -              |
+| 0.0935 | 1000 | 0.2985        | 0.3211                    | 0.0891         |
+| 0.0959 | 1025 | 0.3553        | -                         | -              |
+| 0.0982 | 1050 | 0.2568        | -                         | -              |
+| 0.1006 | 1075 | 0.3447        | -                         | -              |
+| 0.1029 | 1100 | 0.3239        | -                         | -              |
+| 0.1052 | 1125 | 0.3015        | -                         | -              |
+| 0.1076 | 1150 | 0.3865        | -                         | -              |
+| 0.1099 | 1175 | 0.2982        | -                         | -              |
+| 0.1122 | 1200 | 0.3105        | 0.3232                    | 0.0829         |
+| 0.1146 | 1225 | 0.2964        | -                         | -              |
+| 0.1169 | 1250 | 0.2417        | -                         | -              |
+| 0.1193 | 1275 | 0.2686        | -                         | -              |
+| 0.1216 | 1300 | 0.2932        | -                         | -              |
+| 0.1239 | 1325 | 0.2383        | -                         | -              |
+| 0.1263 | 1350 | 0.3108        | -                         | -              |
+| 0.1286 | 1375 | 0.3216        | -                         | -              |
+| 0.1310 | 1400 | 0.2083        | 0.3091                    | 0.0894         |
+| 0.1333 | 1425 | 0.2933        | -                         | -              |
+| 0.1356 | 1450 | 0.2038        | -                         | -              |
+| 0.1380 | 1475 | 0.2515        | -                         | -              |
+| 0.1403 | 1500 | 0.2643        | -                         | -              |
+| 0.1426 | 1525 | 0.2484        | -                         | -              |
+| 0.1450 | 1550 | 0.3216        | -                         | -              |
+| 0.1473 | 1575 | 0.3265        | -                         | -              |
+| 0.1497 | 1600 | 0.2626        | 0.3166                    | 0.0775         |
+| 0.1520 | 1625 | 0.2811        | -                         | -              |
+| 0.1543 | 1650 | 0.2792        | -                         | -              |
+| 0.1567 | 1675 | 0.2888        | -                         | -              |
+| 0.1590 | 1700 | 0.3243        | -                         | -              |
+| 0.1614 | 1725 | 0.2318        | -                         | -              |
+| 0.1637 | 1750 | 0.2943        | -                         | -              |
+| 0.1660 | 1775 | 0.2494        | -                         | -              |
+| 0.1684 | 1800 | 0.3478        | 0.3113                    | 0.0751         |
+| 0.1707 | 1825 | 0.3265        | -                         | -              |
+| 0.1730 | 1850 | 0.2933        | -                         | -              |
+| 0.1754 | 1875 | 0.2671        | -                         | -              |
+| 0.1777 | 1900 | 0.2927        | -                         | -              |
+| 0.1801 | 1925 | 0.2939        | -                         | -              |
+| 0.1824 | 1950 | 0.2356        | -                         | -              |
+| 0.1847 | 1975 | 0.2413        | -                         | -              |
+| 0.1871 | 2000 | 0.2026        | 0.2921                    | 0.0650         |
+| 0.1894 | 2025 | 0.2663        | -                         | -              |
+| 0.1918 | 2050 | 0.2438        | -                         | -              |
+| 0.1941 | 2075 | 0.2321        | -                         | -              |
+| 0.1964 | 2100 | 0.2482        | -                         | -              |
+| 0.1988 | 2125 | 0.3000        | -                         | -              |
+| 0.2011 | 2150 | 0.1990        | -                         | -              |
+| 0.2034 | 2175 | 0.2393        | -                         | -              |
+| 0.2058 | 2200 | 0.2370        | 0.2844                    | 0.0670         |
+| 0.2081 | 2225 | 0.2131        | -                         | -              |
+| 0.2105 | 2250 | 0.2548        | -                         | -              |
+| 0.2128 | 2275 | 0.3016        | -                         | -              |
+| 0.2151 | 2300 | 0.1959        | -                         | -              |
+| 0.2175 | 2325 | 0.2604        | -                         | -              |
+| 0.2198 | 2350 | 0.3141        | -                         | -              |
+| 0.2221 | 2375 | 0.2729        | -                         | -              |
+| 0.2245 | 2400 | 0.2492        | 0.2854                    | 0.0640         |
+| 0.2268 | 2425 | 0.2326        | -                         | -              |
+| 0.2292 | 2450 | 0.2850        | -                         | -              |
+| 0.2315 | 2475 | 0.2393        | -                         | -              |
+| 0.2338 | 2500 | 0.2748        | -                         | -              |
+| 0.2362 | 2525 | 0.2289        | -                         | -              |
+| 0.2385 | 2550 | 0.2486        | -                         | -              |
+| 0.2409 | 2575 | 0.2846        | -                         | -              |
+| 0.2432 | 2600 | 0.2027        | 0.2798                    | 0.0586         |
+| 0.2455 | 2625 | 0.2336        | -                         | -              |
+| 0.2479 | 2650 | 0.2207        | -                         | -              |
+| 0.2502 | 2675 | 0.2357        | -                         | -              |
+| 0.2525 | 2700 | 0.2132        | -                         | -              |
