exec_date=2025-05-27T12:22:36.961936 -- model_name=microsoft/mpnet-base -- dataset_path=sentence-transformers/all-nli -- dataset_name=triplet -- train_size=1000

README.md

@@ -8,7 +8,7 @@ tags:
 - nli
 - tutorial
 - generated_from_trainer
-- dataset_size:10000
+- dataset_size:1000
 - loss:MultipleNegativesRankingLoss
 base_model: microsoft/mpnet-base
 widget:
@@ -47,6 +47,16 @@ pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 metrics:
 - cosine_accuracy
+co2_eq_emissions:
+  emissions: 0.006544502824422758
+  energy_consumed: 0.00011678478960050603
+  source: codecarbon
+  training_type: fine-tuning
+  on_cloud: false
+  cpu_model: Apple M4
+  ram_total_size: 24.0
+  hours_used: 0.02
+  hardware_used: Apple M4
 model-index:
 - name: microsoft/mpnet-base
   results:
@@ -58,7 +68,7 @@ model-index:
       type: all-nli-eval
     metrics:
     - type: cosine_accuracy
-      value: 0.7859963774681091
+      value: 0.621051013469696
       name: Cosine Accuracy
   - task:
       type: triplet
@@ -68,7 +78,7 @@ model-index:
       type: all-nli-test
     metrics:
     - type: cosine_accuracy
-      value: 0.8060221076011658
+      value: 0.8116205334663391
       name: Cosine Accuracy
 ---
 
@@ -171,7 +181,7 @@ You can finetune this model on your own dataset.
 
 | Metric              | all-nli-eval | all-nli-test |
 |:--------------------|:-------------|:-------------|
-| **cosine_accuracy** | **0.786**    | **0.806**    |
+| **cosine_accuracy** | **0.6211**   | **0.8116**   |
 
 <!--
 ## Bias, Risks and Limitations
@@ -192,7 +202,7 @@ You can finetune this model on your own dataset.
 #### all-nli
 
 * Dataset: [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
-* Size: 10,000 training samples
+* Size: 1,000 training samples
 * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
 * Approximate statistics based on the first 1000 samples:
   |         | anchor                                                                            | positive                                                                          | negative                                                                         |
@@ -370,17 +380,22 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-| Epoch | Step | Training Loss | Validation Loss | all-nli-eval_cosine_accuracy | all-nli-test_cosine_accuracy |
-|:-----:|:----:|:-------------:|:---------------:|:----------------------------:|:----------------------------:|
-| -1    | -1   | -             | -               | 0.6211                       | -                            |
-| 0.16  | 100  | 1.7157        | 0.7149          | 0.8109                       | -                            |
-| 0.32  | 200  | 0.831         | 0.7081          | 0.8164                       | -                            |
-| 0.48  | 300  | 0.7266        | 0.8863          | 0.8056                       | -                            |
-| 0.64  | 400  | 0.6932        | 1.0048          | 0.7942                       | -                            |
-| 0.8   | 500  | 0.5364        | 0.9695          | 0.7852                       | -                            |
-| 0.96  | 600  | 0.3202        | 0.9368          | 0.7860                       | -                            |
-| -1    | -1   | -             | -               | -                            | 0.8060                       |
-
+| Epoch | Step | all-nli-eval_cosine_accuracy | all-nli-test_cosine_accuracy |
+|:-----:|:----:|:----------------------------:|:----------------------------:|
+| -1    | -1   | 0.6211                       | 0.8116                       |
+
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.000 kWh
+- **Carbon Emitted**: 0.000 kg of CO2
+- **Hours Used**: 0.02 hours
+
+### Training Hardware
+- **On Cloud**: No
+- **GPU Model**: Apple M4
+- **CPU Model**: Apple M4
+- **RAM Size**: 24.00 GB
 
 ### Framework Versions
 - Python: 3.12.4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2d3e226416df060d8221227a5beaaf77dd7ca6f690859f914d91e790f25695b
+oid sha256:876e98ba961ccbb0b15e849ece50e7802b9ae9d2226f48813367d94455a9d5af
 size 437967672