Training in progress, epoch 1

README.md

@@ -0,0 +1,48 @@
+---
+library_name: transformers
+base_model: xaviergillard/brabrant-xvii-ner
+tags:
+- generated_from_trainer
+model-index:
+- name: brabrant-xvii-ner
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# brabrant-xvii-ner
+
+This model is a fine-tuned version of [xaviergillard/brabrant-xvii-ner](https://huggingface.co/xaviergillard/brabrant-xvii-ner) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.1.2
+- Datasets 3.3.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "xaviergillard/xlm-roberta-large-vieille-france",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "-100": "IGN",
+    "0": "B-PERS",
+    "1": "I-PERS",
+    "2": "B-LOC",
+    "3": "I-LOC",
+    "4": "B-DATE",
+    "5": "I-DATE",
+    "6": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-DATE": 4,
+    "B-LOC": 2,
+    "B-PERS": 0,
+    "I-DATE": 5,
+    "I-LOC": 3,
+    "I-PERS": 1,
+    "IGN": -100,
+    "O": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

metrics.json

@@ -0,0 +1 @@
+{"valid_loss": 0.1110556498169899, "valid_model_preparation_time": 0.0042, "valid_precision": 0.7115384615384616, "valid_recall": 0.7665745856353591, "valid_f1": 0.7380319148936171, "valid_runtime": 5.2226, "valid_samples_per_second": 36.763, "valid_steps_per_second": 1.149}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:037e8f72c28d9e46ec218646afbc855be80cf7ff4a6c90a8e0159055ac805c83
+size 2235444656

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e354e1f208b4bbb3e011ac0936290ca38a20f8b60ce91ba3d25d5685367c0955
+size 5432