+| 0.2549 | 2725 | 0.2152        | -                         | -              |
+| 0.2572 | 2750 | 0.2046        | -                         | -              |
+| 0.2596 | 2775 | 0.1824        | -                         | -              |
+| 0.2619 | 2800 | 0.2406        | 0.2775                    | 0.0624         |
+| 0.2642 | 2825 | 0.2240        | -                         | -              |
+| 0.2666 | 2850 | 0.2538        | -                         | -              |
+| 0.2689 | 2875 | 0.1901        | -                         | -              |
+| 0.2713 | 2900 | 0.2792        | -                         | -              |
+| 0.2736 | 2925 | 0.2489        | -                         | -              |
+| 0.2759 | 2950 | 0.2371        | -                         | -              |
+| 0.2783 | 2975 | 0.2170        | -                         | -              |
+| 0.2806 | 3000 | 0.2408        | 0.2762                    | 0.0570         |
+| 0.2829 | 3025 | 0.1543        | -                         | -              |
+| 0.2853 | 3050 | 0.2858        | -                         | -              |
+| 0.2876 | 3075 | 0.2290        | -                         | -              |
+| 0.2900 | 3100 | 0.3003        | -                         | -              |
+| 0.2923 | 3125 | 0.2143        | -                         | -              |
+| 0.2946 | 3150 | 0.2486        | -                         | -              |
+| 0.2970 | 3175 | 0.2412        | -                         | -              |
+| 0.2993 | 3200 | 0.2683        | 0.2755                    | 0.0600         |
+
+</details>
+
+### Training Time
+- **Training**: 3.4 hours
+
+### Framework Versions
+- Python: 3.12.13
+- Sentence Transformers: 5.4.1
+- Transformers: 5.0.0
+- PyTorch: 2.10.0+cu128
+- Accelerate: 1.13.0
+- Datasets: 5.0.0
+- Tokenizers: 0.22.2
+
+## 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",
+}
+```
+
+#### CachedMultipleNegativesRankingLoss
+```bibtex
+@misc{gao2021scaling,
+    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
+    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
+    year={2021},
+    eprint={2101.06983},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+<!--
+## 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-3200/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "prestoai/qwen3-embedding-0.6b-arabic-ecom",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-3200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:107d1da2bfd924135028064ce75d773e7c07be168c0c7c5c2dd51a61ea6f35ed
+size 40419816

checkpoint-3200/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-3200/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "pytorch": "2.10.0+cu128",
+    "sentence_transformers": "5.4.1",
+    "transformers": "5.0.0"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "document": "",
+    "query": "Instruct: Given an Arabic e-commerce search query, retrieve the product that best matches it\nQuery: "
+  },
+  "similarity_fn_name": "cosine"
+}

checkpoint-3200/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
+  }
+]

checkpoint-3200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb0dcf683da0f8873d9c0ced016902b5278db682dd2f69abab08d4c081a387b4
+size 81075515

checkpoint-3200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f2a628cca27586b7b9685c1ef905d45e62563c903b70ba86386be347460a24
+size 14581

checkpoint-3200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83284a67c04a21d8f3293db170a283e02ab6a9faf6b4770338bf77fe03338a8c
+size 1383

checkpoint-3200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fed8ced588c815132b4185b9a709668a7ce8486f26c73be37a22ef968e56a29
+size 1465

checkpoint-3200/sentence_bert_config.json

@@ -0,0 +1,10 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        }
+    },
+    "module_output_name": "token_embeddings"
+}

checkpoint-3200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b23115c7cace3b6700c333da5038e66e95a9c2c71531b6953563a8c8bb1dee
+size 11423967

checkpoint-3200/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 128,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-3200/trainer_state.json

@@ -0,0 +1,1186 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.29931718267701807,
+  "eval_steps": 200,
+  "global_step": 3200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0023384154896642037,
+      "grad_norm": 1.9981695413589478,
+      "learning_rate": 4.4859813084112145e-06,
+      "loss": 0.47716766357421875,
+      "step": 25
+    },
+    {
+      "epoch": 0.004676830979328407,
+      "grad_norm": 1.9483280181884766,
+      "learning_rate": 9.158878504672897e-06,
+      "loss": 0.4592530059814453,
+      "step": 50
+    },
+    {
+      "epoch": 0.0070152464689926105,
+      "grad_norm": 2.1290855407714844,
+      "learning_rate": 1.3831775700934579e-05,
+      "loss": 0.394501838684082,
+      "step": 75
+    },
+    {
+      "epoch": 0.009353661958656815,
+      "grad_norm": 2.8394205570220947,
+      "learning_rate": 1.8504672897196264e-05,
+      "loss": 0.3752219009399414,
+      "step": 100
+    },
+    {
+      "epoch": 0.011692077448321018,
+      "grad_norm": 2.5833706855773926,
+      "learning_rate": 2.3177570093457944e-05,
+      "loss": 0.40475303649902344,
+      "step": 125
+    },
+    {
+      "epoch": 0.014030492937985221,
+      "grad_norm": 2.622011661529541,
+      "learning_rate": 2.7850467289719627e-05,
+      "loss": 0.45625301361083986,
+      "step": 150
+    },
