Training in progress, step 12000

1_Pooling/config.json

@@ -1,7 +1,7 @@
 {
-    "word_embedding_dimension": 768,
-    "pooling_mode_cls_token": false,
-    "pooling_mode_mean_tokens": true,
+    "word_embedding_dimension": 512,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
     "pooling_mode_max_tokens": false,
     "pooling_mode_mean_sqrt_len_tokens": false,
     "pooling_mode_weightedmean_tokens": false,

Information-Retrieval_evaluation_val_results.csv

@@ -10,3 +10,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 -1,-1,0.827675,0.903,0.928425,0.827675,0.827675,0.30099999999999993,0.903,0.18568500000000004,0.928425,0.827675,0.8671804166666619,0.8711970039682481,0.8922532953454642,0.87334664003711
 -1,-1,0.83295,0.9071,0.9329,0.83295,0.83295,0.3023666666666666,0.9071,0.18658000000000005,0.9329,0.83295,0.872013749999996,0.8760916468253912,0.8970951855878305,0.8781372459990227
 -1,-1,0.83545,0.911175,0.9366,0.83545,0.83545,0.303725,0.911175,0.18732000000000001,0.9366,0.83545,0.8751591666666616,0.8790415476190412,0.8999318372974409,0.8810239994800558
+-1,-1,0.0,0.0,2.5e-05,0.0,0.0,0.0,0.0,5e-06,2.5e-05,0.0,5e-06,1.697420634920635e-05,4.0643645983386815e-05,5.219463554638405e-05

README.md

@@ -5,123 +5,51 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:713743
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
-base_model: google/embeddinggemma-300m
+base_model: prajjwal1/bert-small
 widget:
-- source_sentence: 'Abraham Lincoln: Why is the Gettysburg Address so memorable?'
+- source_sentence: How do I calculate IQ?
   sentences:
-  - 'Abraham Lincoln: Why is the Gettysburg Address so memorable?'
-  - What does the Gettysburg Address really mean?
-  - What is eatalo.com?
-- source_sentence: Has the influence of Ancient Carthage in science, math, and society
-    been underestimated?
+  - What is the easiest way to know my IQ?
+  - How do I calculate not IQ ?
+  - What are some creative and innovative business ideas with less investment in India?
+- source_sentence: How can I learn martial arts in my home?
   sentences:
-  - How does one earn money online without an investment from home?
-  - Has the influence of Ancient Carthage in science, math, and society been underestimated?
-  - Has the influence of the Ancient Etruscans in science and math been underestimated?
-- source_sentence: Is there any app that shares charging to others like share it how
-    we transfer files?
+  - How can I learn martial arts by myself?
+  - What are the advantages and disadvantages of investing in gold?
+  - Can people see that I have looked at their pictures on instagram if I am not following
+    them?
+- source_sentence: When Enterprise picks you up do you have to take them back?
   sentences:
-  - How do you think of Chinese claims that the present Private Arbitration is illegal,
-    its verdict violates the UNCLOS and is illegal?
-  - Is there any app that shares charging to others like share it how we transfer
-    files?
-  - Are there any platforms that provides end-to-end encryption for file transfer/
-    sharing?
-- source_sentence: Why AAP’s MLA Dinesh Mohaniya has been arrested?
+  - Are there any software Training institute in Tuticorin?
+  - When Enterprise picks you up do you have to take them back?
+  - When Enterprise picks you up do them have to take youback?
+- source_sentence: What are some non-capital goods?
   sentences:
-  - What are your views on the latest sex scandal by AAP MLA Sandeep Kumar?
-  - What is a dc current? What are some examples?
-  - Why AAP’s MLA Dinesh Mohaniya has been arrested?
-- source_sentence: What is the difference between economic growth and economic development?
+  - What are capital goods?
+  - How is the value of [math]\pi[/math] calculated?
+  - What are some non-capital goods?
+- source_sentence: What is the QuickBooks technical support phone number in New York?
   sentences:
-  - How cold can the Gobi Desert get, and how do its average temperatures compare
-    to the ones in the Simpson Desert?
-  - the difference between economic growth and economic development is What?
-  - What is the difference between economic growth and economic development?
+  - What caused the Great Depression?
+  - Can I apply for PR in Canada?
+  - Which is the best QuickBooks Hosting Support Number in New York?
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
-metrics:
-- cosine_accuracy@1
-- cosine_accuracy@3
-- cosine_accuracy@5
-- cosine_precision@1
-- cosine_precision@3
-- cosine_precision@5
-- cosine_recall@1
-- cosine_recall@3
-- cosine_recall@5
-- cosine_ndcg@10
-- cosine_mrr@1
-- cosine_mrr@5
-- cosine_mrr@10
-- cosine_map@100
-model-index:
-- name: SentenceTransformer based on google/embeddinggemma-300m
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: val
-      type: val
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.0
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.0
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 2.5e-05
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.0
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.0
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 5.0e-06
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.0
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.0
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 2.5e-05
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 4.0643645983386815e-05
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.0
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 5.0e-06
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 1.697420634920635e-05
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 5.219463554638405e-05
-      name: Cosine Map@100
 ---
 
