From 586431db13af396e27dbe826365d85cdaa5f68b1 Mon Sep 17 00:00:00 2001
From: xxl <505279206@qq.com>
Date: Mon, 17 Mar 2025 10:04:14 +0800
Subject: [PATCH] first commit

---
 README.md         | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 model.safetensors |  3 +++
 pytorch_model.bin |  3 +++
 3 files changed, 52 insertions(+)
 create mode 100644 model.safetensors
 create mode 100644 pytorch_model.bin

diff --git a/README.md b/README.md
index 8884bab..a735015 100644
--- a/README.md
+++ b/README.md
@@ -105,6 +105,52 @@ The EuroBERT family exhibits strong multilingual performance across domains and
   <img src="img/long_context.png" width="100%"  alt="EuroBERT" />
 </div>
 
+### Suggested Fine-Tuning Hyperparameters
+
+If you plan to fine-tune this model on some downstream tasks, you can follow the hyperparameters we found in our paper.
+
+#### Base Hyperparameters (unchanged across tasks)
+
+- Warmup Ratio: 0.1
+- Learning Rate Scheduler: Linear
+- Adam Beta 1: 0.9  
+- Adam Beta 2: 0.95  
+- Adam Epsilon: 1e-5  
+- Weight Decay: 0.1  
+
+#### Task-Specific Learning Rates
+
+##### Sequence Classification:
+
+| Dataset                              | EuroBERT-210m | EuroBERT-610m | EuroBERT-2.1B |
+|--------------------------------------|----------------|----------------|----------------|
+| XNLI                                 | 3.6e-05        | 3.6e-05        | 2.8e-05        |
+| PAWS-X                               | 3.6e-05        | 4.6e-05        | 3.6e-05        |
+| QAM                                  | 3.6e-05        | 2.8e-05        | 2.2e-05        |
+| AmazonReviews                        | 3.6e-05        | 2.8e-05        | 3.6e-05        |
+| MassiveIntent                        | 6.0e-05        | 4.6e-05        | 2.8e-05        |
+| CodeDefect                           | 3.6e-05        | 2.8e-05        | 1.3e-05        |
+| CodeComplexity                       | 3.6e-05        | 3.6e-05        | 1.0e-05        |
+| MathShepherd                         | 7.7e-05        | 2.8e-05        | 1.7e-05        |
+
+##### Sequence Regression:
+
+| Dataset                  | EuroBERT-210m | EuroBERT-610m | EuroBERT-2.1B |
+|--------------------------|----------------|----------------|----------------|
+| SeaHorse                 | 3.6e-05        | 3.6e-05        | 2.8e-05        |
+| SummevalMultilingual     | 3.6e-05        | 2.8e-05        | 3.6e-05        |
+| WMT                      | 2.8e-05        | 2.8e-05        | 1.3e-05        |
+
+##### Retrieval:
+| Dataset                                 | EuroBERT-210m | EuroBERT-610m | EuroBERT-2.1B |
+|-----------------------------------------|----------------|----------------|----------------|
+| MIRACL                                  | 4.6e-05        | 3.6e-05        | 2.8e-05        |
+| MLDR                                    | 2.8e-05        | 2.2e-05        | 4.6e-05        |
+| CC-News                                 | 4.6e-05        | 4.6e-05        | 3.6e-05        |
+| Wikipedia                               | 2.8e-05        | 3.6e-05        | 2.8e-05        |
+| CodeSearchNet                           | 4.6e-05        | 2.8e-05        | 3.6e-05        |
+| CqaDupStackMath                         | 4.6e-05        | 2.8e-05        | 3.6e-05        |
+| MathFormula                             | 1.7e-05        | 3.6e-05        | 3.6e-05        |
 
 ## License
 
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..09f97ef
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e41b32655cbe62c63dac675b1a2a6625632ed1991243eed5d641d2f6952791
+size 3022529592
diff --git a/pytorch_model.bin b/pytorch_model.bin
new file mode 100644
index 0000000..90f7aac
--- /dev/null
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ec9ab592ee33fee99ffc6d4ca90800866630f1023cbda2f56cec88625601dc
+size 3022568750