+    {
+      "epoch": 0.016368908427649424,
+      "grad_norm": 2.9406535625457764,
+      "learning_rate": 3.2523364485981314e-05,
+      "loss": 0.34918937683105467,
+      "step": 175
+    },
+    {
+      "epoch": 0.01870732391731363,
+      "grad_norm": 3.8391785621643066,
+      "learning_rate": 3.7196261682242994e-05,
+      "loss": 0.41711517333984377,
+      "step": 200
+    },
+    {
+      "epoch": 0.01870732391731363,
+      "eval_pairs_with_negatives_loss": 0.3914637565612793,
+      "eval_pairs_with_negatives_runtime": 44.0353,
+      "eval_pairs_with_negatives_samples_per_second": 28.523,
+      "eval_pairs_with_negatives_steps_per_second": 3.565,
+      "step": 200
+    },
+    {
+      "epoch": 0.01870732391731363,
+      "eval_positives_loss": 0.1480681300163269,
+      "eval_positives_runtime": 51.7193,
+      "eval_positives_samples_per_second": 42.537,
+      "eval_positives_steps_per_second": 5.317,
+      "step": 200
+    },
+    {
+      "epoch": 0.02104573940697783,
+      "grad_norm": 2.3628170490264893,
+      "learning_rate": 4.186915887850468e-05,
+      "loss": 0.4296648406982422,
+      "step": 225
+    },
+    {
+      "epoch": 0.023384154896642036,
+      "grad_norm": 2.698835611343384,
+      "learning_rate": 4.6542056074766354e-05,
+      "loss": 0.43652393341064455,
+      "step": 250
+    },
+    {
+      "epoch": 0.02572257038630624,
+      "grad_norm": 4.1166558265686035,
+      "learning_rate": 5.121495327102804e-05,
+      "loss": 0.4344004440307617,
+      "step": 275
+    },
+    {
+      "epoch": 0.028060985875970442,
+      "grad_norm": 4.551556587219238,
+      "learning_rate": 5.588785046728973e-05,
+      "loss": 0.41842262268066405,
+      "step": 300
+    },
+    {
+      "epoch": 0.030399401365634647,
+      "grad_norm": 2.3925657272338867,
+      "learning_rate": 6.056074766355141e-05,
+      "loss": 0.4197782897949219,
+      "step": 325
+    },
+    {
+      "epoch": 0.03273781685529885,
+      "grad_norm": 3.1023190021514893,
+      "learning_rate": 6.52336448598131e-05,
+      "loss": 0.4292975616455078,
+      "step": 350
+    },
+    {
+      "epoch": 0.03507623234496305,
+      "grad_norm": 4.1481032371521,
+      "learning_rate": 6.990654205607478e-05,
+      "loss": 0.4758753204345703,
+      "step": 375
+    },
+    {
+      "epoch": 0.03741464783462726,
+      "grad_norm": 3.8799962997436523,
+      "learning_rate": 7.457943925233644e-05,
+      "loss": 0.3311753845214844,
+      "step": 400
+    },
+    {
+      "epoch": 0.03741464783462726,
+      "eval_pairs_with_negatives_loss": 0.3694910407066345,
+      "eval_pairs_with_negatives_runtime": 44.2166,
+      "eval_pairs_with_negatives_samples_per_second": 28.406,
+      "eval_pairs_with_negatives_steps_per_second": 3.551,
+      "step": 400
+    },
+    {
+      "epoch": 0.03741464783462726,
+      "eval_positives_loss": 0.11797073483467102,
+      "eval_positives_runtime": 51.3355,
+      "eval_positives_samples_per_second": 42.855,
+      "eval_positives_steps_per_second": 5.357,
+      "step": 400
+    },
+    {
+      "epoch": 0.03975306332429146,
+      "grad_norm": 3.7068564891815186,
+      "learning_rate": 7.925233644859813e-05,
+      "loss": 0.388726806640625,
+      "step": 425
+    },
+    {
+      "epoch": 0.04209147881395566,
+      "grad_norm": 2.3407328128814697,
+      "learning_rate": 8.392523364485981e-05,
+      "loss": 0.4401784133911133,
+      "step": 450
+    },
+    {
+      "epoch": 0.04442989430361987,
+      "grad_norm": 3.0923948287963867,
+      "learning_rate": 8.85981308411215e-05,
+      "loss": 0.41050430297851564,
+      "step": 475
+    },
+    {
+      "epoch": 0.04676830979328407,
+      "grad_norm": 2.626753568649292,
+      "learning_rate": 9.327102803738317e-05,
+      "loss": 0.3923164749145508,
+      "step": 500
+    },
+    {
+      "epoch": 0.04910672528294827,
+      "grad_norm": 2.729557991027832,
+      "learning_rate": 9.794392523364486e-05,
+      "loss": 0.3163204765319824,
+      "step": 525
+    },
+    {
+      "epoch": 0.05144514077261248,
+      "grad_norm": 3.1612608432769775,
+      "learning_rate": 9.986215045293424e-05,
+      "loss": 0.35652976989746094,
+      "step": 550
+    },
+    {
+      "epoch": 0.05378355626227668,
+      "grad_norm": 2.224350690841675,
+      "learning_rate": 9.961599054745964e-05,
+      "loss": 0.37072269439697264,
+      "step": 575
+    },
+    {
+      "epoch": 0.056121971751940884,
+      "grad_norm": 3.207382917404175,
+      "learning_rate": 9.936983064198503e-05,
+      "loss": 0.3007513427734375,
+      "step": 600
+    },
+    {
+      "epoch": 0.056121971751940884,
+      "eval_pairs_with_negatives_loss": 0.3388254940509796,
+      "eval_pairs_with_negatives_runtime": 43.9558,
+      "eval_pairs_with_negatives_samples_per_second": 28.574,
+      "eval_pairs_with_negatives_steps_per_second": 3.572,
+      "step": 600
+    },
+    {
+      "epoch": 0.056121971751940884,
+      "eval_positives_loss": 0.10862970352172852,
+      "eval_positives_runtime": 51.7355,
+      "eval_positives_samples_per_second": 42.524,
+      "eval_positives_steps_per_second": 5.315,
+      "step": 600
+    },
+    {
+      "epoch": 0.058460387241605086,
+      "grad_norm": 4.494985103607178,
+      "learning_rate": 9.912367073651045e-05,
+      "loss": 0.35943916320800784,
+      "step": 625
+    },
+    {
+      "epoch": 0.060798802731269294,
+      "grad_norm": 3.7057838439941406,
+      "learning_rate": 9.887751083103585e-05,