-# SentenceTransformer based on google/embeddinggemma-300m
+# SentenceTransformer based on prajjwal1/bert-small
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m). 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.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small). It maps sentences & paragraphs to a 512-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:** [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) <!-- at revision 57c266a740f537b4dc058e1b0cda161fd15afa75 -->
+- **Base model:** [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small) <!-- at revision 0ec5f86f27c1a77d704439db5e01c307ea11b9d4 -->
 - **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 768 dimensions
+- **Output Dimensionality:** 512 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
@@ -137,11 +65,8 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [g
 
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
-  (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})
-  (2): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
-  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
-  (4): Normalize()
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
+  (1): Pooling({'word_embedding_dimension': 512, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
 )
 ```
 
@@ -160,25 +85,23 @@ Then you can load this model and run inference.
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("redis/model-b-structured")
+model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
-queries = [
-    "What is the difference between economic growth and economic development?",
+sentences = [
+    'What is the QuickBooks technical support phone number in New York?',
+    'Which is the best QuickBooks Hosting Support Number in New York?',
+    'Can I apply for PR in Canada?',
 ]
-documents = [
-    'What is the difference between economic growth and economic development?',
-    'the difference between economic growth and economic development is What?',
-    'How cold can the Gobi Desert get, and how do its average temperatures compare to the ones in the Simpson Desert?',
-]
-query_embeddings = model.encode_query(queries)
-document_embeddings = model.encode_document(documents)
-print(query_embeddings.shape, document_embeddings.shape)
-# [1, 768] [3, 768]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 512]
 
 # Get the similarity scores for the embeddings
-similarities = model.similarity(query_embeddings, document_embeddings)
+similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[nan, nan, nan]])
+# tensor([[1.0000, 0.8563, 0.0594],
+#         [0.8563, 1.0000, 0.1245],
+#         [0.0594, 0.1245, 1.0000]])
 ```
 
 <!--
@@ -205,32 +128,6 @@ You can finetune this model on your own dataset.
 *List how the model may foreseeably be misused and address what users ought not to do with the model.*
 -->
 
