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-33/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": 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
+}

README.md

@@ -0,0 +1,72 @@
+
+---
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- autotrain
+base_model: djovak/embedic-large
+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: 0.12450794875621796
+
+cosine_accuracy: 1.0
+
+dot_accuracy: 0.0
+
+manhattan_accuracy: 1.0
+
+euclidean_accuracy: 1.0
+
+max_accuracy: 1.0
+
+runtime: 58.713
+
+samples_per_second: 0.766
+
+steps_per_second: 0.051
+
+: 8.909090909090908
+
+## 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-33/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

checkpoint-33/README.md

@@ -0,0 +1,460 @@
+---
+base_model: djovak/embedic-large
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- dot_accuracy
+- manhattan_accuracy
+- euclidean_accuracy
+- max_accuracy
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:176
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Kako Meridian kladionica tretira odlaganja?
+  sentences:
+  - Klađenje na dubl se razlikuje od singla, gde timska hemija i tehnika igrača poput
+    voleja i servisa igraju ključnu ulogu.
+  - Važno je pratiti formu igrača, promene u servisu i povrede kako biste doneli informisane
+    odluke u klađenju uživo na tenis.
+  - Meridian kladionica računa kvotu 1.00 ako se utakmica ne odigra u roku od sledećeg
+    dana od planiranog termina.
+- source_sentence: Šta je hajnc sistem klađenja?
+  sentences:
+  - Loši vremenski uslovi, kao što su kiša ili sneg, mogu otežati igru i smanjiti
+    broj golova.
+  - Hajnc je kombinovani sistem klađenja koji uključuje šest događaja i ukupno 57
+    pojedinačnih opklada.
+  - Za razliku od drugih sportova, vremenski uslovi ne utiču direktno na košarkaške
+    mečeve, ali povrede ili izostanci igrača mogu značajno promeniti ishod.
+- source_sentence: Kako funkcioniše klađenje na poluvreme/kraj?
+  sentences:
+  - Ako se utakmica odloži za više od 48 sati, kvota postaje 1.00 i ulog se vraća,
+    osim ako su ostali parovi na tiketu.
+  - Ova vrsta klađenja zahteva predviđanje ishoda i na poluvremenu i na kraju utakmice.
+    Na primer, opklada 1-2 znači da domaćin vodi na poluvremenu, ali gost pobeđuje
+    na kraju.
+  - Sistem 'Srećni 31' uključuje pet događaja i ukupno 31 pojedinačnu opkladu koja
+    obuhvata singl, dubl, trostruke, četvorostruke i petostruke opklade.
+- source_sentence: Kako koristiti informacije za klađenje?
+  sentences:
+  - Informacije su ključne za uspešno klađenje. Preporučuje se korišćenje službenih
+    sportskih stranica, portala i aplikacija za vesti kako biste dobili najnovije
+    podatke o utakmicama i igračima.
+  - Koeficijenti, ili kvote, označavaju verovatnoću ishoda događaja i određuju potencijalni
+    dobitak na osnovu uloženog novca.
+  - Hendikep klađenje podrazumeva da slabiji tim dobija prednost u bodovima pre početka
+    meča, čime se izjednačavaju šanse za pobedu.
+- source_sentence: Šta je klađenje na kartone?
+  sentences:
+  - Ravnomerno klađenje podrazumeva postavljanje istog uloga na svaki događaj kako
+    bi se smanjio rizik.
+  - Klađenje na broj kornera podrazumeva predviđanje koliko će kornera biti izvedeno
+    tokom meča, sa kvotama koje se menjaju uživo.
+  - Klađenje na kartone uključuje predviđanje broja žutih ili crvenih kartona na utakmici,
+    postavljajući granicu pre početka utakmice.
+model-index:
+- name: SentenceTransformer based on djovak/embedic-large
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy
+      value: 1.0
+      name: Cosine Accuracy
+    - type: dot_accuracy
+      value: 0.0
+      name: Dot Accuracy
+    - type: manhattan_accuracy
+      value: 1.0
+      name: Manhattan Accuracy
+    - type: euclidean_accuracy
+      value: 1.0
+      name: Euclidean Accuracy
+    - type: max_accuracy
+      value: 1.0
+      name: Max Accuracy
+---
+
+# SentenceTransformer based on djovak/embedic-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [djovak/embedic-large](https://huggingface.co/djovak/embedic-large). 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:** [djovak/embedic-large](https://huggingface.co/djovak/embedic-large) <!-- at revision 4d275ee32c11e1e2a1de8dc59493551c8e2bc4c8 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 tokens
+- **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': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (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 = [
+    'Šta je klađenje na kartone?',
+    'Klađenje na kartone uključuje predviđanje broja žutih ili crvenih kartona na utakmici, postavljajući granicu pre početka utakmice.',
+    'Ravnomerno klađenje podrazumeva postavljanje istog uloga na svaki događaj kako bi se smanjio rizik.',
+]
+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    | 1.0     |
+| dot_accuracy       | 0.0     |
+| manhattan_accuracy | 1.0     |
+| euclidean_accuracy | 1.0     |
+| **max_accuracy**   | **1.0** |
+
+<!--
+## 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: 176 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 176 samples:
+  |         | anchor                                                                           | positive                                                                           | negative                                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 12.9 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 33.32 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 21 tokens</li><li>mean: 33.6 tokens</li><li>max: 54 tokens</li></ul> |
+* Samples:
+  | anchor                                                              | positive                                                                                                                                              | negative                                                                                                                                                                                         |