+      "loss": 0.39355968475341796,
+      "step": 650
+    },
+    {
+      "epoch": 0.06313721822093349,
+      "grad_norm": 1.6454180479049683,
+      "learning_rate": 9.863135092556125e-05,
+      "loss": 0.32073760986328126,
+      "step": 675
+    },
+    {
+      "epoch": 0.0654756337105977,
+      "grad_norm": 3.901522636413574,
+      "learning_rate": 9.838519102008666e-05,
+      "loss": 0.3371485900878906,
+      "step": 700
+    },
+    {
+      "epoch": 0.0678140492002619,
+      "grad_norm": 2.2362253665924072,
+      "learning_rate": 9.813903111461206e-05,
+      "loss": 0.3385154724121094,
+      "step": 725
+    },
+    {
+      "epoch": 0.0701524646899261,
+      "grad_norm": 2.490204334259033,
+      "learning_rate": 9.789287120913746e-05,
+      "loss": 0.2718297004699707,
+      "step": 750
+    },
+    {
+      "epoch": 0.07249088017959031,
+      "grad_norm": 2.2875030040740967,
+      "learning_rate": 9.764671130366287e-05,
+      "loss": 0.44294830322265627,
+      "step": 775
+    },
+    {
+      "epoch": 0.07482929566925452,
+      "grad_norm": 1.40684175491333,
+      "learning_rate": 9.740055139818827e-05,
+      "loss": 0.2684394645690918,
+      "step": 800
+    },
+    {
+      "epoch": 0.07482929566925452,
+      "eval_pairs_with_negatives_loss": 0.34527480602264404,
+      "eval_pairs_with_negatives_runtime": 44.0724,
+      "eval_pairs_with_negatives_samples_per_second": 28.499,
+      "eval_pairs_with_negatives_steps_per_second": 3.562,
+      "step": 800
+    },
+    {
+      "epoch": 0.07482929566925452,
+      "eval_positives_loss": 0.10431129485368729,
+      "eval_positives_runtime": 51.6255,
+      "eval_positives_samples_per_second": 42.615,
+      "eval_positives_steps_per_second": 5.327,
+      "step": 800
+    },
+    {
+      "epoch": 0.07716771115891871,
+      "grad_norm": 2.8712947368621826,
+      "learning_rate": 9.715439149271367e-05,
+      "loss": 0.25394817352294924,
+      "step": 825
+    },
+    {
+      "epoch": 0.07950612664858292,
+      "grad_norm": 1.8017457723617554,
+      "learning_rate": 9.690823158723908e-05,
+      "loss": 0.32388198852539063,
+      "step": 850
+    },
+    {
+      "epoch": 0.08184454213824713,
+      "grad_norm": 2.945971727371216,
+      "learning_rate": 9.666207168176448e-05,
+      "loss": 0.29435272216796876,
+      "step": 875
+    },
+    {
+      "epoch": 0.08418295762791132,
+      "grad_norm": 2.1370229721069336,
+      "learning_rate": 9.641591177628988e-05,
+      "loss": 0.30667646408081056,
+      "step": 900
+    },
+    {
+      "epoch": 0.08652137311757553,
+      "grad_norm": 3.4880053997039795,
+      "learning_rate": 9.616975187081529e-05,
+      "loss": 0.3113353729248047,
+      "step": 925
+    },
+    {
+      "epoch": 0.08885978860723974,
+      "grad_norm": 1.221985101699829,
+      "learning_rate": 9.592359196534069e-05,
+      "loss": 0.33869354248046873,
+      "step": 950
+    },
+    {
+      "epoch": 0.09119820409690393,
+      "grad_norm": 2.5686190128326416,
+      "learning_rate": 9.567743205986609e-05,
+      "loss": 0.2734596633911133,
+      "step": 975
+    },
+    {
+      "epoch": 0.09353661958656814,
+      "grad_norm": 1.7126892805099487,
+      "learning_rate": 9.54312721543915e-05,
+      "loss": 0.2984904098510742,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09353661958656814,
+      "eval_pairs_with_negatives_loss": 0.3210560381412506,
+      "eval_pairs_with_negatives_runtime": 44.9784,
+      "eval_pairs_with_negatives_samples_per_second": 27.925,
+      "eval_pairs_with_negatives_steps_per_second": 3.491,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09353661958656814,
+      "eval_positives_loss": 0.08913413435220718,
+      "eval_positives_runtime": 52.3889,
+      "eval_positives_samples_per_second": 41.994,
+      "eval_positives_steps_per_second": 5.249,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09587503507623235,
+      "grad_norm": 1.6900842189788818,
+      "learning_rate": 9.51851122489169e-05,
+      "loss": 0.355332145690918,
+      "step": 1025
+    },
+    {
+      "epoch": 0.09821345056589655,
+      "grad_norm": 0.7989633083343506,
+      "learning_rate": 9.49389523434423e-05,
+      "loss": 0.25679166793823244,
+      "step": 1050
+    },
+    {
+      "epoch": 0.10055186605556075,
+      "grad_norm": 1.7311954498291016,
+      "learning_rate": 9.469279243796771e-05,
+      "loss": 0.344718017578125,
+      "step": 1075
+    },
+    {
+      "epoch": 0.10289028154522496,
+      "grad_norm": 1.9694781303405762,
+      "learning_rate": 9.444663253249311e-05,
+      "loss": 0.3239378356933594,
+      "step": 1100
+    },
+    {
+      "epoch": 0.10522869703488916,
+      "grad_norm": 2.0283656120300293,
+      "learning_rate": 9.420047262701852e-05,
+      "loss": 0.3015079879760742,
+      "step": 1125
+    },
+    {
+      "epoch": 0.10756711252455337,
+      "grad_norm": 2.0422067642211914,
+      "learning_rate": 9.395431272154392e-05,
+      "loss": 0.3864572906494141,
+      "step": 1150
+    },
+    {
+      "epoch": 0.10990552801421756,
+      "grad_norm": 2.2227938175201416,
+      "learning_rate": 9.370815281606933e-05,
+      "loss": 0.2981968116760254,
+      "step": 1175
+    },
+    {
+      "epoch": 0.11224394350388177,
+      "grad_norm": 1.9632631540298462,
+      "learning_rate": 9.346199291059473e-05,
+      "loss": 0.3105415725708008,
+      "step": 1200
+    },
+    {
+      "epoch": 0.11224394350388177,