-## Evaluation
-
-### Metrics
-
-#### Information Retrieval
-
-* Dataset: `val`
-* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
-
-| Metric             | Value   |
-|:-------------------|:--------|
-| cosine_accuracy@1  | 0.0     |
-| cosine_accuracy@3  | 0.0     |
-| cosine_accuracy@5  | 0.0     |
-| cosine_precision@1 | 0.0     |
-| cosine_precision@3 | 0.0     |
-| cosine_precision@5 | 0.0     |
-| cosine_recall@1    | 0.0     |
-| cosine_recall@3    | 0.0     |
-| cosine_recall@5    | 0.0     |
-| **cosine_ndcg@10** | **0.0** |
-| cosine_mrr@1       | 0.0     |
-| cosine_mrr@5       | 0.0     |
-| cosine_mrr@10      | 0.0     |
-| cosine_map@100     | 0.0001  |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -249,49 +146,23 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 713,743 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: 6 tokens</li><li>mean: 15.9 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.86 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.63 tokens</li><li>max: 61 tokens</li></ul> |
-* Samples:
-  | anchor                                                                         | positive                                                                              | negative                                                                                                          |
-  |:-------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|
-  | <code>Which one is better Linux OS? Ubuntu or Mint?</code>                     | <code>Why do you use Linux Mint?</code>                                               | <code>Which one is not better Linux OS ? Ubuntu or Mint ?</code>                                                  |
-  | <code>What is flow?</code>                                                     | <code>What is flow?</code>                                                            | <code>What are flow lines?</code>                                                                                 |
-  | <code>How is Trump planning to get Mexico to pay for his supposed wall?</code> | <code>How is it possible for Donald Trump to force Mexico to pay for the wall?</code> | <code>Why do we connect the positive terminal before the negative terminal to ground in a vehicle battery?</code> |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
-  ```json
-  {
-      "scale": 7.0,
-      "similarity_fct": "cos_sim",
-      "gather_across_devices": false
-  }
-  ```
-
-### Evaluation Dataset
-
-#### Unnamed Dataset
-
-* Size: 40,000 evaluation samples
-* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Size: 100,000 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
+  |         | sentence_0                                                                        | sentence_1                                                                        | sentence_2                                                                        |
   |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.38 tokens</li><li>max: 75 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.39 tokens</li><li>max: 75 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.58 tokens</li><li>max: 68 tokens</li></ul> |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.79 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.68 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 16.37 tokens</li><li>max: 67 tokens</li></ul> |
 * Samples:
-  | anchor                                                                                                                                                       | positive                                                                                                                                                     | negative                                                                                                                                                            |
-  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Why are all my questions on Quora marked needing improvement?</code>                                                                                   | <code>Why are all my questions immediately being marked as needing improvement?</code>                                                                       | <code>For a post-graduate student in IIT, is it allowed to take an external scholarship as a top-up to his/her MHRD assistantship?</code>                           |
-  | <code>Can blue butter fly needle with vaccum tube be reused? Is it HIV risk? . Heard the needle is too small to be reused . Had blood draw at clinic?</code> | <code>Can blue butter fly needle with vaccum tube be reused? Is it HIV risk? . Heard the needle is too small to be reused . Had blood draw at clinic?</code> | <code>Can blue butter fly needle with vaccum tube be reused not ? Is it HIV risk ? . Heard the needle is too small to be reused . Had blood draw at clinic ?</code> |
-  | <code>Why do people still believe the world is flat?</code>                                                                                                  | <code>Why are there still people who believe the world is flat?</code>                                                                                       | <code>I'm not able to buy Udemy course .it is not accepting mine and my friends debit card.my card can be used for Flipkart .how to purchase now?</code>            |
+  | sentence_0                                                       | sentence_1                                                       | sentence_2                                                                        |
+  |:-----------------------------------------------------------------|:-----------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | <code>Is masturbating bad for boys?</code>                       | <code>Is masturbating bad for boys?</code>                       | <code>How harmful or unhealthy is masturbation?</code>                            |
+  | <code>Does a train engine move in reverse?</code>                | <code>Does a train engine move in reverse?</code>                | <code>Time moves forward, not in reverse. Doesn't that make time a vector?</code> |
+  | <code>What is the most badass thing anyone has ever done?</code> | <code>What is the most badass thing anyone has ever done?</code> | <code>anyone is the most badass thing Whathas ever done?</code>                   |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
-      "scale": 7.0,
+      "scale": 20.0,
       "similarity_fct": "cos_sim",
       "gather_across_devices": false
   }
@@ -300,30 +171,17 @@ You can finetune this model on your own dataset.
 ### Training Hyperparameters
 #### Non-Default Hyperparameters
 
-- `eval_strategy`: steps
 - `per_device_train_batch_size`: 64
 - `per_device_eval_batch_size`: 64
-- `learning_rate`: 2e-05
-- `weight_decay`: 0.0001
-- `max_steps`: 5000
-- `warmup_ratio`: 0.1
 - `fp16`: True
-- `dataloader_drop_last`: True
-- `dataloader_num_workers`: 1
-- `dataloader_prefetch_factor`: 1
-- `load_best_model_at_end`: True
-- `optim`: adamw_torch
-- `ddp_find_unused_parameters`: False
-- `push_to_hub`: True
-- `hub_model_id`: redis/model-b-structured
-- `eval_on_start`: True
+- `multi_dataset_batch_sampler`: round_robin
 
