Training completed!

README.md

@@ -1,25 +1,13 @@
 ---
 license: mit
+base_model: xlm-roberta-base
 tags:
 - generated_from_trainer
-datasets:
-- xtreme
 metrics:
 - f1
 model-index:
 - name: xlm-roberta-base-finetuned-panx-fr
-  results:
-  - task:
-      name: Token Classification
-      type: token-classification
-    dataset:
-      name: xtreme
-      type: xtreme
-      args: PAN-X.fr
-    metrics:
-    - name: F1
-      type: f1
-      value: 0.8133891213389121
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # xlm-roberta-base-finetuned-panx-fr
 
-This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3018
-- F1: 0.8134
+- Loss: 0.2842
+- F1: 0.8406
 
 ## Model description
 
@@ -61,14 +49,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.7716        | 1.0   | 96   | 0.3991          | 0.7408 |
-| 0.3348        | 2.0   | 192  | 0.3204          | 0.7915 |
-| 0.2228        | 3.0   | 288  | 0.3018          | 0.8134 |
+| 0.5754        | 1.0   | 191  | 0.3338          | 0.7683 |
+| 0.2626        | 2.0   | 382  | 0.2696          | 0.8190 |
+| 0.1788        | 3.0   | 573  | 0.2842          | 0.8406 |
 
 
 ### Framework versions
 
-- Transformers 4.16.2
+- Transformers 4.41.2
 - Pytorch 2.3.0+cu121
-- Datasets 1.16.1
+- Datasets 2.20.0
 - Tokenizers 0.19.1

config.json

@@ -40,7 +40,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.16.2",
+  "transformers_version": "4.41.2",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e09f44383d10230547ea233cbc46d85722aed9c73fc9e39aad936c209b2c18f
+size 1109860880

special_tokens_map.json

@@ -1 +1,15 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "special": true}}
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -1 +1,54 @@
-{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": false, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139dcda634a5170a082d43cc16fd11aaadd624eb0dcb4ce993b6ed4a9bee4c9b
-size 3576
+oid sha256:01feca5a80766d41001e355bc7f1900a79abcb725897c8d25ca647281dfca5b9
+size 5176