Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+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

@@ -1,3 +1,414 @@
----
-license: mit
----
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:47610
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: '[MENTION] Gustavus And Louise Pfeiffer Research Foundation [CITY]
+    Bangor [COUNTRY] United States'
+  sentences:
+  - '[MENTION] Gustavus And Louise Pfeiffer Research Foundation [CITY] Bangor [COUNTRY]
+    United States'
+  - '[MENTION] Fifth Tianjin Central Hospital [CITY] Tianjin [COUNTRY] China'
+  - '[MENTION] Purdue Research Foundation [ACRONYM] PRF [CITY] West Lafayette [COUNTRY]
+    United States'
+- source_sentence: '[MENTION] ইন্টার-ইউরিভার্সিটি সেন্টার ফর অ্যাস্ট্রোনমি অ্যান্ড
+    অ্যাস্ট্রোফিজিক্স [CITY] Pune [COUNTRY] India'
+  sentences:
+  - '[MENTION] National Centre for Radio Astrophysics [ACRONYM] NCRA TIFR [PARENT]
+    Tata Institute of Fundamental Research [ACRONYM] TIFR [CITY] Pune [COUNTRY] India'
+  - '[MENTION] Inter-University Centre for Astronomy and Astrophysics [ACRONYM] IUCAA
+    [CITY] Pune [COUNTRY] India'
+  - '[MENTION] Iskra Medical (Slovenia) [CITY] Radovljica [COUNTRY] Slovenia'
+- source_sentence: '[MENTION] Raytheon Technologies (Canada) [CITY] Calgary [COUNTRY]
+    Canada'
+  sentences:
+  - '[MENTION] Raytheon Technologies (Canada) [ACRONYM] RCL [PARENT] RTX (United States)
+    [CITY] Calgary [COUNTRY] Canada'
+  - '[MENTION] Yunnan Open University [CITY] Kunming [COUNTRY] China'
+  - '[MENTION] ATCO (Canada) [CITY] Calgary [COUNTRY] Canada'
+- source_sentence: '[MENTION] 유한양행 [CITY] Seoul'
+  sentences:
+  - '[MENTION] Instituto de Medicina Molecular João Lobo Antunes [ACRONYM] IMM [PARENT]
+    University of Lisbon [CITY] Lisbon [COUNTRY] Portugal'
+  - '[MENTION] Boehringer Ingelheim (South Korea) [PARENT] Boehringer Ingelheim (Germany)
+    [CITY] Seoul [COUNTRY] South Korea'
+  - '[MENTION] Yuhan (South Korea) [CITY] Seoul [COUNTRY] South Korea'
+- source_sentence: '[MENTION] Hyderabad Cleft Society [COUNTRY] India'
+  sentences:
+  - '[MENTION] Hyderabad Cleft Society [ACRONYM] HCS [CITY] Hyderabad [COUNTRY] India'
+  - '[MENTION] Hyderabad Rheumatology Center [ACRONYM] HRC [CITY] Hyderabad [COUNTRY]
+    India'
+  - '[MENTION] National Institute of Technology Akita College [PARENT] National Institute
+    of Technology [CITY] Akita [COUNTRY] Japan'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: entity linking eval
+      type: entity_linking_eval
+    metrics:
+    - type: pearson_cosine
+      value: 0.7072780089709011
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6825742231480432
+      name: Spearman Cosine
+---
+
+# SentenceTransformer
+
+This is a [sentence-transformers](https://www.SBERT.net) model trained. 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:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 128 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': 128, '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 = [
+    '[MENTION] Hyderabad Cleft Society [COUNTRY] India',
+    '[MENTION] Hyderabad Cleft Society [ACRONYM] HCS [CITY] Hyderabad [COUNTRY] India',
+    '[MENTION] Hyderabad Rheumatology Center [ACRONYM] HRC [CITY] Hyderabad [COUNTRY] India',
+]
+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
+
+#### Semantic Similarity
+
+* Dataset: `entity_linking_eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7073     |
+| **spearman_cosine** | **0.6826** |
+
+<!--
+## 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: 47,610 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                        | sentence_1                                                                        | sentence_2                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                             |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 13.61 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 18.63 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 19.66 tokens</li><li>max: 58 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                    | sentence_1                                                                                                                                  | sentence_2                                                                                                                                               |
+  |:--------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>[MENTION] The Prince Of Wales'S Institute Of Architecture [CITY] London [COUNTRY] United Kingdom</code> | <code>[MENTION] The Princes Foundation [CITY] London [COUNTRY] United Kingdom</code>                                                        | <code>[MENTION] Royal Institute of British Architects [ACRONYM] RIBA [CITY] London [COUNTRY] United Kingdom</code>                                       |
+  | <code>[MENTION] Development Finance & Public Policies [COUNTRY] Belgium</code>                                | <code>[MENTION] Development Finance and Public Policies [ACRONYM] DEFIPP [PARENT] University of Namur [CITY] Namur [COUNTRY] Belgium</code> | <code>[MENTION] Service Public Federal Finances [ACRONYM] SPF [CITY] Brussels [COUNTRY] Belgium</code>                                                   |
+  | <code>[MENTION] EES [COUNTRY] United States</code>                                                            | <code>[MENTION] Emerald Education Systems [ACRONYM] EES [CITY] Pasadena [COUNTRY] United States</code>                                      | <code>[MENTION] ESI Group (United States) [ACRONYM] ESI [PARENT] ESI Group (France) [ACRONYM] ESI [CITY] Farmington Hills [COUNTRY] United States</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `fp16`: 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
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `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`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: 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
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | entity_linking_eval_spearman_cosine |
+|:------:|:----:|:-------------:|:-----------------------------------:|
+| 0.1680 | 500  | 0.3431        | -                                   |
+| 0.3360 | 1000 | 0.252         | 0.4769                              |
+| 0.5040 | 1500 | 0.291         | -                                   |
+| 0.6720 | 2000 | 0.2445        | 0.6494                              |
+| 0.8401 | 2500 | 0.2339        | -                                   |
+| 1.0    | 2976 | -             | 0.6694                              |
+| 1.0081 | 3000 | 0.2256        | 0.6730                              |
+| 1.1761 | 3500 | 0.16          | -                                   |
+| 1.3441 | 4000 | 0.1428        | 0.6750                              |
+| 1.5121 | 4500 | 0.1661        | -                                   |
+| 1.6801 | 5000 | 0.139         | 0.6713                              |
+| 1.8481 | 5500 | 0.1408        | -                                   |
+| 2.0    | 5952 | -             | 0.6768                              |
+| 2.0161 | 6000 | 0.1409        | 0.6763                              |
+| 2.1841 | 6500 | 0.0759        | -                                   |
+| 2.3522 | 7000 | 0.0702        | 0.6820                              |
+| 2.5202 | 7500 | 0.0716        | -                                   |
+| 2.6882 | 8000 | 0.0777        | 0.6805                              |
+| 2.8562 | 8500 | 0.0685        | -                                   |
+| 3.0    | 8928 | -             | 0.6826                              |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.4.1
+- Transformers: 4.41.2
+- PyTorch: 2.2.0+cu121
+- Accelerate: 1.2.1
+- Datasets: 2.18.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[ACRONYM]": 250003,
+  "[CITY]": 250005,
+  "[COUNTRY]": 250006,
+  "[MENTION]": 250002,
+  "[PARENT]": 250004
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/home/pablo/affilgood/affilgood/entity_linking/data/contrastive/model/finetuned_with_iter0_100percROR_special_tokens",
+  "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": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250007
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.2.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