 #### All Hyperparameters
 <details><summary>Click to expand</summary>
 
 - `overwrite_output_dir`: False
 - `do_predict`: False
-- `eval_strategy`: steps
+- `eval_strategy`: no
 - `prediction_loss_only`: True
 - `per_device_train_batch_size`: 64
 - `per_device_eval_batch_size`: 64
@@ -332,17 +190,17 @@ You can finetune this model on your own dataset.
 - `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
-- `learning_rate`: 2e-05
-- `weight_decay`: 0.0001
+- `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`: 3.0
-- `max_steps`: 5000
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
-- `warmup_ratio`: 0.1
+- `warmup_ratio`: 0.0
 - `warmup_steps`: 0
 - `log_level`: passive
 - `log_level_replica`: warning
@@ -370,14 +228,14 @@ You can finetune this model on your own dataset.
 - `tpu_num_cores`: None
 - `tpu_metrics_debug`: False
 - `debug`: []
-- `dataloader_drop_last`: True
-- `dataloader_num_workers`: 1
-- `dataloader_prefetch_factor`: 1
+- `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`: True
+- `load_best_model_at_end`: False
 - `ignore_data_skip`: False
 - `fsdp`: []
 - `fsdp_min_num_params`: 0
@@ -387,23 +245,23 @@ You can finetune this model on your own dataset.
 - `parallelism_config`: None
 - `deepspeed`: None
 - `label_smoothing_factor`: 0.0
-- `optim`: adamw_torch
+- `optim`: adamw_torch_fused
 - `optim_args`: None
 - `adafactor`: False
 - `group_by_length`: False
 - `length_column_name`: length
 - `project`: huggingface
 - `trackio_space_id`: trackio
-- `ddp_find_unused_parameters`: False
+- `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
+- `push_to_hub`: False
 - `resume_from_checkpoint`: None
-- `hub_model_id`: redis/model-b-structured
+- `hub_model_id`: None
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -430,43 +288,31 @@ You can finetune this model on your own dataset.
 - `neftune_noise_alpha`: None
 - `optim_target_modules`: None
 - `batch_eval_metrics`: False
-- `eval_on_start`: True
+- `eval_on_start`: False
 - `use_liger_kernel`: False
 - `liger_kernel_config`: None
 - `eval_use_gather_object`: False
 - `average_tokens_across_devices`: True
 - `prompts`: None
 - `batch_sampler`: batch_sampler
-- `multi_dataset_batch_sampler`: proportional
+- `multi_dataset_batch_sampler`: round_robin
 - `router_mapping`: {}
 - `learning_rate_mapping`: {}
 
 </details>
 
 ### Training Logs
-| Epoch  | Step | Training Loss | Validation Loss | val_cosine_ndcg@10 |
-|:------:|:----:|:-------------:|:---------------:|:------------------:|
-| 0      | 0    | -             | 1.1196          | 0.8084             |
-| 0.0224 | 250  | 0.3432        | 0.2247          | 0.8873             |
-| 0.0448 | 500  | 0.2279        | 0.2306          | 0.8821             |
-| 0.0673 | 750  | 0.2253        | 0.2339          | 0.8802             |
-| 0.0897 | 1000 | 0.2231        | 0.2147          | 0.8882             |
-| 0.1121 | 1250 | 0.2091        | 0.2115          | 0.8881             |
-| 0.1345 | 1500 | 0.2145        | 0.2059          | 0.8886             |
-| 0.1569 | 1750 | 0.2049        | 0.2025          | 0.8910             |
-| 0.1793 | 2000 | 0.2066        | nan             | 0.0346             |
-| 0.2018 | 2250 | 0.2012        | 0.2087          | 0.8929             |
-| 0.2242 | 2500 | 0.2175        | 0.2187          | 0.8960             |
-| 0.2466 | 2750 | 0.2311        | nan             | 0.2274             |
-| 0.2690 | 3000 | 0.2477        | nan             | 0.1686             |
-| 0.2914 | 3250 | 0.2484        | nan             | 0.1686             |
-| 0.3138 | 3500 | 0.253         | nan             | 0.1686             |
-| 0.3363 | 3750 | 0.249         | nan             | 0.1686             |
-| 0.3587 | 4000 | 0.2524        | nan             | 0.1686             |
-| 0.3811 | 4250 | 0.2502        | nan             | 0.0000             |
-| 0.4035 | 4500 | 0.0           | nan             | 0.0000             |
-| 0.4259 | 4750 | 0.0           | nan             | 0.0000             |
-| 0.4484 | 5000 | 0.0           | nan             | 0.0000             |
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.3199 | 500  | 0.4294        |
+| 0.6398 | 1000 | 0.1268        |
+| 0.9597 | 1500 | 0.1           |
+| 1.2796 | 2000 | 0.0792        |
+| 1.5995 | 2500 | 0.0706        |
+| 1.9194 | 3000 | 0.0687        |
+| 2.2393 | 3500 | 0.0584        |
+| 2.5592 | 4000 | 0.057         |
+| 2.8791 | 4500 | 0.0581        |
 