+      "eval_pairs_with_negatives_loss": 0.3232487738132477,
+      "eval_pairs_with_negatives_runtime": 44.5297,
+      "eval_pairs_with_negatives_samples_per_second": 28.206,
+      "eval_pairs_with_negatives_steps_per_second": 3.526,
+      "step": 1200
+    },
+    {
+      "epoch": 0.11224394350388177,
+      "eval_positives_loss": 0.08286190032958984,
+      "eval_positives_runtime": 52.0911,
+      "eval_positives_samples_per_second": 42.234,
+      "eval_positives_steps_per_second": 5.279,
+      "step": 1200
+    },
+    {
+      "epoch": 0.11458235899354598,
+      "grad_norm": 0.5930349826812744,
+      "learning_rate": 9.321583300512013e-05,
+      "loss": 0.29635957717895506,
+      "step": 1225
+    },
+    {
+      "epoch": 0.11692077448321017,
+      "grad_norm": 1.5982012748718262,
+      "learning_rate": 9.296967309964554e-05,
+      "loss": 0.24172809600830078,
+      "step": 1250
+    },
+    {
+      "epoch": 0.11925918997287438,
+      "grad_norm": 0.5673118829727173,
+      "learning_rate": 9.272351319417094e-05,
+      "loss": 0.26859012603759763,
+      "step": 1275
+    },
+    {
+      "epoch": 0.12159760546253859,
+      "grad_norm": 1.4948972463607788,
+      "learning_rate": 9.247735328869634e-05,
+      "loss": 0.2932207489013672,
+      "step": 1300
+    },
+    {
+      "epoch": 0.12393602095220278,
+      "grad_norm": 1.545386791229248,
+      "learning_rate": 9.223119338322175e-05,
+      "loss": 0.2383422088623047,
+      "step": 1325
+    },
+    {
+      "epoch": 0.12627443644186698,
+      "grad_norm": 2.5136566162109375,
+      "learning_rate": 9.198503347774715e-05,
+      "loss": 0.31081596374511716,
+      "step": 1350
+    },
+    {
+      "epoch": 0.12861285193153119,
+      "grad_norm": 1.8467180728912354,
+      "learning_rate": 9.173887357227255e-05,
+      "loss": 0.321625862121582,
+      "step": 1375
+    },
+    {
+      "epoch": 0.1309512674211954,
+      "grad_norm": 1.3382201194763184,
+      "learning_rate": 9.149271366679796e-05,
+      "loss": 0.2083415222167969,
+      "step": 1400
+    },
+    {
+      "epoch": 0.1309512674211954,
+      "eval_pairs_with_negatives_loss": 0.3091065585613251,
+      "eval_pairs_with_negatives_runtime": 44.3305,
+      "eval_pairs_with_negatives_samples_per_second": 28.333,
+      "eval_pairs_with_negatives_steps_per_second": 3.542,
+      "step": 1400
+    },
+    {
+      "epoch": 0.1309512674211954,
+      "eval_positives_loss": 0.08935973793268204,
+      "eval_positives_runtime": 51.7119,
+      "eval_positives_samples_per_second": 42.543,
+      "eval_positives_steps_per_second": 5.318,
+      "step": 1400
+    },
+    {
+      "epoch": 0.1332896829108596,
+      "grad_norm": 1.0311458110809326,
+      "learning_rate": 9.124655376132336e-05,
+      "loss": 0.2932785987854004,
+      "step": 1425
+    },
+    {
+      "epoch": 0.1356280984005238,
+      "grad_norm": 2.180497884750366,
+      "learning_rate": 9.100039385584876e-05,
+      "loss": 0.2038213348388672,
+      "step": 1450
+    },
+    {
+      "epoch": 0.13796651389018802,
+      "grad_norm": 2.1046860218048096,
+      "learning_rate": 9.075423395037416e-05,
+      "loss": 0.2514521217346191,
+      "step": 1475
+    },
+    {
+      "epoch": 0.1403049293798522,
+      "grad_norm": 2.4484400749206543,
+      "learning_rate": 9.050807404489957e-05,
+      "loss": 0.26426057815551757,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1426433448695164,
+      "grad_norm": 0.5209934711456299,
+      "learning_rate": 9.026191413942497e-05,
+      "loss": 0.2484210968017578,
+      "step": 1525
+    },
+    {
+      "epoch": 0.14498176035918062,
+      "grad_norm": 2.0274691581726074,
+      "learning_rate": 9.001575423395037e-05,
+      "loss": 0.32157943725585936,
+      "step": 1550
+    },
+    {
+      "epoch": 0.14732017584884483,
+      "grad_norm": 2.850849151611328,
+      "learning_rate": 8.976959432847578e-05,
+      "loss": 0.32649993896484375,
+      "step": 1575
+    },
+    {
+      "epoch": 0.14965859133850903,
+      "grad_norm": 3.255429267883301,
+      "learning_rate": 8.952343442300118e-05,
+      "loss": 0.26256885528564455,
+      "step": 1600
+    },
+    {
+      "epoch": 0.14965859133850903,
+      "eval_pairs_with_negatives_loss": 0.3166193962097168,
+      "eval_pairs_with_negatives_runtime": 44.3277,
+      "eval_pairs_with_negatives_samples_per_second": 28.334,
+      "eval_pairs_with_negatives_steps_per_second": 3.542,
+      "step": 1600
+    },
+    {
+      "epoch": 0.14965859133850903,
+      "eval_positives_loss": 0.077468141913414,
+      "eval_positives_runtime": 51.8074,
+      "eval_positives_samples_per_second": 42.465,
+      "eval_positives_steps_per_second": 5.308,
+      "step": 1600
+    },
+    {
+      "epoch": 0.15199700682817324,
+      "grad_norm": 2.324928045272827,
+      "learning_rate": 8.927727451752658e-05,
+      "loss": 0.28111976623535156,
+      "step": 1625
+    },
+    {
+      "epoch": 0.15433542231783742,
+      "grad_norm": 1.722293496131897,
+      "learning_rate": 8.9031114612052e-05,
+      "loss": 0.27923690795898437,
+      "step": 1650
+    },
+    {
+      "epoch": 0.15667383780750163,
+      "grad_norm": 2.5481624603271484,
+      "learning_rate": 8.87849547065774e-05,
+      "loss": 0.2887708282470703,
+      "step": 1675
+    },
+    {
+      "epoch": 0.15901225329716584,
+      "grad_norm": 1.4688785076141357,
+      "learning_rate": 8.853879480110279e-05,
+      "loss": 0.32429874420166016,
