davanstrien/modernbert-hf-dataset-domain-v1

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: answerdotai/ModernBERT-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: modernbert-output
+  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. -->
+
+# modernbert-output
+
+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: 0.6180
+- Accuracy: 0.8867
+- Macro F1: 0.8872
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- 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
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
+| 3.0392        | 1.0   | 140  | 0.6617          | 0.8267   | 0.8251   |
+| 1.4070        | 2.0   | 280  | 0.5377          | 0.8733   | 0.8759   |
+| 0.5328        | 3.0   | 420  | 0.6954          | 0.86     | 0.8646   |
+| 0.3036        | 4.0   | 560  | 0.6180          | 0.8867   | 0.8872   |
+| 0.0971        | 5.0   | 700  | 0.6528          | 0.88     | 0.8813   |
+
+
+### Framework versions
+
+- Transformers 5.3.0
+- Pytorch 2.11.0+cu130
+- Datasets 4.8.4
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,102 @@
+{
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "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": 50282,
+  "global_attn_every_n_layers": 3,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "biology",
+    "1": "chemistry",
+    "2": "climate",
+    "3": "code",
+    "4": "cybersecurity",
+    "5": "finance",
+    "6": "legal",
+    "7": "math",
+    "8": "medical",
+    "9": "none"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "biology": 0,
+    "chemistry": 1,
+    "climate": 2,
+    "code": 3,
+    "cybersecurity": 4,
+    "finance": 5,
+    "legal": 6,
+    "math": 7,
+    "medical": 8,
+    "none": 9
+  },
+  "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": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75fcc66c10b8fc27a43c22f0b5c6039fb9a6f43da89c228df51df652d040039
+size 598464400

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77be74738b5f414a0df4d278fc41accfcc7ab59c3a84940ca627f468bb33528
+size 5201