mhr2004/answerdotai-ModernBERT-basemhr2004-atomic.anion.train.no1e-06-64

README.md

@@ -0,0 +1,81 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: answerdotai/ModernBERT-base
+tags:
+- generated_from_trainer
+model-index:
+- name: answerdotai-ModernBERT-basemhr2004-atomic.anion.train.no1e-06-64
+  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. -->
+
+# answerdotai-ModernBERT-basemhr2004-atomic.anion.train.no1e-06-64
+
+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: 0.4237
+
+## 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: 1e-06
+- train_batch_size: 128
+- eval_batch_size: 512
+- seed: 42
+- optimizer: Use 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: 30
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.5508        | 1.0   | 2304  | 0.5309          |
+| 0.4909        | 2.0   | 4608  | 0.4951          |
+| 0.4684        | 3.0   | 6912  | 0.4759          |
+| 0.4607        | 4.0   | 9216  | 0.4630          |
+| 0.4396        | 5.0   | 11520 | 0.4563          |
+| 0.4361        | 6.0   | 13824 | 0.4505          |
+| 0.4235        | 7.0   | 16128 | 0.4534          |
+| 0.4199        | 8.0   | 18432 | 0.4429          |
+| 0.4154        | 9.0   | 20736 | 0.4396          |
+| 0.4155        | 10.0  | 23040 | 0.4369          |
+| 0.4021        | 11.0  | 25344 | 0.4324          |
+| 0.3966        | 12.0  | 27648 | 0.4323          |
+| 0.3929        | 13.0  | 29952 | 0.4292          |
+| 0.3908        | 14.0  | 32256 | 0.4273          |
+| 0.3872        | 15.0  | 34560 | 0.4289          |
+| 0.3834        | 16.0  | 36864 | 0.4261          |
+| 0.3767        | 17.0  | 39168 | 0.4276          |
+| 0.3775        | 18.0  | 41472 | 0.4270          |
+| 0.367         | 19.0  | 43776 | 0.4260          |
+| 0.3673        | 20.0  | 46080 | 0.4275          |
+| 0.3726        | 21.0  | 48384 | 0.4233          |
+| 0.3575        | 22.0  | 50688 | 0.4248          |
+| 0.3633        | 23.0  | 52992 | 0.4251          |
+| 0.36          | 24.0  | 55296 | 0.4237          |
+
+
+### Framework versions
+
+- Transformers 4.51.2
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,46 @@
+{
+  "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,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "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",
+  "problem_type": "single_label_classification",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.2",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99c7ac24bc0988d17a4f3c7bc1effa1bde2173d5e5ffceb72e94e8aa671d049
+size 598439784

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36758d00b45e75fa4f7be2727013b713e7332beda5ec065047da378e097a9c4
+size 5368