+      "step": 1700
+    },
+    {
+      "epoch": 0.16135066878683005,
+      "grad_norm": 0.970000684261322,
+      "learning_rate": 8.82926348956282e-05,
+      "loss": 0.23183115005493163,
+      "step": 1725
+    },
+    {
+      "epoch": 0.16368908427649426,
+      "grad_norm": 2.141195297241211,
+      "learning_rate": 8.80464749901536e-05,
+      "loss": 0.2943249702453613,
+      "step": 1750
+    },
+    {
+      "epoch": 0.16602749976615844,
+      "grad_norm": 0.9625000357627869,
+      "learning_rate": 8.7800315084679e-05,
+      "loss": 0.24936399459838868,
+      "step": 1775
+    },
+    {
+      "epoch": 0.16836591525582265,
+      "grad_norm": 2.191002368927002,
+      "learning_rate": 8.755415517920442e-05,
+      "loss": 0.3477742004394531,
+      "step": 1800
+    },
+    {
+      "epoch": 0.16836591525582265,
+      "eval_pairs_with_negatives_loss": 0.311288446187973,
+      "eval_pairs_with_negatives_runtime": 44.4068,
+      "eval_pairs_with_negatives_samples_per_second": 28.284,
+      "eval_pairs_with_negatives_steps_per_second": 3.535,
+      "step": 1800
+    },
+    {
+      "epoch": 0.16836591525582265,
+      "eval_positives_loss": 0.07508163899183273,
+      "eval_positives_runtime": 51.7306,
+      "eval_positives_samples_per_second": 42.528,
+      "eval_positives_steps_per_second": 5.316,
+      "step": 1800
+    },
+    {
+      "epoch": 0.17070433074548685,
+      "grad_norm": 2.958533525466919,
+      "learning_rate": 8.730799527372981e-05,
+      "loss": 0.3265147018432617,
+      "step": 1825
+    },
+    {
+      "epoch": 0.17304274623515106,
+      "grad_norm": 2.005192756652832,
+      "learning_rate": 8.706183536825521e-05,
+      "loss": 0.29331169128417967,
+      "step": 1850
+    },
+    {
+      "epoch": 0.17538116172481527,
+      "grad_norm": 2.02463960647583,
+      "learning_rate": 8.681567546278063e-05,
+      "loss": 0.2671446990966797,
+      "step": 1875
+    },
+    {
+      "epoch": 0.17771957721447948,
+      "grad_norm": 2.153892755508423,
+      "learning_rate": 8.656951555730604e-05,
+      "loss": 0.29273582458496095,
+      "step": 1900
+    },
+    {
+      "epoch": 0.18005799270414366,
+      "grad_norm": 2.7679359912872314,
+      "learning_rate": 8.632335565183144e-05,
+      "loss": 0.29389562606811526,
+      "step": 1925
+    },
+    {
+      "epoch": 0.18239640819380787,
+      "grad_norm": 2.963479995727539,
+      "learning_rate": 8.607719574635684e-05,
+      "loss": 0.2356496810913086,
+      "step": 1950
+    },
+    {
+      "epoch": 0.18473482368347208,
+      "grad_norm": 2.6095352172851562,
+      "learning_rate": 8.583103584088225e-05,
+      "loss": 0.24131065368652344,
+      "step": 1975
+    },
+    {
+      "epoch": 0.18707323917313629,
+      "grad_norm": 2.1474149227142334,
+      "learning_rate": 8.558487593540765e-05,
+      "loss": 0.20256967544555665,
+      "step": 2000
+    },
+    {
+      "epoch": 0.18707323917313629,
+      "eval_pairs_with_negatives_loss": 0.2920902371406555,
+      "eval_pairs_with_negatives_runtime": 44.1734,
+      "eval_pairs_with_negatives_samples_per_second": 28.433,
+      "eval_pairs_with_negatives_steps_per_second": 3.554,
+      "step": 2000
+    },
+    {
+      "epoch": 0.18707323917313629,
+      "eval_positives_loss": 0.06497267633676529,
+      "eval_positives_runtime": 51.883,
+      "eval_positives_samples_per_second": 42.403,
+      "eval_positives_steps_per_second": 5.3,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1894116546628005,
+      "grad_norm": 1.4445933103561401,
+      "learning_rate": 8.533871602993305e-05,
+      "loss": 0.2663409423828125,
+      "step": 2025
+    },
+    {
+      "epoch": 0.1917500701524647,
+      "grad_norm": 2.1832194328308105,
+      "learning_rate": 8.509255612445846e-05,
+      "loss": 0.24383123397827147,
+      "step": 2050
+    },
+    {
+      "epoch": 0.19408848564212888,
+      "grad_norm": 1.7301610708236694,
+      "learning_rate": 8.484639621898386e-05,
+      "loss": 0.23211950302124024,
+      "step": 2075
+    },
+    {
+      "epoch": 0.1964269011317931,
+      "grad_norm": 1.9371556043624878,
+      "learning_rate": 8.460023631350926e-05,
+      "loss": 0.24819377899169923,
+      "step": 2100
+    },
+    {
+      "epoch": 0.1987653166214573,
+      "grad_norm": 2.9007513523101807,
+      "learning_rate": 8.435407640803467e-05,
+      "loss": 0.3000238037109375,
+      "step": 2125
+    },
+    {
+      "epoch": 0.2011037321111215,
+      "grad_norm": 2.155949115753174,
+      "learning_rate": 8.410791650256007e-05,
+      "loss": 0.19902172088623046,
+      "step": 2150
+    },
+    {
+      "epoch": 0.20344214760078572,
+      "grad_norm": 1.1646662950515747,
+      "learning_rate": 8.386175659708547e-05,
+      "loss": 0.2393128204345703,
+      "step": 2175
+    },
+    {
+      "epoch": 0.20578056309044993,
+      "grad_norm": 0.6050031185150146,
+      "learning_rate": 8.361559669161088e-05,
+      "loss": 0.23696456909179686,
+      "step": 2200
+    },
+    {
+      "epoch": 0.20578056309044993,
+      "eval_pairs_with_negatives_loss": 0.2844306230545044,
+      "eval_pairs_with_negatives_runtime": 43.6185,
+      "eval_pairs_with_negatives_samples_per_second": 28.795,
+      "eval_pairs_with_negatives_steps_per_second": 3.599,
+      "step": 2200
+    },
+    {
+      "epoch": 0.20578056309044993,
+      "eval_positives_loss": 0.06695789843797684,
+      "eval_positives_runtime": 51.2178,