 
 ### Framework Versions

config.json

@@ -1,60 +1,25 @@
 {
-  "_sliding_window_pattern": 6,
   "architectures": [
-    "Gemma3TextModel"
+    "BertModel"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "attn_logit_softcapping": null,
-  "bos_token_id": 2,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
   "dtype": "float32",
-  "eos_token_id": 1,
-  "final_logit_softcapping": null,
-  "head_dim": 256,
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 768,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 1152,
-  "layer_types": [
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "full_attention"
-  ],
-  "max_position_embeddings": 2048,
-  "model_type": "gemma3_text",
-  "num_attention_heads": 3,
-  "num_hidden_layers": 24,
-  "num_key_value_heads": 1,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
-  "query_pre_attn_scalar": 256,
-  "rms_norm_eps": 1e-06,
-  "rope_local_base_freq": 10000.0,
-  "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": 257,
+  "position_embedding_type": "absolute",
   "transformers_version": "4.57.3",
-  "use_bidirectional_attention": true,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 262144
+  "vocab_size": 30522
 }

config_sentence_transformers.json

@@ -6,20 +6,8 @@
     "pytorch": "2.9.1+cu128"
   },
   "prompts": {
-    "query": "task: search result | query: ",
-    "document": "title: none | text: ",
-    "BitextMining": "task: search result | query: ",
-    "Clustering": "task: clustering | query: ",
-    "Classification": "task: classification | query: ",
-    "InstructionRetrieval": "task: code retrieval | query: ",
-    "MultilabelClassification": "task: classification | query: ",
-    "PairClassification": "task: sentence similarity | query: ",
-    "Reranking": "task: search result | query: ",
-    "Retrieval": "task: search result | query: ",
-    "Retrieval-query": "task: search result | query: ",
-    "Retrieval-document": "title: none | text: ",
-    "STS": "task: sentence similarity | query: ",
-    "Summarization": "task: summarization | query: "
+    "query": "",
+    "document": ""
   },
   "default_prompt_name": null,
   "similarity_fn_name": "cosine"

