mhr2004/answerdotai-ModernBERT-base-atomic-anion-1e-06-256

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-base-atomic-anion-1e-06-256
+  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-base-atomic-anion-1e-06-256
+
+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: 0.3983
+
+## 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: 256
+- eval_batch_size: 256
+- 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: 30
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.5623        | 1.0   | 1152  | 0.5391          |
+| 0.4968        | 2.0   | 2304  | 0.4940          |
+| 0.4624        | 3.0   | 3456  | 0.4727          |
+| 0.4443        | 4.0   | 4608  | 0.4542          |
+| 0.4246        | 5.0   | 5760  | 0.4470          |
+| 0.4141        | 6.0   | 6912  | 0.4378          |
+| 0.3985        | 7.0   | 8064  | 0.4288          |
+| 0.393         | 8.0   | 9216  | 0.4221          |
+| 0.3788        | 9.0   | 10368 | 0.4176          |
+| 0.3696        | 10.0  | 11520 | 0.4137          |
+| 0.3621        | 11.0  | 12672 | 0.4114          |
+| 0.3542        | 12.0  | 13824 | 0.4051          |
+| 0.3475        | 13.0  | 14976 | 0.4049          |
+| 0.3418        | 14.0  | 16128 | 0.4005          |
+| 0.3351        | 15.0  | 17280 | 0.4005          |
+| 0.3295        | 16.0  | 18432 | 0.3979          |
+| 0.3259        | 17.0  | 19584 | 0.3970          |
+| 0.3217        | 18.0  | 20736 | 0.3958          |
+| 0.3136        | 19.0  | 21888 | 0.3965          |
+| 0.3125        | 20.0  | 23040 | 0.3971          |
+| 0.3075        | 21.0  | 24192 | 0.3957          |
+| 0.3055        | 22.0  | 25344 | 0.3964          |
+| 0.3011        | 23.0  | 26496 | 0.3968          |
+| 0.2971        | 24.0  | 27648 | 0.3983          |
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "answerdotai/ModernBERT-base",
+  "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",
+  "reference_compile": true,
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451abe595f6507a7a2e05de46536aa03c29cc064d3b7d82fc15168081f39364b
+size 598439784

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788ce8e959e0dfb80ce4fbb5acb989ec6b967e5a6118f7bbff97de33d61320b9
+size 5368