+      "eval_positives_samples_per_second": 42.954,
+      "eval_positives_steps_per_second": 5.369,
+      "step": 2200
+    },
+    {
+      "epoch": 0.2081189785801141,
+      "grad_norm": 1.7829246520996094,
+      "learning_rate": 8.336943678613628e-05,
+      "loss": 0.21305316925048828,
+      "step": 2225
+    },
+    {
+      "epoch": 0.21045739406977831,
+      "grad_norm": 1.9647576808929443,
+      "learning_rate": 8.312327688066168e-05,
+      "loss": 0.2547788429260254,
+      "step": 2250
+    },
+    {
+      "epoch": 0.21279580955944252,
+      "grad_norm": 0.9661738276481628,
+      "learning_rate": 8.287711697518709e-05,
+      "loss": 0.30158185958862305,
+      "step": 2275
+    },
+    {
+      "epoch": 0.21513422504910673,
+      "grad_norm": 0.4944344162940979,
+      "learning_rate": 8.263095706971249e-05,
+      "loss": 0.1959225845336914,
+      "step": 2300
+    },
+    {
+      "epoch": 0.21747264053877094,
+      "grad_norm": 2.383636474609375,
+      "learning_rate": 8.238479716423789e-05,
+      "loss": 0.260382194519043,
+      "step": 2325
+    },
+    {
+      "epoch": 0.21981105602843512,
+      "grad_norm": 2.4864633083343506,
+      "learning_rate": 8.21386372587633e-05,
+      "loss": 0.3141353225708008,
+      "step": 2350
+    },
+    {
+      "epoch": 0.22214947151809933,
+      "grad_norm": 1.3516175746917725,
+      "learning_rate": 8.18924773532887e-05,
+      "loss": 0.2728991889953613,
+      "step": 2375
+    },
+    {
+      "epoch": 0.22448788700776354,
+      "grad_norm": 3.200805902481079,
+      "learning_rate": 8.16463174478141e-05,
+      "loss": 0.24915071487426757,
+      "step": 2400
+    },
+    {
+      "epoch": 0.22448788700776354,
+      "eval_pairs_with_negatives_loss": 0.2853996157646179,
+      "eval_pairs_with_negatives_runtime": 44.3715,
+      "eval_pairs_with_negatives_samples_per_second": 28.306,
+      "eval_pairs_with_negatives_steps_per_second": 3.538,
+      "step": 2400
+    },
+    {
+      "epoch": 0.22448788700776354,
+      "eval_positives_loss": 0.06402233988046646,
+      "eval_positives_runtime": 51.541,
+      "eval_positives_samples_per_second": 42.684,
+      "eval_positives_steps_per_second": 5.336,
+      "step": 2400
+    },
+    {
+      "epoch": 0.22682630249742775,
+      "grad_norm": 2.3375115394592285,
+      "learning_rate": 8.140015754233951e-05,
+      "loss": 0.23255537033081056,
+      "step": 2425
+    },
+    {
+      "epoch": 0.22916471798709195,
+      "grad_norm": 1.075677752494812,
+      "learning_rate": 8.115399763686491e-05,
+      "loss": 0.2849599456787109,
+      "step": 2450
+    },
+    {
+      "epoch": 0.23150313347675616,
+      "grad_norm": 1.7264649868011475,
+      "learning_rate": 8.090783773139031e-05,
+      "loss": 0.23932256698608398,
+      "step": 2475
+    },
+    {
+      "epoch": 0.23384154896642034,
+      "grad_norm": 2.3798885345458984,
+      "learning_rate": 8.066167782591572e-05,
+      "loss": 0.27479507446289064,
+      "step": 2500
+    },
+    {
+      "epoch": 0.23617996445608455,
+      "grad_norm": 1.7838364839553833,
+      "learning_rate": 8.041551792044112e-05,
+      "loss": 0.22890100479125977,
+      "step": 2525
+    },
+    {
+      "epoch": 0.23851837994574876,
+      "grad_norm": 0.8337921500205994,
+      "learning_rate": 8.016935801496652e-05,
+      "loss": 0.24863414764404296,
+      "step": 2550
+    },
+    {
+      "epoch": 0.24085679543541297,
+      "grad_norm": 3.2835209369659424,
+      "learning_rate": 7.992319810949192e-05,
+      "loss": 0.2846149635314941,
+      "step": 2575
+    },
+    {
+      "epoch": 0.24319521092507718,
+      "grad_norm": 1.3565106391906738,
+      "learning_rate": 7.967703820401733e-05,
+      "loss": 0.2026744842529297,
+      "step": 2600
+    },
+    {
+      "epoch": 0.24319521092507718,
+      "eval_pairs_with_negatives_loss": 0.27976956963539124,
+      "eval_pairs_with_negatives_runtime": 44.1274,
+      "eval_pairs_with_negatives_samples_per_second": 28.463,
+      "eval_pairs_with_negatives_steps_per_second": 3.558,
+      "step": 2600
+    },
+    {
+      "epoch": 0.24319521092507718,
+      "eval_positives_loss": 0.05857069417834282,
+      "eval_positives_runtime": 51.6223,
+      "eval_positives_samples_per_second": 42.617,
+      "eval_positives_steps_per_second": 5.327,
+      "step": 2600
+    },
+    {
+      "epoch": 0.24553362641474138,
+      "grad_norm": 1.8603383302688599,
+      "learning_rate": 7.943087829854273e-05,
+      "loss": 0.23360692977905273,
+      "step": 2625
+    },
+    {
+      "epoch": 0.24787204190440557,
+      "grad_norm": 2.318513870239258,
+      "learning_rate": 7.918471839306813e-05,
+      "loss": 0.2207220458984375,
+      "step": 2650
+    },
+    {
+      "epoch": 0.2502104573940698,
+      "grad_norm": 1.7352806329727173,
+      "learning_rate": 7.893855848759354e-05,
+      "loss": 0.23572732925415038,
+      "step": 2675
+    },
+    {
+      "epoch": 0.25254887288373395,
+      "grad_norm": 2.457981824874878,
+      "learning_rate": 7.869239858211895e-05,
+      "loss": 0.21319828033447266,
+      "step": 2700
+    },
+    {
+      "epoch": 0.2548872883733982,
+      "grad_norm": 1.7361868619918823,
+      "learning_rate": 7.844623867664435e-05,
+      "loss": 0.21519132614135741,
+      "step": 2725
+    },
+    {
+      "epoch": 0.25722570386306237,
+      "grad_norm": 2.6403586864471436,
+      "learning_rate": 7.820007877116977e-05,
+      "loss": 0.2046283531188965,
