Model save

README.md

@@ -0,0 +1,100 @@
+---
+license: mit
+base_model: FacebookAI/xlm-roberta-large
+tags:
+- generated_from_trainer
+datasets:
+- cnec
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: CNEC1_1_Supertypes_xlm-roberta-large
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: cnec
+      type: cnec
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.8376762067492525
+    - name: Recall
+      type: recall
+      value: 0.879766711529834
+    - name: F1
+      type: f1
+      value: 0.8582056892778994
+    - name: Accuracy
+      type: accuracy
+      value: 0.9616300402045357
+---
+
+<!-- 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. -->
+
+# CNEC1_1_Supertypes_xlm-roberta-large
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the cnec dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2548
+- Precision: 0.8377
+- Recall: 0.8798
+- F1: 0.8582
+- Accuracy: 0.9616
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3769        | 0.85  | 500  | 0.2160          | 0.7075    | 0.8008 | 0.7513 | 0.9428   |
+| 0.1806        | 1.7   | 1000 | 0.1810          | 0.7730    | 0.8466 | 0.8081 | 0.9527   |
+| 0.1218        | 2.56  | 1500 | 0.1958          | 0.7917    | 0.8425 | 0.8163 | 0.9546   |
+| 0.1027        | 3.41  | 2000 | 0.1970          | 0.7919    | 0.8654 | 0.8270 | 0.9557   |
+| 0.0819        | 4.26  | 2500 | 0.1964          | 0.7840    | 0.8546 | 0.8178 | 0.9591   |
+| 0.0594        | 5.11  | 3000 | 0.2186          | 0.8002    | 0.8645 | 0.8311 | 0.9576   |
+| 0.0435        | 5.96  | 3500 | 0.2055          | 0.8171    | 0.8677 | 0.8416 | 0.9597   |
+| 0.0303        | 6.81  | 4000 | 0.2243          | 0.8222    | 0.8816 | 0.8508 | 0.9608   |
+| 0.0259        | 7.67  | 4500 | 0.2335          | 0.8311    | 0.8784 | 0.8541 | 0.9607   |
+| 0.0152        | 8.52  | 5000 | 0.2526          | 0.8315    | 0.8721 | 0.8513 | 0.9603   |
+| 0.0135        | 9.37  | 5500 | 0.2548          | 0.8377    | 0.8798 | 0.8582 | 0.9616   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

runs/Mar05_14-13-34_g10/events.out.tfevents.1709644416.g10.2818507.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f956dc4ef47e75241a97f0935fc1dd86207f629842a106f84ad3628f2d46eae0
-size 12024
+oid sha256:1359a8e2acfd82dda0923607be6ade252b18b7bffca97b1371e6ff0fc57d9eb9
+size 12378