End of training

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: xml-roberta-large-v3
+  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. -->
+
+# xml-roberta-large-v3
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0792
+- Precision: 0.9448
+- Recall: 0.9726
+- F1: 0.9585
+- Accuracy: 0.9806
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 48
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3722        | 1.0   | 204  | 0.2039          | 0.8490    | 0.8680 | 0.8584 | 0.9440   |
+| 0.1353        | 2.0   | 408  | 0.0930          | 0.9324    | 0.9626 | 0.9473 | 0.9759   |
+| 0.0969        | 3.0   | 612  | 0.0869          | 0.9407    | 0.9684 | 0.9543 | 0.9776   |
+| 0.0785        | 4.0   | 816  | 0.0818          | 0.9411    | 0.9729 | 0.9568 | 0.9793   |
+| 0.0498        | 5.0   | 1020 | 0.0792          | 0.9448    | 0.9726 | 0.9585 | 0.9806   |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "xlm-roberta-large",
+  "_name_or_path": "/content/biobert-ner-training",
   "architectures": [
     "XLMRobertaForTokenClassification"
   ],

runs/Nov26_09-54-55_ae990c00c960/events.out.tfevents.1732614897.ae990c00c960.261.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:343d75882b9b05972e3eb02f6bde49260712bdd9f852d41a14c35db57958cab5
-size 12607
+oid sha256:650a3020768a8a317ad3e2e0cabbe8f61c903d85b77bc342c9ccc7c2fd55eff1
+size 13433