Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-126/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

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

README.md

@@ -0,0 +1,64 @@
+
+---
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- autotrain
+base_model: BAAI/bge-m3
+widget:
+- source_sentence: 'search_query: i love autotrain'
+  sentences:
+  - 'search_query: huggingface auto train'
+  - 'search_query: hugging face auto train'
+  - 'search_query: i love autotrain'
+pipeline_tag: sentence-similarity
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Sentence Transformers
+
+## Validation Metrics
+loss: 0.8379377126693726
+
+cosine_accuracy: 0.9651162790697675
+
+runtime: 77.5038
+
+samples_per_second: 1.11
+
+steps_per_second: 0.142
+
+: 2.9411764705882355
+
+## 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 Hugging Face Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'search_query: autotrain',
+    'search_query: auto train',
+    'search_query: i love autotrain',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+```

checkpoint-126/1_Pooling/config.json

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

checkpoint-126/README.md

@@ -0,0 +1,437 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:340
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-m3
+widget:
+- source_sentence: What parameters are needed to configure a gauge?
+  sentences:
+  - Anticipate failures, assess and control risky situations, apply fail-safe actions,
+    optimize maintenance actions, and capitalize knowledge and experience.
+  - A public sequence is visible to all users on the platform, while a private sequence
+    is only visible to its creator.
+  - Title, variable, units, type of gauge (standard, donut, horizontal, vertical),
+    color ranges, optional transparency.
+- source_sentence: What does the Analysis tab in Kasem include?
+  sentences:
+  - '**Degradations** and **deviations** can be linked to a specific equipment and/or
+    a set of equipment, allowing centralized management of issues related to the equipment.'
+  - By clicking on the Report button, users are redirected to the Saved reports tab
+    where they can view all saved reports.
+  - Time series visualization, real-time dashboards, and equipment or fleet knowledge
+    visualization through maintenance-oriented graphs.
+- source_sentence: What is a timer used for in Kasem?
+  sentences:
+  - A plot displays the evolution of a variable over time, allowing the user to observe
+    trends and anomalies in the data visually.
+  - Users can configure the value range, colors of gauges and LEDs, as well as the
+    time period for graphs and plots.
+  - A timer sums the time during which a particular event is occurring, each time
+    it occurs.
+- source_sentence: What is the difference between analog and boolean variables?
+  sentences:
+  - 'Two types of visualisation are available: Equipment knowledge visualisation and
+    Fleet knowledge visualisation.'
+  - Analog variables represent continuous values, while boolean variables only take
+    true or false values.
+  - 'The types include: Stats, Heatmap, Profiles, Distributions, and Alarms.'
+- source_sentence: What is the role of the equipment/fleet selector in the dashboard
+    window?
+  sentences:
+  - To display a 3D graph, you need to set 'View3D' to 'true' in the graph's parameters.
+  - Click 'New fleet', enter the name, select agents, and click 'Save'.
+  - The selector allows you to choose the equipment or fleet for which the dashboards
+    are configured, in order to display specific data.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+model-index:
+- name: SentenceTransformer based on BAAI/bge-m3
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9651162790697675
+      name: Cosine Accuracy
+---
+
+# SentenceTransformer based on BAAI/bge-m3
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision 5617a9f61b028005a4858fdac845db406aefb181 -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'What is the role of the equipment/fleet selector in the dashboard window?',
+    'The selector allows you to choose the equipment or fleet for which the dashboards are configured, in order to display specific data.',
+    "Click 'New fleet', enter the name, select agents, and click 'Save'.",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Triplet
+
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| **cosine_accuracy** | **0.9651** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 340 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 340 samples:
+  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 14.25 tokens</li><li>max: 34 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 28.48 tokens</li><li>max: 84 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 29.52 tokens</li><li>max: 84 tokens</li></ul> |
+* Samples:
+  | anchor                                                                      | positive                                                                                                                                                                               | negative                                                                                                       |