+  |:--------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Kako funkcioniše klađenje uživo na tenis?</code>              | <code>Klađenje uživo na tenis omogućava predviđanje ishoda poena, gemova i setova tokom meča, sa stalnim promenama kvota u zavisnosti od igre.</code> | <code>Trixie sistem klađenja uključuje četiri opklade na tri različita događaja: tri dubl opklade i jednu trostruku opkladu. Dovoljna su dva pogođena događaja da bi se ostvario dobitak.</code> |
+  | <code>Šta je klađenje na produžetke?</code>                         | <code>Klađenje na produžetke uključuje opklade na ishod utakmice u dodatnim periodima igre, nakon regularnog vremena.</code>                          | <code>Najpopularnije lige za klađenje na hokej uključuju NHL, Kontinentalnu ligu (KHL) i švedsku hokejašku ligu.</code>                                                                          |
+  | <code>Kako pandemija COVID-19 utiče na otkazivanje utakmica?</code> | <code>Pandemija COVID-19 je dovela do povećanja broja otkazanih utakmica zbog zdravstvenih protokola i izolacija igrača.</code>                       | <code>Hendikep dodaje golove slabijem timu kako bi se izjednačile šanse za oba tima.</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: 45 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 45 samples:
+  |         | anchor                                                                            | positive                                                                           | negative                                                                           |
+  |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                             | string                                                                             |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 12.89 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 25 tokens</li><li>mean: 35.67 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 21 tokens</li><li>mean: 32.58 tokens</li><li>max: 54 tokens</li></ul> |
+* Samples:
+  | anchor                                                                        | positive                                                                                                                                                        | negative                                                                                                                                                         |
+  |:------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Kako DNB funkcioniše u klađenju uživo?</code>                           | <code>U klađenju uživo, DNB postaje profitabilan kada autsajder postigne gol prvi, povećavajući kvote za favorita.</code>                                       | <code>Klađenje na kornere omogućava predviđanje broja kornera na utakmici. Igrač se kladi da li će broj kornera biti iznad ili ispod postavljene granice.</code> |
+  | <code>Šta se dešava sa opkladama u slučaju promenjenog mesta događaja?</code> | <code>Ako se promeni mesto održavanja utakmice, opklade postaju nevažeće, a kvota se računa kao 1.00.</code>                                                    | <code>Ako se utakmica pomeri za više od 48 sati, kladionica proglašava događaj nevažećim i kvota postaje 1.00.</code>                                            |
+  | <code>Šta je azijski hendikep?</code>                                         | <code>Azijski hendikep daje jednom timu prednost pre početka utakmice, a opklada se deli na dve odvojene opklade kako bi se izjednačile šanse za pobedu.</code> | <code>Najčešći tipovi klađenja uključuju konačan ishod, hendikep, ukupan broj poena, i klađenje na performanse pojedinih igrača.</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_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 1e-05
+- `weight_decay`: 0.01
+- `max_grad_norm`: 0.5
+- `num_train_epochs`: 10
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.2
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `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`: 8
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 4
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 1e-05
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 0.5
+- `num_train_epochs`: 10
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.2
+- `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`: adamw_torch
+- `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`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | max_accuracy |
+|:------:|:----:|:-------------:|:------:|:------------:|
+| 0.9091 | 5    | -             | 0.7353 | 1.0          |
+| 1.8182 | 10   | 0.4569        | -      | -            |
+| 2.0    | 11   | -             | 0.2711 | 1.0          |
+| 2.9091 | 16   | -             | 0.1681 | 1.0          |
+| 3.6364 | 20   | 0.1037        | -      | -            |
+| 4.0    | 22   | -             | 0.1329 | 1.0          |
+| 4.9091 | 27   | -             | 0.1265 | 1.0          |
+| 5.4545 | 30   | 0.0643        | -      | -            |
+| 6.0    | 33   | -             | 0.1245 | 1.0          |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.1.1
+- Transformers: 4.45.0
+- PyTorch: 2.3.0
+- Accelerate: 0.34.1
+- Datasets: 2.19.1
+- Tokenizers: 0.20.0
+
+## 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-33/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "djovak/embedic-large",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-33/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.45.0",
+    "pytorch": "2.3.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-33/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfa3c662d6af06d8e24845f5ee7ab6f3b57efc3c978d322d2d13da3e215a84f
+size 2239607176

