Training completed!

README.md

@@ -1,27 +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
-      config: PAN-X.fr
-      split: train
-      args: PAN-X.fr
-    metrics:
-    - name: F1
-      type: f1
-      value: 0.8366320026836633
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,10 +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: 0.3026
-- F1: 0.8366
+- Loss: 0.2750
+- F1: 0.8495
 
 ## Model description
 
@@ -52,28 +38,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 24
+- eval_batch_size: 24
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
-- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 1.0   | 286  | 0.3632          | 0.7838 |
-| No log        | 2.0   | 572  | 0.3108          | 0.8160 |
-| No log        | 3.0   | 858  | 0.3026          | 0.8366 |
+| 0.5647        | 1.0   | 191  | 0.3242          | 0.7728 |
+| 0.2671        | 2.0   | 382  | 0.2672          | 0.8202 |
+| 0.1744        | 3.0   | 573  | 0.2750          | 0.8495 |
 
 
 ### Framework versions
 
-- Transformers 4.25.1
-- Pytorch 1.13.0+cu116
-- Datasets 2.8.0
-- Tokenizers 0.13.2
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -40,7 +40,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.25.1",
+  "transformers_version": "4.38.2",
   "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:f4b55830c5129ad0002e3e3d4274be61516b188f4caf925b7a55b2a9c38d58c8
+size 1109860880

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
-size 17082758
+oid sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
+size 17082854

tokenizer_config.json

@@ -1,20 +1,54 @@
 {
+  "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": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "name_or_path": "xlm-roberta-base",
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "special_tokens_map_file": null,
   "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c0d1a09c36e34cfe6692f62527a8454ad39f35eec3acc68e8fb760ed4cb42e
-size 3515
+oid sha256:9bcd026dcc32925a68f495a3bd70fd18901a2b789e20df994b9783b9bb32daf8
+size 4984