End of training

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: ModernBERT-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: moe_True_addTokens_False_clipLoss_False_cv_2
+  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. -->
+
+# moe_True_addTokens_False_clipLoss_False_cv_2
+
+This model is a fine-tuned version of [ModernBERT-base](https://huggingface.co/ModernBERT-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 332.7107
+- Model Preparation Time: 0.0049
+- F1: 0.0042
+- Precision: 0.0025
+- Recall: 0.0121
+- Threshold: 1.0
+- Sim Ratio: 1.0011
+- Pos Sim: 1.0
+- Neg Sim: 0.9989
+
+## 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: 0.0001
+- train_batch_size: 16
+- eval_batch_size: 16
+- 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: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | F1     | Precision | Recall | Threshold | Sim Ratio | Pos Sim | Neg Sim |
+|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:---------:|:------:|:---------:|:---------:|:-------:|:-------:|
+| 332.7109      | 0.8   | 5000 | 332.7107        | 0.0049                 | 0.0038 | 0.0023    | 0.0109 | 1.0       | 1.001     | 1.0     | 0.999   |
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "ModernBERT-base",
+  "architectures": [
+    "MoEBertForSentenceSimilarity"
+  ],
+  "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,
+  "lora": false,
+  "lora_alpha": 32,
+  "lora_dropout": 0.01,
+  "lora_r": 8,
+  "loss_type": "mnr_loss",
+  "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_experts": 5,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "reference_compile": null,
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e58000f5702cc44568b04b70c4f3c5d637f99e70f765cddb005fc4175dc163
+size 1535119296

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b06088f4a8722c899c09bd2c89e735020c8622a5e04d65bf79a3a43e346313
+size 5368