End of training

README.md

@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3091
-- F1 Topic: 0.9267
-- F1 Sentiment: 0.9054
-- F1 Macro Avg: 0.9160
+- Loss: 0.2356
+- F1 Topic: 0.9113
+- F1 Sentiment: 0.8898
+- F1 Macro Avg: 0.9005
 
 ## Model description
 
@@ -54,14 +54,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1 Topic | F1 Sentiment | F1 Macro Avg |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------------:|:------------:|
-| 1.0405        | 1.0   | 98   | 0.5945          | 0.7469   | 0.8107       | 0.7788       |
-| 0.4667        | 2.0   | 196  | 0.2880          | 0.8879   | 0.8779       | 0.8829       |
-| 0.2356        | 3.0   | 294  | 0.2474          | 0.9179   | 0.8851       | 0.9015       |
-| 0.158         | 4.0   | 392  | 0.2425          | 0.9250   | 0.8873       | 0.9062       |
-| 0.1171        | 5.0   | 490  | 0.2999          | 0.9236   | 0.9083       | 0.9160       |
-| 0.0779        | 6.0   | 588  | 0.2869          | 0.9264   | 0.8896       | 0.9080       |
-| 0.0702        | 7.0   | 686  | 0.2964          | 0.9300   | 0.9060       | 0.9180       |
-| 0.071         | 8.0   | 784  | 0.3091          | 0.9267   | 0.9054       | 0.9160       |
+| 0.9732        | 1.0   | 148  | 0.4898          | 0.7662   | 0.7817       | 0.7740       |
+| 0.3646        | 2.0   | 296  | 0.2792          | 0.8826   | 0.8688       | 0.8757       |
+| 0.2033        | 3.0   | 444  | 0.2304          | 0.9078   | 0.8870       | 0.8974       |
+| 0.1546        | 4.0   | 592  | 0.2356          | 0.9113   | 0.8898       | 0.9005       |
 
 
 ### Framework versions

classifier.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6302e73e2c506c64be31e4e249ee1291c0c9d9d74641499ccc51c9fa464bc474
-size 34282
+oid sha256:d522922703cc1f3dbdd75dddd2cbce3d627fb7922e1e6bb849a3c9d94d7bee28
+size 42474

config_labels.json

@@ -1 +1 @@
-{"topic_labels": ["Eau - Gestion \u00e9conome de l'eau", "Eau - R\u00e9cup\u00e9ration de l'eau", "Eau - Sensibilisation aux usages de l'eau", "Eau - Traitement de l'eau", "Eau - \u00c9quitabilit\u00e9 des ressources"], "sentiment_labels": ["negative", "neutral", "positive"], "num_topic_labels": 5, "num_sentiment_labels": 3}
+{"topic_labels": ["Aucun th\u00e8me", "Eau - Gestion \u00e9conome de l'eau", "Eau - R\u00e9cup\u00e9ration de l'eau", "Eau - Sensibilisation aux usages de l'eau", "Eau - Traitement de l'eau", "Eau - \u00c9quitabilit\u00e9 des ressources"], "sentiment_labels": ["Aucun sentiment", "negative", "neutral", "positive"], "num_topic_labels": 6, "num_sentiment_labels": 4}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f83820ed7d4e1052b74aa0f8e20af7d9b7a5d4cb937bfa82c142e4a2f657150
-size 2239642104
+oid sha256:7a2de7a3750c386f86520a754cd8db00b11dc1fd2c6617e4d774c8fa402931f0
+size 2239650304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b097793ab9078f7c85aae762d5e15d7049ded404c1e2b57e34ca7982d50dc7
+oid sha256:92aca0d2003529f6eadf23b675eb65f6971f19322d1ee3e6a47acf7d54d4056a
 size 5368