eval/Information-Retrieval_evaluation_val_results.csv

@@ -679,3 +679,52 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 0.4035150645624103,4500,0.0,0.0,2.5e-05,0.0,0.0,0.0,0.0,5e-06,2.5e-05,0.0,5e-06,1.697420634920635e-05,4.0643645983386815e-05,5.219463554638405e-05
 0.4259325681492109,4750,0.0,0.0,2.5e-05,0.0,0.0,0.0,0.0,5e-06,2.5e-05,0.0,5e-06,1.697420634920635e-05,4.0643645983386815e-05,5.219463554638405e-05
 0.4483500717360115,5000,0.0,0.0,2.5e-05,0.0,0.0,0.0,0.0,5e-06,2.5e-05,0.0,5e-06,1.697420634920635e-05,4.0643645983386815e-05,5.219463554638405e-05
+0,0,0.751925,0.887,0.917,0.751925,0.751925,0.29566666666666663,0.887,0.18340000000000004,0.917,0.751925,0.821192916666658,0.8254150297618993,0.8556052902179354,0.8278830901193039
+0.0896700143472023,250,0.80465,0.896325,0.924375,0.80465,0.80465,0.298775,0.896325,0.184875,0.924375,0.80465,0.852659999999995,0.8565211904761864,0.8800328213130088,0.8588291102423605
+0.1793400286944046,500,0.820025,0.89875,0.9253,0.820025,0.820025,0.2995833333333333,0.89875,0.18506,0.9253,0.820025,0.8615108333333292,0.8654402579365047,0.8870095227636031,0.8676799907230608
+0.26901004304160686,750,0.821125,0.899775,0.925575,0.821125,0.821125,0.2999249999999999,0.899775,0.185115,0.925575,0.821125,0.8624174999999963,0.86642163690476,0.8879143529201894,0.8686602623965786
+0.3586800573888092,1000,0.822575,0.89985,0.9263,0.822575,0.822575,0.29994999999999994,0.89985,0.18526,0.9263,0.822575,0.8632583333333298,0.8672305357142832,0.8886276582361335,0.8694671920858201
+0.4483500717360115,1250,0.822725,0.9006,0.926475,0.822725,0.822725,0.3001999999999999,0.9006,0.18529500000000004,0.926475,0.822725,0.8636683333333298,0.8676871031746004,0.8890995637213502,0.869907342550433
+0.5380200860832137,1500,0.823925,0.900825,0.926275,0.823925,0.823925,0.300275,0.900825,0.18525500000000003,0.926275,0.823925,0.8643383333333308,0.8683831448412673,0.8896475955998834,0.8706135646799439
+0.6276901004304161,1750,0.82525,0.902,0.927425,0.82525,0.82525,0.30066666666666664,0.902,0.185485,0.927425,0.82525,0.8655337499999965,0.8696110317460287,0.8909058933560547,0.8717896326318644
+0.7173601147776184,2000,0.8246,0.902325,0.92685,0.8246,0.8246,0.30077499999999996,0.902325,0.18537000000000003,0.92685,0.8246,0.8651599999999963,0.8692929960317426,0.8906287939435462,0.8714942451461398
+0.8070301291248206,2250,0.82515,0.902525,0.927075,0.82515,0.82515,0.3008416666666666,0.902525,0.185415,0.927075,0.82515,0.8654974999999964,0.8697102480158696,0.8911223828711662,0.8718783764760456
+0.896700143472023,2500,0.824625,0.902775,0.927675,0.824625,0.824625,0.3009249999999999,0.902775,0.185535,0.927675,0.824625,0.8654166666666628,0.8695106051587264,0.8909426642160327,0.8717054008785079
+0.9863701578192252,2750,0.825375,0.9027,0.9276,0.825375,0.825375,0.3009,0.9027,0.18552000000000002,0.9276,0.825375,0.8658224999999957,0.8699597023809489,0.891320667068452,0.8721370407336589
+1.0760401721664274,3000,0.826025,0.9025,0.927675,0.826025,0.826025,0.30083333333333323,0.9025,0.18553500000000003,0.927675,0.826025,0.8662079166666632,0.8702979464285674,0.8915119967833314,0.872510571142309
+1.16571018651363,3250,0.825725,0.90265,0.9274,0.825725,0.825725,0.3008833333333333,0.90265,0.18548,0.9274,0.825725,0.8659145833333294,0.8700107539682509,0.891222478634554,0.8722470996330639
+1.2553802008608321,3500,0.82525,0.90305,0.928175,0.82525,0.82525,0.3010166666666666,0.90305,0.18563500000000002,0.928175,0.82525,0.8659366666666619,0.8700273908730114,0.8914502713155418,0.8722180663314848
+1.3450502152080344,3750,0.826225,0.902825,0.928275,0.826225,0.826225,0.3009416666666666,0.902825,0.18565500000000001,0.928275,0.826225,0.8664804166666623,0.8706096130952335,0.8919543885192465,0.8727891622700147
+1.4347202295552366,4000,0.8264,0.902725,0.927975,0.8264,0.8264,0.3009083333333333,0.902725,0.18559500000000004,0.927975,0.8264,0.8664483333333288,0.8706402281745992,0.891983843733548,0.8728380784984238
+1.524390243902439,4250,0.8266,0.9036,0.929175,0.8266,0.8266,0.30119999999999997,0.9036,0.18583500000000003,0.929175,0.8266,0.8670083333333283,0.871095853174598,0.8924808083686762,0.8732574599816396
+1.6140602582496413,4500,0.826675,0.90375,0.928825,0.826675,0.826675,0.30124999999999996,0.90375,0.185765,0.928825,0.826675,0.8669558333333298,0.8710873214285674,0.892471870823939,0.8732517911596164
+1.7037302725968435,4750,0.826025,0.90415,0.9284,0.826025,0.826025,0.3013833333333333,0.90415,0.18567999999999998,0.9284,0.826025,0.866584999999996,0.8707971230158688,0.8922687828652679,0.8729724881673945
+1.793400286944046,5000,0.8265,0.9048,0.929275,0.8265,0.8265,0.3016,0.9048,0.18585500000000002,0.929275,0.8265,0.8670866666666623,0.8711956349206301,0.8926408625431878,0.8733700026530962
+1.8830703012912482,5250,0.8266,0.903875,0.92895,0.8266,0.8266,0.3012916666666666,0.903875,0.18579000000000004,0.92895,0.8266,0.8669020833333292,0.8710456150793603,0.8924858518633457,0.8732353782999096
+1.9727403156384504,5500,0.8271,0.904475,0.928975,0.8271,0.8271,0.3014916666666666,0.904475,0.18579500000000002,0.928975,0.8271,0.867337916666662,0.8714944543650747,0.892834931269629,0.8736889896748274
+2.062410329985653,5750,0.827175,0.90435,0.92955,0.827175,0.827175,0.30144999999999994,0.90435,0.18591000000000005,0.92955,0.827175,0.8675820833333281,0.8716831349206297,0.8930074386378707,0.8738795306452989
+2.152080344332855,6000,0.8271,0.904575,0.929575,0.8271,0.8271,0.30152499999999993,0.904575,0.18591500000000005,0.929575,0.8271,0.8676179166666625,0.8717332341269798,0.8931109587880816,0.8739079151666905
+2.2417503586800573,6250,0.827225,0.904475,0.92955,0.827225,0.827225,0.3014916666666666,0.904475,0.18591000000000005,0.92955,0.827225,0.8675649999999959,0.8717064186507892,0.8931235559174038,0.873877398407616
+2.33142037302726,6500,0.8273,0.905225,0.929775,0.8273,0.8273,0.30174166666666663,0.905225,0.185955,0.929775,0.8273,0.8677670833333289,0.8718472718253913,0.8932079921309838,0.8740305777000185
+2.421090387374462,6750,0.827425,0.905075,0.9297,0.827425,0.827425,0.3016916666666666,0.905075,0.18594000000000002,0.9297,0.827425,0.8678008333333294,0.8718941964285661,0.8932542348032559,0.8740757678933109
+2.5107604017216643,7000,0.8269,0.90525,0.9296,0.8269,0.8269,0.3017499999999999,0.90525,0.18592,0.9296,0.8269,0.867580833333329,0.8717025595238047,0.8931301877553839,0.8738871433454486
+2.6004304160688667,7250,0.827225,0.904975,0.929675,0.827225,0.827225,0.3016583333333333,0.904975,0.185935,0.929675,0.827225,0.8677058333333296,0.8717949007936467,0.8931569064335827,0.8739934443060552
+2.6901004304160687,7500,0.82755,0.9051,0.93,0.82755,0.82755,0.3017,0.9051,0.18600000000000003,0.93,0.82755,0.8679774999999965,0.8720509126984096,0.8933746803361129,0.8742608501545442
+2.779770444763271,7750,0.827825,0.9054,0.929975,0.827825,0.827825,0.30179999999999996,0.9054,0.18599500000000002,0.929975,0.827825,0.8681562499999959,0.8722401388888844,0.8935616290842326,0.8744330985543757
+2.869440459110473,8000,0.828275,0.905375,0.92995,0.828275,0.828275,0.3017916666666666,0.905375,0.18599000000000004,0.92995,0.828275,0.8683970833333294,0.8725187599206307,0.8937878693376755,0.8747118448510659
+2.9591104734576756,8250,0.8276,0.905175,0.9303,0.8276,0.8276,0.301725,0.905175,0.18606000000000003,0.9303,0.8276,0.8680820833333295,0.8721759920634872,0.8935945905099506,0.8743330189280194
+3.048780487804878,8500,0.828325,0.90515,0.930475,0.828325,0.828325,0.30171666666666663,0.90515,0.18609500000000004,0.930475,0.828325,0.8684974999999953,0.8725453273809473,0.8938128351914529,0.8747440172400296
+3.1384505021520805,8750,0.82795,0.9052,0.9302,0.82795,0.82795,0.30173333333333324,0.9052,0.18604,0.9302,0.82795,0.8682741666666624,0.8724082142857096,0.893791889973397,0.8745838158482304
+3.2281205164992826,9000,0.8283,0.905375,0.930825,0.8283,0.8283,0.3017916666666666,0.905375,0.186165,0.930825,0.8283,0.8685966666666627,0.8726080357142809,0.8938966727680374,0.8747960624601541
+3.317790530846485,9250,0.82835,0.905475,0.930475,0.82835,0.82835,0.30182499999999995,0.905475,0.18609500000000004,0.930475,0.82835,0.8685666666666628,0.8726975595238055,0.8940499889166927,0.8748546291176182
+3.407460545193687,9500,0.8283,0.9056,0.930575,0.8283,0.8283,0.30186666666666667,0.9056,0.18611500000000003,0.930575,0.8283,0.8685999999999962,0.8727170337301539,0.8940961677203971,0.8748585659281131
+3.4971305595408895,9750,0.82805,0.90565,0.930775,0.82805,0.82805,0.3018833333333333,0.90565,0.18615500000000001,0.930775,0.82805,0.8685420833333294,0.8726378075396779,0.8940545972391326,0.8747808576034762
+3.586800573888092,10000,0.828125,0.9052,0.9304,0.828125,0.828125,0.30173333333333324,0.9052,0.18608000000000002,0.9304,0.828125,0.8683999999999958,0.872550267857138,0.8939721843580628,0.8746969389189057
+3.6764705882352944,10250,0.828325,0.9055,0.930675,0.828325,0.828325,0.3018333333333333,0.9055,0.18613500000000002,0.930675,0.828325,0.8685495833333294,0.8726263194444398,0.893987547028647,0.874796265410846
+3.7661406025824964,10500,0.828175,0.905125,0.930675,0.828175,0.828175,0.30170833333333325,0.905125,0.18613500000000002,0.930675,0.828175,0.8684674999999954,0.8725678670634869,0.8939775062267301,0.8747340075836931
+3.855810616929699,10750,0.82815,0.905175,0.93075,0.82815,0.82815,0.3017249999999999,0.905175,0.18615000000000004,0.93075,0.82815,0.8684716666666625,0.8725727777777725,0.8940086829611978,0.8747196153860665
+3.945480631276901,11000,0.828675,0.9054,0.93065,0.828675,0.828675,0.3018,0.9054,0.18613000000000002,0.93065,0.828675,0.8687779166666618,0.8729081150793602,0.8942634666022241,0.8750627536951296
+4.035150645624103,11250,0.8284,0.90535,0.9306,0.8284,0.8284,0.3017833333333333,0.90535,0.18612000000000004,0.9306,0.8284,0.8686220833333292,0.8727696130952336,0.8941853658108053,0.874910002213559
+4.124820659971306,11500,0.828425,0.905575,0.9308,0.828425,0.828425,0.3018583333333333,0.905575,0.18616000000000002,0.9308,0.828425,0.8687266666666623,0.872845128968249,0.8942524642669559,0.8749859334121904
+4.214490674318508,11750,0.828225,0.905425,0.930775,0.828225,0.828225,0.30180833333333323,0.905425,0.18615500000000001,0.930775,0.828225,0.8685866666666623,0.8726996329365029,0.8941203987290073,0.8748458978394003
+4.30416068866571,12000,0.828275,0.90535,0.930675,0.828275,0.828275,0.3017833333333333,0.90535,0.186135,0.930675,0.828275,0.8685570833333288,0.8726829662698361,0.8940991092644636,0.8748315667834753

