Training completed!

README.md

@@ -16,13 +16,13 @@ model-index:
     dataset:
       name: xtreme
       type: xtreme
-      config: PAN-X.de
+      config: PAN-X.fr
       split: validation
-      args: PAN-X.de
+      args: PAN-X.fr
     metrics:
     - name: F1
       type: f1
-      value: 0.867219445706497
+      value: 0.19409162266305124
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1343
-- F1: 0.8672
+- Loss: 1.0251
+- F1: 0.1941
 
 ## Model description
 
@@ -64,9 +64,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.2584        | 1.0   | 525  | 0.1500          | 0.8296 |
-| 0.1253        | 2.0   | 1050 | 0.1360          | 0.8551 |
-| 0.0817        | 3.0   | 1575 | 0.1343          | 0.8672 |
+| 1.8089        | 1.0   | 11   | 1.3639          | 0.1455 |
+| 1.2489        | 2.0   | 22   | 1.1180          | 0.1487 |
+| 1.0743        | 3.0   | 33   | 1.0251          | 0.1941 |
 
 
 ### Framework versions

config.json

@@ -11,6 +11,7 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
+    "-100": "IGN",
     "0": "O",
     "1": "B-PER",
     "2": "I-PER",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a57d63ac8442e951034dc737f0f659444e4eca8fd0fe71e6f4b1569a875a4f
-size 1109899305
+oid sha256:c7afa08ff690742bb8695bdbd3cd4096928ded3f1e14abb7cd44b6a02d826228
+size 1109902377

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
-size 17082660
+oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
+size 17082758

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c4c8b6c3345568927425358b3e9500e0ec02ce81ce819288321437e869c820
+oid sha256:a109d49bc9a90fc1c7ecd915474aa7fd83f206a41325b3b1758cba941eeeab84
 size 4091