Add new CrossEncoder model

README.md

@@ -0,0 +1,425 @@
+---
+tags:
+- sentence-transformers
+- cross-encoder
+- generated_from_trainer
+- dataset_size:18549
+- loss:BinaryCrossEntropyLoss
+base_model: cross-encoder/ms-marco-MiniLM-L6-v2
+datasets:
+- CharlesPing/climate-cross-encoder-mixed-neg-v1
+pipeline_tag: text-ranking
+library_name: sentence-transformers
+metrics:
+- map
+- mrr@10
+- ndcg@10
+model-index:
+- name: CrossEncoder based on cross-encoder/ms-marco-MiniLM-L6-v2
+  results:
+  - task:
+      type: cross-encoder-reranking
+      name: Cross Encoder Reranking
+    dataset:
+      name: climate rerank multineg
+      type: climate-rerank-multineg
+    metrics:
+    - type: map
+      value: 0.9339128697042365
+      name: Map
+    - type: mrr@10
+      value: 0.9415467625899281
+      name: Mrr@10
+    - type: ndcg@10
+      value: 0.9532837597926094
+      name: Ndcg@10
+---
+
+# CrossEncoder based on cross-encoder/ms-marco-MiniLM-L6-v2
+
+This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [cross-encoder/ms-marco-MiniLM-L6-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L6-v2) on the [climate-cross-encoder-mixed-neg-v1](https://huggingface.co/datasets/CharlesPing/climate-cross-encoder-mixed-neg-v1) dataset using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Cross Encoder
+- **Base model:** [cross-encoder/ms-marco-MiniLM-L6-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L6-v2) <!-- at revision ce0834f22110de6d9222af7a7a03628121708969 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Number of Output Labels:** 1 label
+- **Training Dataset:**
+    - [climate-cross-encoder-mixed-neg-v1](https://huggingface.co/datasets/CharlesPing/climate-cross-encoder-mixed-neg-v1)
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder)
+
+## 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 CrossEncoder
+
+# Download from the 🤗 Hub
+model = CrossEncoder("CharlesPing/finetuned-ce-climate-multineg-v1")
+# Get scores for pairs of texts
+pairs = [
+    ['Within a decade, certain kinds of branching and plate coral could be extinct, reef scientists say, along with a variety of small fish that rely on them for protection from predators.', 'They are important apex predators feeding on a wide variety of smaller fish and cephalopods.'],
+    ['Armed conflicts over resources may become a reality, and have the potential to escalate into nuclear war.', 'The length of the track is 1,000 meters.'],
+    ['The natural cycle adds and removes CO2 to keep a balance; humans add extra CO2 without removing any.', 'Their post office was established in February 1882 and closed in December 1942'],
+    ['The atmosphere of the Earth is less able to absorb shortwave radiation from the Sun than thermal radiation coming from the surface.', 'Its fundamental principle is that of balance – the energy that the Earth absorbs from the sun each year is equal to that which it loses to space by radiation.'],
+    ['But then, just over a year ago, Mike Wallace, a hydrologist with 30 years’ experience, noticed while researching his PhD that they had omitted some key information[…] his results were surprising: there has been no reduction in oceanic pH', 'It is also known for its Kampot fish sauce and durian.'],
+]
+scores = model.predict(pairs)
+print(scores.shape)
+# (5,)
+
+# Or rank different texts based on similarity to a single text
+ranks = model.rank(
+    'Within a decade, certain kinds of branching and plate coral could be extinct, reef scientists say, along with a variety of small fish that rely on them for protection from predators.',
+    [
+        'They are important apex predators feeding on a wide variety of smaller fish and cephalopods.',
+        'The length of the track is 1,000 meters.',
+        'Their post office was established in February 1882 and closed in December 1942',
+        'Its fundamental principle is that of balance – the energy that the Earth absorbs from the sun each year is equal to that which it loses to space by radiation.',
+        'It is also known for its Kampot fish sauce and durian.',
+    ]
+)
+# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
+```
+
+<!--
+### 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
+
+#### Cross Encoder Reranking
+
+* Dataset: `climate-rerank-multineg`
+* Evaluated with [<code>CrossEncoderRerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderRerankingEvaluator) with these parameters:
+  ```json
+  {
+      "at_k": 10
+  }
+  ```
+
+| Metric      | Value      |
+|:------------|:-----------|
+| map         | 0.9339     |
+| mrr@10      | 0.9415     |
+| **ndcg@10** | **0.9533** |
+
+<!--
+## 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
+
+#### climate-cross-encoder-mixed-neg-v1
+
+* Dataset: [climate-cross-encoder-mixed-neg-v1](https://huggingface.co/datasets/CharlesPing/climate-cross-encoder-mixed-neg-v1) at [7ee5ee6](https://huggingface.co/datasets/CharlesPing/climate-cross-encoder-mixed-neg-v1/tree/7ee5ee6e1a6c7731a99935bf686edaf21ad91f0c)