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.83545,
-  "val_cosine_accuracy@3": 0.911175,
-  "val_cosine_accuracy@5": 0.9366,
-  "val_cosine_precision@1": 0.83545,
-  "val_cosine_precision@3": 0.303725,
-  "val_cosine_precision@5": 0.18732000000000001,
-  "val_cosine_recall@1": 0.83545,
-  "val_cosine_recall@3": 0.911175,
-  "val_cosine_recall@5": 0.9366,
-  "val_cosine_ndcg@10": 0.8999318372974409,
-  "val_cosine_mrr@1": 0.83545,
-  "val_cosine_mrr@5": 0.8751591666666616,
-  "val_cosine_mrr@10": 0.8790415476190412,
-  "val_cosine_map@100": 0.8810239994800558
+  "val_cosine_accuracy@1": 0.0,
+  "val_cosine_accuracy@3": 0.0,
+  "val_cosine_accuracy@5": 2.5e-05,
+  "val_cosine_precision@1": 0.0,
+  "val_cosine_precision@3": 0.0,
+  "val_cosine_precision@5": 5e-06,
+  "val_cosine_recall@1": 0.0,
+  "val_cosine_recall@3": 0.0,
+  "val_cosine_recall@5": 2.5e-05,
+  "val_cosine_ndcg@10": 4.0643645983386815e-05,
+  "val_cosine_mrr@1": 0.0,
+  "val_cosine_mrr@5": 5e-06,
+  "val_cosine_mrr@10": 1.697420634920635e-05,
+  "val_cosine_map@100": 5.219463554638405e-05
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:545b247747446f3974b25dce1c7156ba3f4d45cf47a42bc853d38de5dc798cfe
-size 1211486072
+oid sha256:c16a8a0c066ce6670147940dcb6ed642b624b948c9a93d349a3f2c82687151c3
+size 90864192