+      "step": 2750
+    },
+    {
+      "epoch": 0.2595641193527266,
+      "grad_norm": 2.263866424560547,
+      "learning_rate": 7.795391886569517e-05,
+      "loss": 0.18240520477294922,
+      "step": 2775
+    },
+    {
+      "epoch": 0.2619025348423908,
+      "grad_norm": 2.069082736968994,
+      "learning_rate": 7.770775896022056e-05,
+      "loss": 0.2405707359313965,
+      "step": 2800
+    },
+    {
+      "epoch": 0.2619025348423908,
+      "eval_pairs_with_negatives_loss": 0.2774912714958191,
+      "eval_pairs_with_negatives_runtime": 44.1229,
+      "eval_pairs_with_negatives_samples_per_second": 28.466,
+      "eval_pairs_with_negatives_steps_per_second": 3.558,
+      "step": 2800
+    },
+    {
+      "epoch": 0.2619025348423908,
+      "eval_positives_loss": 0.06239576265215874,
+      "eval_positives_runtime": 51.4606,
+      "eval_positives_samples_per_second": 42.751,
+      "eval_positives_steps_per_second": 5.344,
+      "step": 2800
+    },
+    {
+      "epoch": 0.264240950332055,
+      "grad_norm": 1.5124787092208862,
+      "learning_rate": 7.746159905474598e-05,
+      "loss": 0.2240062713623047,
+      "step": 2825
+    },
+    {
+      "epoch": 0.2665793658217192,
+      "grad_norm": 2.6289567947387695,
+      "learning_rate": 7.721543914927138e-05,
+      "loss": 0.2537799644470215,
+      "step": 2850
+    },
+    {
+      "epoch": 0.2689177813113834,
+      "grad_norm": 1.4767881631851196,
+      "learning_rate": 7.696927924379677e-05,
+      "loss": 0.19011005401611328,
+      "step": 2875
+    },
+    {
+      "epoch": 0.2712561968010476,
+      "grad_norm": 1.8631181716918945,
+      "learning_rate": 7.672311933832217e-05,
+      "loss": 0.27923820495605467,
+      "step": 2900
+    },
+    {
+      "epoch": 0.2735946122907118,
+      "grad_norm": 1.699515461921692,
+      "learning_rate": 7.647695943284759e-05,
+      "loss": 0.24893655776977539,
+      "step": 2925
+    },
+    {
+      "epoch": 0.27593302778037604,
+      "grad_norm": 1.1183840036392212,
+      "learning_rate": 7.623079952737299e-05,
+      "loss": 0.23708009719848633,
+      "step": 2950
+    },
+    {
+      "epoch": 0.2782714432700402,
+      "grad_norm": 1.764267921447754,
+      "learning_rate": 7.598463962189838e-05,
+      "loss": 0.2170231056213379,
+      "step": 2975
+    },
+    {
+      "epoch": 0.2806098587597044,
+      "grad_norm": 1.3701727390289307,
+      "learning_rate": 7.57384797164238e-05,
+      "loss": 0.2408245849609375,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2806098587597044,
+      "eval_pairs_with_negatives_loss": 0.27622753381729126,
+      "eval_pairs_with_negatives_runtime": 44.0716,
+      "eval_pairs_with_negatives_samples_per_second": 28.499,
+      "eval_pairs_with_negatives_steps_per_second": 3.562,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2806098587597044,
+      "eval_positives_loss": 0.05702820420265198,
+      "eval_positives_runtime": 51.7038,
+      "eval_positives_samples_per_second": 42.55,
+      "eval_positives_steps_per_second": 5.319,
+      "step": 3000
+    },
+    {
+      "epoch": 0.28294827424936864,
+      "grad_norm": 0.21540337800979614,
+      "learning_rate": 7.54923198109492e-05,
+      "loss": 0.15430140495300293,
+      "step": 3025
+    },
+    {
+      "epoch": 0.2852866897390328,
+      "grad_norm": 1.8154865503311157,
+      "learning_rate": 7.52461599054746e-05,
+      "loss": 0.2857963180541992,
+      "step": 3050
+    },
+    {
+      "epoch": 0.28762510522869705,
+      "grad_norm": 1.347398042678833,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.22897544860839844,
+      "step": 3075
+    },
+    {
+      "epoch": 0.28996352071836123,
+      "grad_norm": 1.910434603691101,
+      "learning_rate": 7.47538400945254e-05,
+      "loss": 0.3003374099731445,
+      "step": 3100
+    },
+    {
+      "epoch": 0.2923019362080254,
+      "grad_norm": 2.536224365234375,
+      "learning_rate": 7.45076801890508e-05,
+      "loss": 0.21426973342895508,
+      "step": 3125
+    },
+    {
+      "epoch": 0.29464035169768965,
+      "grad_norm": 1.4936145544052124,
+      "learning_rate": 7.426152028357622e-05,
+      "loss": 0.248642578125,
+      "step": 3150
+    },
+    {
+      "epoch": 0.29697876718735383,
+      "grad_norm": 1.5778441429138184,
+      "learning_rate": 7.401536037810162e-05,
+      "loss": 0.24121809005737305,
+      "step": 3175
+    },
+    {
+      "epoch": 0.29931718267701807,
+      "grad_norm": 2.0866878032684326,
+      "learning_rate": 7.376920047262702e-05,
+      "loss": 0.2682598304748535,
+      "step": 3200
+    },
+    {
+      "epoch": 0.29931718267701807,
+      "eval_pairs_with_negatives_loss": 0.27552473545074463,
+      "eval_pairs_with_negatives_runtime": 44.3024,
+      "eval_pairs_with_negatives_samples_per_second": 28.351,
+      "eval_pairs_with_negatives_steps_per_second": 3.544,
+      "step": 3200
+    },
+    {
+      "epoch": 0.29931718267701807,
+      "eval_positives_loss": 0.06003187596797943,
+      "eval_positives_runtime": 52.079,
+      "eval_positives_samples_per_second": 42.244,
+      "eval_positives_steps_per_second": 5.28,
+      "step": 3200
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 10691,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "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
+}

checkpoint-3200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f64c13625404e7e8b2e3825b7c2b388aa17cbed32c8e2be6731de0c81a3f24a0
+size 5457