+* Size: 18,549 training samples
+* Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                                            | doc                                                                                               | label                                                          |
+  |:--------|:-------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                                           | string                                                                                            | float                                                          |
+  | details | <ul><li>min: 26 characters</li><li>mean: 123.32 characters</li><li>max: 332 characters</li></ul> | <ul><li>min: 20 characters</li><li>mean: 144.94 characters</li><li>max: 1979 characters</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.21</li><li>max: 1.0</li></ul> |
+* Samples:
+  | query                                                                                                                                         | doc                                                                                                                                                                                                         | label            |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>CO2 emissions were much smaller 100 years ago.</code>                                                                                   | <code>For example, in the Internet protocol suite, the contents of a web page are encapsulated with an HTTP header, then by a TCP header, an IP header, and, finally, by a frame header and trailer.</code> | <code>0.0</code> |
+  | <code>Though CRU neglected to provide an exact list of temperature stations, it could not have hid or tampered with data.</code>              | <code>In Informatics, dummy data is benign information that does not contain any useful data, but serves to reserve space where real data is nominally present.</code>                                      | <code>0.0</code> |
+  | <code>Postma's model contains many simple errors; in no way does Postma undermine the existence or necessity of the greenhouse effect.</code> | <code>Arizona State University at the West Campus is one of four university campuses that compose Arizona State University (ASU).</code>                                                                    | <code>0.0</code> |
+* Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
+  ```json
+  {
+      "activation_fn": "torch.nn.modules.linear.Identity",
+      "pos_weight": null
+  }
+  ```
+
+### Evaluation Dataset
+
+#### climate-cross-encoder-mixed-neg-v1
+
+* Dataset: [climate-cross-encoder-mixed-neg-v1](https://huggingface.co/datasets/CharlesPing/climate-cross-encoder-mixed-neg-v1) at [7ee5ee6](https://huggingface.co/datasets/CharlesPing/climate-cross-encoder-mixed-neg-v1/tree/7ee5ee6e1a6c7731a99935bf686edaf21ad91f0c)
+* Size: 2,061 evaluation samples
+* Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                                            | doc                                                                                             | label                                                          |
+  |:--------|:-------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                                           | string                                                                                          | float                                                          |
+  | details | <ul><li>min: 31 characters</li><li>mean: 124.23 characters</li><li>max: 319 characters</li></ul> | <ul><li>min: 9 characters</li><li>mean: 138.92 characters</li><li>max: 851 characters</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.18</li><li>max: 1.0</li></ul> |
+* Samples:
+  | query                                                                                                                                                                                               | doc                                                                                                       | label            |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>Within a decade, certain kinds of branching and plate coral could be extinct, reef scientists say, along with a variety of small fish that rely on them for protection from predators.</code> | <code>They are important apex predators feeding on a wide variety of smaller fish and cephalopods.</code> | <code>1.0</code> |
+  | <code>Armed conflicts over resources may become a reality, and have the potential to escalate into nuclear war.</code>                                                                              | <code>The length of the track is 1,000 meters.</code>                                                     | <code>0.0</code> |
