Fine-tuned ModernBERT-base on biglam/on_the_books

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: answerdotai/ModernBERT-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: jim-crow-laws-claude-code
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# jim-crow-laws-claude-code
+
+This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1205
+- Accuracy: 0.9776
+- Precision Jim Crow: 0.9352
+- Recall Jim Crow: 0.9902
+- F1 Jim Crow: 0.9619
+- F1 Macro: 0.9730
+- Roc Auc: 0.9965
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Jim Crow | Recall Jim Crow | F1 Jim Crow | F1 Macro | Roc Auc |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------------------:|:---------------:|:-----------:|:--------:|:-------:|
+| 0.2893        | 1.0   | 90   | 0.1920          | 0.9524   | 0.8972             | 0.9412          | 0.9187      | 0.9425   | 0.9913  |
+| 0.0716        | 2.0   | 180  | 0.0793          | 0.9776   | 0.9519             | 0.9706          | 0.9612      | 0.9727   | 0.9971  |
+| 0.1101        | 3.0   | 270  | 0.1205          | 0.9776   | 0.9352             | 0.9902          | 0.9619      | 0.9730   | 0.9965  |
+| 0.0027        | 4.0   | 360  | 0.1251          | 0.9776   | 0.9352             | 0.9902          | 0.9619      | 0.9730   | 0.9958  |
+| 0.0001        | 5.0   | 450  | 0.1231          | 0.9748   | 0.9346             | 0.9804          | 0.9569      | 0.9696   | 0.9960  |
+
+
+### Framework versions
+
+- Transformers 5.7.0
+- Pytorch 2.11.0+cu130
+- Datasets 4.8.5
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,86 @@
+{
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "float32",
+  "embedding_dropout": 0.0,
+  "eos_token_id": null,
+  "global_attn_every_n_layers": 3,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "no_jim_crow",
+    "1": "jim_crow"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "jim_crow": 1,
+    "no_jim_crow": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "layer_types": [
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "local_attention": 128,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 160000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291f3e6175ab7a4eb12d0c4ae31156b8b5458c9514dbe0bbd7d50009d6bf2619
+size 598439784

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1033e08c09e9c076396099defaf634bcfb61d672a52e6f44d26b9b4916f539
+size 5329