checkpoint-33/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-33/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534a3cefca7a26a5cf3ec9d3b4936a12e21e5dfa7cedbd79e38c883123d1bcdf
+size 4471044921

checkpoint-33/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc566a35845d6fe51ff230b5d3f1b0215c0787058eb36327f493e6c6ea2d696e
+size 13990

checkpoint-33/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5bd01514c0ed55d14d32113f513a6a0f1eb4d2c5ce558a43eb0831f821af9d
+size 1064

checkpoint-33/sentence_bert_config.json

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

checkpoint-33/sentencepiece.bpe.model

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

checkpoint-33/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-33/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fbf784ee16fec3bc557753a524df9e1c6959d0a13ff61366f6d0018341528d
+size 17090510

checkpoint-33/tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

checkpoint-33/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.12450794875621796,
+  "best_model_checkpoint": "autotrain-kladionica/checkpoint-33",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 33,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9090909090909091,
+      "eval_cosine_accuracy": 1.0,
+      "eval_dot_accuracy": 0.0,
+      "eval_euclidean_accuracy": 1.0,
+      "eval_loss": 0.7352991104125977,
+      "eval_manhattan_accuracy": 1.0,
+      "eval_max_accuracy": 1.0,
+      "eval_runtime": 59.5349,
+      "eval_samples_per_second": 0.756,
+      "eval_steps_per_second": 0.05,
+      "step": 5
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 4.690580368041992,
+      "learning_rate": 1e-05,
+      "loss": 0.4569,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_cosine_accuracy": 1.0,
+      "eval_dot_accuracy": 0.0,
+      "eval_euclidean_accuracy": 1.0,
+      "eval_loss": 0.271090030670166,
+      "eval_manhattan_accuracy": 1.0,
+      "eval_max_accuracy": 1.0,
+      "eval_runtime": 58.202,
+      "eval_samples_per_second": 0.773,
+      "eval_steps_per_second": 0.052,
+      "step": 11
+    },
+    {
+      "epoch": 2.909090909090909,
+      "eval_cosine_accuracy": 1.0,
+      "eval_dot_accuracy": 0.0,
+      "eval_euclidean_accuracy": 1.0,
+      "eval_loss": 0.16810357570648193,
+      "eval_manhattan_accuracy": 1.0,
+      "eval_max_accuracy": 1.0,
+      "eval_runtime": 64.351,
+      "eval_samples_per_second": 0.699,
+      "eval_steps_per_second": 0.047,
+      "step": 16
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 1.5101182460784912,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.1037,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_cosine_accuracy": 1.0,
+      "eval_dot_accuracy": 0.0,
+      "eval_euclidean_accuracy": 1.0,
+      "eval_loss": 0.132945716381073,
+      "eval_manhattan_accuracy": 1.0,
+      "eval_max_accuracy": 1.0,
+      "eval_runtime": 57.7743,
+      "eval_samples_per_second": 0.779,
+      "eval_steps_per_second": 0.052,
+      "step": 22
+    },
