mmbert-news-classifier

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: mit
+base_model: jhu-clsp/mmBERT-small
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: mmbert-xnli
+  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. -->
+
+# mmbert-xnli
+
+This model is a fine-tuned version of [jhu-clsp/mmBERT-small](https://huggingface.co/jhu-clsp/mmBERT-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3736
+- Accuracy: 0.8863
+- F1: 0.8863
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 337  | 0.4502          | 0.8600   | 0.8587 |
+| 0.6169        | 2.0   | 674  | 0.3983          | 0.8796   | 0.8786 |
+| 0.2926        | 3.0   | 1011 | 0.3693          | 0.8904   | 0.8907 |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.2

config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 1,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 1,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 160000,
+  "mask_token_id": 4,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 6,
+  "num_hidden_layers": 22,
+  "pad_token_id": 0,
+  "position_embedding_type": "sans_pos",
+  "problem_type": "single_label_classification",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 1,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "vocab_size": 256000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e37febace17010843fefc718f9255a0fbf52db38602b7a82fdf52542b65a6d3
+size 562594180

runs/Sep25_04-25-18_af36607984a6/events.out.tfevents.1758774327.af36607984a6.92.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccafbb24ce4c862aad0b96d52753c93415337c3a6fe759db71f7088c56606aa
+size 5885

runs/Sep25_04-47-26_af36607984a6/events.out.tfevents.1758775694.af36607984a6.36.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243c82d74c83333e91cb9e96a53047d9ab9444d7ddd68bb209213f28cbd9b025
+size 7767

runs/Sep25_04-47-26_af36607984a6/events.out.tfevents.1758778450.af36607984a6.36.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b478e412d163be9cdd3dc94e841ab4c02579f39d8fd46e48246bf874ebcdd42b
+size 457

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7a46de687cc4a13524b40a36b3c8bd51cb4f0028519302d3de24745b9eb955
+size 5304