Training complete

README.md

@@ -9,11 +9,6 @@ metrics:
 model-index:
 - name: relatives_psr_seq
   results: []
-datasets:
-- djamina/relatives_psr
-language:
-- fr
-pipeline_tag: token-classification
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -23,11 +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: 0.6376
-- Precision: 0.6453
-- Recall: 0.2937
-- F1: 0.2919
-- Accuracy: 0.7824
+- Loss: 0.6642
+- Precision: 0.5052
+- Recall: 0.4082
+- F1: 0.4051
+- Accuracy: 0.7670
 
 ## Model description
 
@@ -58,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 44   | 0.7001          | 0.6678    | 0.2208 | 0.2122 | 0.7718   |
-| No log        | 2.0   | 88   | 0.6490          | 0.6596    | 0.2806 | 0.2749 | 0.7818   |
-| No log        | 3.0   | 132  | 0.6615          | 0.5962    | 0.2484 | 0.2518 | 0.7794   |
-| No log        | 4.0   | 176  | 0.6732          | 0.5933    | 0.2792 | 0.2793 | 0.7815   |
-| No log        | 5.0   | 220  | 0.6376          | 0.6453    | 0.2937 | 0.2919 | 0.7824   |
+| No log        | 1.0   | 49   | 0.7285          | 0.7125    | 0.3284 | 0.2862 | 0.7611   |
+| No log        | 2.0   | 98   | 0.6789          | 0.6397    | 0.3400 | 0.3098 | 0.7685   |
+| No log        | 3.0   | 147  | 0.6739          | 0.5247    | 0.3754 | 0.3685 | 0.7672   |
+| No log        | 4.0   | 196  | 0.6650          | 0.4600    | 0.3984 | 0.3886 | 0.7555   |
+| No log        | 5.0   | 245  | 0.6642          | 0.5052    | 0.4082 | 0.4051 | 0.7670   |
 
 
 ### Framework versions
@@ -70,4 +65,4 @@ The following hyperparameters were used during training:
 - Transformers 4.41.2
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.2
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1

config.json

@@ -10,24 +10,24 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6"
+    "0": "O",
+    "1": "B-DET",
+    "2": "I-DET",
+    "3": "B-APPO",
+    "4": "I-APPO",
+    "5": "B-AMBIGUE",
+    "6": "I-AMBIGUE"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5,
-    "LABEL_6": 6
+    "B-AMBIGUE": 5,
+    "B-APPO": 3,
+    "B-DET": 1,
+    "I-AMBIGUE": 6,
+    "I-APPO": 4,
+    "I-DET": 2,
+    "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 sha256:23917d75bb7e5c3c100095ff67d498e71811a71cb0bedb422d8d9ece1b05b944
+oid sha256:e43e3582e825e46dbf3d442815d50a0b22b0da1f8f249d2ea00c849c318041df
 size 1877848852

runs/Jun05_17-39-05_85b7333225dc/events.out.tfevents.1717609183.85b7333225dc.3235.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ec373cd8a6d46dee2e81f7ec83338c2fba30a7a43c3e01fb467194e0040e5f
+size 7710

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 sha256:576df6536ab41938f524c4e8fd8ea4ee16674839fd5f84799eb992fd8d7ccd8d
+oid sha256:0663de823692a0fce5fce313fb6d8a91f3419773b1b568a370170a40090f2ef7
 size 5112