eval/similarity_evaluation_entity_linking_eval_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_pearson,cosine_spearman
+1.0,2976,0.6804017422113144,0.6694244550447879
+2.0,5952,0.7012000194087423,0.6768105861152512
+3.0,8928,0.7072780089709011,0.6825742231480432

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2175e93d789cd4ea065c2244d4cb51f5d20638d892f9c8c9dbfc96b91bda996d
+size 2239627656

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"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "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 sha256:44bc27f1c2bc1189b4bda0a3c563b961c21609fbe8f02ca6a16992b626b33190
+size 17083913

tokenizer_config.json

@@ -0,0 +1,101 @@
+{
+  "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
+    },
+    "250002": {
+      "content": "[MENTION]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250003": {
+      "content": "[ACRONYM]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250004": {
+      "content": "[PARENT]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250005": {
+      "content": "[CITY]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250006": {
+      "content": "[COUNTRY]",
+      "lstrip": false,
+      "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": 128,
+  "model_max_length": 128,
+  "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.json

@@ -0,0 +1,15 @@
+{
+  "model_name": "/home/pablo/affilgood/affilgood/entity_linking/data/contrastive/model/finetuned_with_iter0_100percROR_special_tokens",
+  "data_file": "/home/pablo/affilgood/affilgood/entity_linking/data/contrastive/dataset/iter1_thres60_5neg_more-labels_100percROR_special_tokens.json",
+  "output_dir": "/home/pablo/affilgood/affilgood/entity_linking/data/contrastive/model/finetuned_with_iter1_thres60_5neg_more-labels_100percROR_special_tokens",
+  "batch_size": 16,
+  "epochs": 3,
+  "learning_rate": 2e-05,
+  "warmup_steps": 1000,
+  "max_seq_length": 128,
+  "eval_steps": 1000,
+  "seed": 42,
+  "use_amp": true,
+  "num_hard_negatives": 5,
+  "temperature": 0.05
+}

training_info.txt

@@ -0,0 +1 @@
+Model trained on: 2025-03-25 14:58:11