tp_llm

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: Jerome-Dej/camembert_classif
+base_model: camembert/camembert-base-wikipedia-4gb
 tags:
 - generated_from_trainer
 metrics:
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # camembert_classif_rte
 
-This model is a fine-tuned version of [Jerome-Dej/camembert_classif](https://huggingface.co/Jerome-Dej/camembert_classif) on an unknown dataset.
+This model is a fine-tuned version of [camembert/camembert-base-wikipedia-4gb](https://huggingface.co/camembert/camembert-base-wikipedia-4gb) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2162
-- Accuracy: 0.9644
+- Loss: 0.2278
+- Accuracy: 0.9653
 
 ## Model description
 
@@ -42,15 +42,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.0665        | 1.0   | 16000 | 0.2217          | 0.9574   |
-| 0.1007        | 2.0   | 32000 | 0.1761          | 0.962    |
-| 0.0412        | 3.0   | 48000 | 0.2162          | 0.9644   |
+| 0.163         | 1.0   | 16000 | 0.1371          | 0.9597   |
+| 0.1374        | 2.0   | 32000 | 0.1505          | 0.9633   |
+| 0.0877        | 3.0   | 48000 | 0.1622          | 0.9642   |
+| 0.0491        | 4.0   | 64000 | 0.1940          | 0.9644   |
+| 0.0143        | 5.0   | 80000 | 0.2278          | 0.9653   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5543a3ae2f0026659979dd40ebc50e0c6c65551b22fd100d941fe537a4d0a8a1
+oid sha256:e74b7e5b9f70b95d49a4cdae1df05c255ff1aa2d1e22ef772b77f790214da221
 size 442518104