+  |:----------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------|
+  | <code>What does the 'L' character do in a Cron expression?</code>           | <code>The 'L' character stands for 'last'. For example, 'L' in the day-of-month field means 'the last day of the month'.</code>                                                        | <code>They allow expanding or collapsing levels of causes to explore the chains leading to root causes.</code> |
+  | <code>How do you link a variable to a characteristic for a timeline?</code> | <code>In Knowledge Administration under Equipment/Degradations, select the equipment, then in the Characteristics tab, add or modify a characteristic to link it to a variable.</code> | <code>They allow expanding or collapsing levels of causes to explore the chains leading to root causes.</code> |
+  | <code>Which modules are detailed in the Basics documentation?</code>        | <code>Event, Equipment, Analysis, Task, Report, Documentation, and a glossary of specific terms.</code>                                                                                | <code>When a new equipment is installed, a new KPI is defined, or to manage equipment more efficiently.</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 86 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 86 samples:
+  |         | anchor                                                                            | positive                                                                          | negative                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                           |
+  | details | <ul><li>min: 8 tokens</li><li>mean: 15.12 tokens</li><li>max: 34 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 27.36 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 26.0 tokens</li><li>max: 53 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                 | positive                                                                                                                                                               | negative                                                                                                                                 |
+  |:---------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>What are the four main modules covered by the advanced documentation?</code>     | <code>Data processing, knowledge analysis, knowledge administration, and system administration.</code>                                                                 | <code>It is used to discretize data and condition the display of curves. Each curve represents a variable within a Mode interval.</code> |
+  | <code>What is the role of the equipment/fleet selector in the dashboard window?</code> | <code>The selector allows you to choose the equipment or fleet for which the dashboards are configured, in order to display specific data.</code>                      | <code>Click 'New fleet', enter the name, select agents, and click 'Save'.</code>                                                         |
+  | <code>What are the filters in the `General` tab used for?</code>                       | <code>The filters, toggled using four `buttons`, allow displaying equipment-related news based on their type: `intervention`, `document`, `report`, or `event`.</code> | <code>They indicate binary states such as equipment running, stopped, or in protection mode.</code>                                      |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 4
+- `gradient_accumulation_steps`: 2
+- `learning_rate`: 3e-05
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `optim`: sgd
+- `ddp_find_unused_parameters`: False
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 4
+- `per_device_eval_batch_size`: 8
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 3e-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
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: sgd
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: False
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | cosine_accuracy |
+|:------:|:----:|:-------------:|:---------------:|:---------------:|
+| 0.4    | 17   | 0.5842        | -               | -               |
+| 0.8    | 34   | 0.4413        | -               | -               |
+| 1.0    | 43   | -             | 0.8394          | 0.9651          |
+| 1.1882 | 51   | 0.4844        | -               | -               |
+| 1.5882 | 68   | 0.4827        | -               | -               |
+| 1.9882 | 85   | 0.5319        | -               | -               |
+| 2.0    | 86   | -             | 0.8383          | 0.9651          |
+| 2.3765 | 102  | 0.5825        | -               | -               |
+| 2.7765 | 119  | 0.5355        | -               | -               |
+| 2.9412 | 126  | -             | 0.8379          | 0.9651          |
+
+
+### Framework Versions
+- Python: 3.10.16
+- Sentence Transformers: 3.3.1
+- Transformers: 4.48.0
+- PyTorch: 2.4.0
+- Accelerate: 1.2.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