+    {
+      "epoch": 4.909090909090909,
+      "eval_cosine_accuracy": 1.0,
+      "eval_dot_accuracy": 0.0,
+      "eval_euclidean_accuracy": 1.0,
+      "eval_loss": 0.1265309602022171,
+      "eval_manhattan_accuracy": 1.0,
+      "eval_max_accuracy": 1.0,
+      "eval_runtime": 57.1986,
+      "eval_samples_per_second": 0.787,
+      "eval_steps_per_second": 0.052,
+      "step": 27
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 3.2575457096099854,
+      "learning_rate": 5e-06,
+      "loss": 0.0643,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_cosine_accuracy": 1.0,
+      "eval_dot_accuracy": 0.0,
+      "eval_euclidean_accuracy": 1.0,
+      "eval_loss": 0.12450794875621796,
+      "eval_manhattan_accuracy": 1.0,
+      "eval_max_accuracy": 1.0,
+      "eval_runtime": 57.4285,
+      "eval_samples_per_second": 0.784,
+      "eval_steps_per_second": 0.052,
+      "step": 33
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-33/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5bd0b93b2bc206736e76a939a0672af14c80c5cf01af4b31cad5f6bd79f857c
+size 5496

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "djovak/embedic-large",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.45.0",
+    "pytorch": "2.3.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfa3c662d6af06d8e24845f5ee7ab6f3b57efc3c978d322d2d13da3e215a84f
+size 2239607176

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/Oct01_08-01-11_r-luka023-autotrain-advanced-gjssstet-2e8d4-rjpch/events.out.tfevents.1727769674.r-luka023-autotrain-advanced-gjssstet-2e8d4-rjpch.108.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d7235f312648e33ec9d9e6089e812db60f4fda97c0e1f1f614cd6690b802ba
-size 9614
+oid sha256:5816e9e2cbeea5b67e21ebf44da2b71f4740eb76e68aa884cefb7aef360810a3
+size 10518

runs/Oct01_08-01-11_r-luka023-autotrain-advanced-gjssstet-2e8d4-rjpch/events.out.tfevents.1727774367.r-luka023-autotrain-advanced-gjssstet-2e8d4-rjpch.108.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:212078f807d6155452aa11c4d16d947f46063f2456e0a55740b443eb3b4df201
+size 644

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "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 sha256:42fbf784ee16fec3bc557753a524df9e1c6959d0a13ff61366f6d0018341528d
+size 17090510

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5bd0b93b2bc206736e76a939a0672af14c80c5cf01af4b31cad5f6bd79f857c
+size 5496

training_params.json

@@ -0,0 +1,33 @@
+{
+    "data_path": "autotrain-kladionica/autotrain-data",
+    "model": "djovak/embedic-large",
+    "lr": 1e-05,
+    "epochs": 10,
+    "max_seq_length": 128,
+    "batch_size": 8,
+    "warmup_ratio": 0.2,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "cosine",
+    "weight_decay": 0.01,
+    "max_grad_norm": 0.5,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "logging_steps": 10,
+    "project_name": "autotrain-kladionica",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "luka023",
+    "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"
+}