+  | <code>The natural cycle adds and removes CO2 to keep a balance; humans add extra CO2 without removing any.</code>                                                                                   | <code>Their post office was established in February 1882 and closed in December 1942</code>               | <code>0.0</code> |
+* Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
+  ```json
+  {
+      "activation_fn": "torch.nn.modules.linear.Identity",
+      "pos_weight": null
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 32
+- `learning_rate`: 2e-05
+- `warmup_ratio`: 0.1
+- `load_best_model_at_end`: True
+
+#### 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`: 32
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-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`: False
+- `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}
+- `tp_size`: 0
+- `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`: 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
+- `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 | climate-rerank-multineg_ndcg@10 |
+|:----------:|:--------:|:-------------:|:---------------:|:-------------------------------:|
+| 0.0862     | 100      | 0.6482        | -               | -                               |
+| 0.1724     | 200      | 0.513         | -               | -                               |
+| 0.2586     | 300      | 0.4079        | -               | -                               |
+| 0.3448     | 400      | 0.3655        | -               | -                               |
+| 0.4310     | 500      | 0.3771        | 0.3597          | 0.9309                          |
+| 0.5172     | 600      | 0.336         | -               | -                               |
+| 0.6034     | 700      | 0.3322        | -               | -                               |
+| 0.6897     | 800      | 0.3337        | -               | -                               |
+| 0.7759     | 900      | 0.3342        | -               | -                               |
+| **0.8621** | **1000** | **0.3437**    | **0.3364**      | **0.9378**                      |
+| 0.9483     | 1100     | 0.3341        | -               | -                               |
+| 1.0345     | 1200     | 0.3193        | -               | -                               |
+| 1.1207     | 1300     | 0.286         | -               | -                               |
+| 1.2069     | 1400     | 0.2883        | -               | -                               |
+| 1.2931     | 1500     | 0.2786        | 0.3290          | 0.9441                          |
+| 1.3793     | 1600     | 0.3022        | -               | -                               |
+| 1.4655     | 1700     | 0.2828        | -               | -                               |
+| 1.5517     | 1800     | 0.2925        | -               | -                               |
+| 1.6379     | 1900     | 0.2827        | -               | -                               |
+| 1.7241     | 2000     | 0.291         | 0.3426          | 0.9463                          |
+| 1.8103     | 2100     | 0.2947        | -               | -                               |
+| 1.8966     | 2200     | 0.2918        | -               | -                               |
+| 1.9828     | 2300     | 0.2868        | -               | -                               |
+| 2.0690     | 2400     | 0.2633        | -               | -                               |
+| 2.1552     | 2500     | 0.2524        | 0.3324          | 0.9521                          |
+| 2.2414     | 2600     | 0.2412        | -               | -                               |
+| 2.3276     | 2700     | 0.2796        | -               | -                               |
+| 2.4138     | 2800     | 0.2374        | -               | -                               |
+| 2.5        | 2900     | 0.2243        | -               | -                               |
+| 2.5862     | 3000     | 0.2451        | 0.3459          | 0.9533                          |
+| 2.6724     | 3100     | 0.2388        | -               | -                               |
+| 2.7586     | 3200     | 0.2447        | -               | -                               |
+| 2.8448     | 3300     | 0.2548        | -               | -                               |
+| 2.9310     | 3400     | 0.2487        | -               | -                               |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.12
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.3
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+<!--
+## 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.*
+-->

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "sentence_transformers": {
+    "activation_fn": "torch.nn.modules.linear.Identity",
+    "version": "4.1.0"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65efb33c12979f8f394cfdbb78de1951bb4e748d317d128d05b93dcd3255c631
+size 90866412

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}