checkpoint-126/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "BAAI/bge-m3",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-126/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.48.0",
+    "pytorch": "2.4.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-126/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1246e02d548f39bc37d7b52bcb5aee097683123d01a5c6796443a8f365a054f5
+size 2271064456

checkpoint-126/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

checkpoint-126/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20e93ac6a02d8d161cb48761bf43258dec3c498061124dc59a7acf1510f061ae
+size 2088

checkpoint-126/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a3ac39414ad4eb7e3c0da2057ee1123b08074c5fef973cc95d1f3460c1004a
+size 13990

checkpoint-126/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d95161f978d2461508a828136f0c18f61cd6fa369963ba3776f55bd11a90d912
+size 1064

checkpoint-126/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

checkpoint-126/sentencepiece.bpe.model

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

checkpoint-126/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-126/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
+size 17083053

checkpoint-126/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-126/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.8379377126693726,
+  "best_model_checkpoint": "autotrain-pe4xw-rb8r8/checkpoint-126",
+  "epoch": 2.9411764705882355,
+  "eval_steps": 500,
+  "global_step": 126,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 20.175811767578125,
+      "learning_rate": 2.893805309734513e-05,
+      "loss": 0.5842,
+      "step": 17
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 13.500060081481934,
+      "learning_rate": 2.442477876106195e-05,
+      "loss": 0.4413,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_cosine_accuracy": 0.9651162790697675,
+      "eval_loss": 0.8393570780754089,
+      "eval_runtime": 77.8013,
+      "eval_samples_per_second": 1.105,
+      "eval_steps_per_second": 0.141,
+      "step": 43
+    },
+    {
+      "epoch": 1.188235294117647,
+      "grad_norm": 14.887923240661621,
+      "learning_rate": 1.991150442477876e-05,
+      "loss": 0.4844,
+      "step": 51
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 21.601289749145508,
+      "learning_rate": 1.5398230088495576e-05,
+      "loss": 0.4827,
+      "step": 68
+    },
+    {
+      "epoch": 1.988235294117647,
+      "grad_norm": 19.94289207458496,
+      "learning_rate": 1.088495575221239e-05,
+      "loss": 0.5319,
+      "step": 85
+    },
+    {
+      "epoch": 2.0,
+      "eval_cosine_accuracy": 0.9651162790697675,
+      "eval_loss": 0.8382742404937744,
+      "eval_runtime": 78.3331,
+      "eval_samples_per_second": 1.098,
+      "eval_steps_per_second": 0.14,
+      "step": 86
+    },
+    {
+      "epoch": 2.376470588235294,
+      "grad_norm": 36.912296295166016,
+      "learning_rate": 6.371681415929204e-06,
+      "loss": 0.5825,
+      "step": 102
+    },
+    {
+      "epoch": 2.776470588235294,
+      "grad_norm": 15.572786331176758,
+      "learning_rate": 1.8584070796460177e-06,
+      "loss": 0.5355,
+      "step": 119
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "eval_cosine_accuracy": 0.9651162790697675,
+      "eval_loss": 0.8379377126693726,
+      "eval_runtime": 77.9595,
+      "eval_samples_per_second": 1.103,
+      "eval_steps_per_second": 0.141,
+      "step": 126
+    }
+  ],
+  "logging_steps": 17,
+  "max_steps": 126,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 2
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-126/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2d487d4c68837ccc6a7f8c3dbe38e8aad412c2c7e4e7897fb9b515bd203a46
+size 5624

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "BAAI/bge-m3",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.48.0",
+    "pytorch": "2.4.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1246e02d548f39bc37d7b52bcb5aee097683123d01a5c6796443a8f365a054f5
+size 2271064456

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

runs/Apr30_08-03-57_r-sarahharouni-mistral-rag-kasem-7mps8ht6-81272-u15nc/events.out.tfevents.1746000239.r-sarahharouni-mistral-rag-kasem-7mps8ht6-81272-u15nc.663.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b236238227ed5fc9a978bf92a343211a04aad38dcb9b2c5554477fa13ae50dbd
-size 6313
+oid sha256:179215a39b98983de58efa025947fe90e2db89899543ec8c9e00c23acfba2afb
+size 7192

runs/Apr30_08-03-57_r-sarahharouni-mistral-rag-kasem-7mps8ht6-81272-u15nc/events.out.tfevents.1746002934.r-sarahharouni-mistral-rag-kasem-7mps8ht6-81272-u15nc.663.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67881ab7429c9dec08c8109ac05c4f2fec931a84a8a2e211a75b3219e156ab35
+size 412

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
+size 17083053

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2d487d4c68837ccc6a7f8c3dbe38e8aad412c2c7e4e7897fb9b515bd203a46
+size 5624

training_params.json

@@ -0,0 +1,33 @@
+{
+    "data_path": "autotrain-pe4xw-rb8r8/autotrain-data",
+    "model": "BAAI/bge-m3",
+    "lr": 3e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 4,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 2,
+    "optimizer": "sgd",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "logging_steps": -1,
+    "project_name": "autotrain-pe4xw-rb8r8",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "sarahharouni",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01,
+    "trainer": "triplet",
+    "sentence1_column": "autotrain_sentence1",
+    "sentence2_column": "autotrain_sentence2",
+    "sentence3_column": "autotrain_sentence3",
+    "target_column": "autotrain_target"
+}