Training complete

README.md

@@ -9,18 +9,6 @@ metrics:
 model-index:
 - name: relatives_psr
   results: []
-widget:
-- text: >-
-    Rappelez-vous que la seule loi qui compte, la grande loi de la cité, la
-    grande loi de la République est celle qui est forgée grâce au débat et au
-    dissentiment, non à la pensée unique.
-- text: >-
-    Le Parlement prendra toute sa place dans l'effort de redressement du pays, un Parlement qui mesure à sa juste valeur l'attente de l'opinion et qui, dans le cadre de la séparation des pouvoirs, poursuivra sa rénovation
-language:
-- fr
-pipeline_tag: token-classification
-datasets:
-- djamina/relatives_psr
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0554
-- Precision: 0.7125
-- Recall: 0.4765
-- F1: 0.4668
-- Accuracy: 0.9791
+- Loss: 0.0536
+- Precision: 0.6640
+- Recall: 0.6450
+- F1: 0.6483
+- Accuracy: 0.9804
 
 ## Model description
 
@@ -65,16 +53,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 44   | 0.0591          | 0.8332    | 0.4040 | 0.3670 | 0.9764   |
-| No log        | 2.0   | 88   | 0.0541          | 0.7191    | 0.4742 | 0.4308 | 0.9788   |
-| No log        | 3.0   | 132  | 0.0562          | 0.7176    | 0.4238 | 0.4357 | 0.9776   |
-| No log        | 4.0   | 176  | 0.0544          | 0.7158    | 0.4467 | 0.4316 | 0.9794   |
-| No log        | 5.0   | 220  | 0.0554          | 0.7125    | 0.4765 | 0.4668 | 0.9791   |
+| No log        | 1.0   | 49   | 0.0602          | 0.7398    | 0.6309 | 0.5692 | 0.9769   |
+| No log        | 2.0   | 98   | 0.0583          | 0.6821    | 0.6304 | 0.5952 | 0.9789   |
+| No log        | 3.0   | 147  | 0.0584          | 0.6604    | 0.6098 | 0.5610 | 0.9776   |
+| No log        | 4.0   | 196  | 0.0564          | 0.5868    | 0.6107 | 0.5981 | 0.9761   |
+| No log        | 5.0   | 245  | 0.0536          | 0.6640    | 0.6450 | 0.6483 | 0.9804   |
 
 
 ### Framework versions
 
 - Transformers 4.41.2
 - Pytorch 2.3.0+cu121
-- Datasets 2.19.1
-- Tokenizers 0.19.1
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -18,10 +18,10 @@
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "O": 0,
-    "DET": 1,
+    "AMBIGUE": 3,
     "APPO": 2,
-    "AMBIGUE": 3
+    "DET": 1,
+    "O": 0
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4672b5549ec8d9f7737f1b8a4f16ee8cf0af5b7d3b2feeeb9b0ed15ab335069b
+oid sha256:c47dc4f39cc656b60e56d0eea10078a6c4674cd5d982826530df2ade940ec43c
 size 1877839624

runs/Jun04_23-27-50_eefaff9f758d/events.out.tfevents.1717543689.eefaff9f758d.4259.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22fb096491073b9e0bdaa26f0e60ae488fd9607d29ed8b46d43bd7859594ceb
+size 7574

sentencepiece.bpe.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
-size 810912
+oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
+size 808767

tokenizer_config.json

@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "3": {
       "content": "<unk>",
       "lstrip": false,
       "normalized": false,
@@ -32,6 +32,14 @@
       "single_word": false,
       "special": true
     },
+    "4": {
+      "content": "<unk>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
     "5": {
       "content": "<s>",
       "lstrip": false,
@@ -55,14 +63,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32005": {
-      "content": "<unk>NOTUSED",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [
@@ -75,9 +75,10 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "sp_model_kwargs": {},
   "tokenizer_class": "CamembertTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88a7977eb6a316e1efca6956faede7efdb7615bd6d16ed16f95b95e9e173b19
+oid sha256:dd2109481ecfe42e2134e8db5c5cc8b16f0d22287b04bb90d0095e1a660e425c
 size 5112