modules.json

@@ -10,23 +10,5 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
-  },
-  {
-    "idx": 2,
-    "name": "2",
-    "path": "2_Dense",
-    "type": "sentence_transformers.models.Dense"
-  },
-  {
-    "idx": 3,
-    "name": "3",
-    "path": "3_Dense",
-    "type": "sentence_transformers.models.Dense"
-  },
-  {
-    "idx": 4,
-    "name": "4",
-    "path": "4_Normalize",
-    "type": "sentence_transformers.models.Normalize"
   }
 ]

special_tokens_map.json

@@ -1,30 +1,34 @@
 {
-  "boi_token": "<start_of_image>",
-  "bos_token": {
-    "content": "<bos>",
+  "cls_token": {
+    "content": "[CLS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "eoi_token": "<end_of_image>",
-  "eos_token": {
-    "content": "<eos>",
+  "mask_token": {
+    "content": "[MASK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "image_token": "<image_soft_token>",
   "pad_token": {
-    "content": "<pad>",
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7ae06c2d5423018713138be1af08ead828be6d5aec3dcaf4004830d73339843
-size 33385261
+oid sha256:2fc687b11de0bc1b3d8348f92e3b49ef1089a621506c7661fbf3248fcd54947e
+size 711649

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0550728e68dcb4297a5ed369ce43e645f35ae6cb79deed45333999adba8e4c4e
+oid sha256:9b00bfe28f1f5c19078fccb765b6539914861c7d57b38fb16b169199ec0cec5c
 size 6161