belisards/ia_m1_v1

README.md

@@ -4,6 +4,11 @@ license: mit
 base_model: belisards/congretimbau3
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- f1
+- recall
+- precision
 model-index:
 - name: modelos
   results: []
@@ -16,16 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [belisards/congretimbau3](https://huggingface.co/belisards/congretimbau3) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.0444
-- eval_accuracy: 0.7976
-- eval_f1: 0.7873
-- eval_recall: 0.7721
-- eval_precision: 0.8096
-- eval_runtime: 1.8041
-- eval_samples_per_second: 93.121
-- eval_steps_per_second: 3.326
-- epoch: 3.3590
-- step: 131
+- Loss: 0.6549
+- Accuracy: 0.7857
+- F1: 0.7762
+- Recall: 0.7635
+- Precision: 0.8003
 
 ## Model description
 
@@ -50,9 +50,22 @@ The following hyperparameters were used during training:
 - seed: 5151
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 150
+- lr_scheduler_warmup_steps: 100
 - num_epochs: 10
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Recall | Precision |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
+| 1.8909        | 1.4286 | 50   | 1.8932          | 0.3214   | 0.0541 | 0.1111 | 0.0357    |
+| 1.2159        | 2.8571 | 100  | 1.1457          | 0.6786   | 0.5282 | 0.5134 | 0.6288    |
+| 0.4356        | 4.2857 | 150  | 0.6699          | 0.7857   | 0.7612 | 0.7466 | 0.8026    |
+| 0.2795        | 5.7143 | 200  | 0.5790          | 0.7857   | 0.7803 | 0.7777 | 0.7890    |
+| 0.1434        | 7.1429 | 250  | 0.6343          | 0.7679   | 0.7257 | 0.7028 | 0.7958    |
+| 0.0907        | 8.5714 | 300  | 0.6382          | 0.7946   | 0.7561 | 0.7409 | 0.8181    |
+| 0.056         | 10.0   | 350  | 0.6453          | 0.8036   | 0.7874 | 0.7770 | 0.8175    |
+
+
 ### Framework versions
 
 - Transformers 4.45.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c8317cc692aeb690197185da4c097a66fea020d59faf5dd2a1120c9137547b
+oid sha256:5771ea19ecef8b5c60c936209d5117917bb8b6870c4ed223e0f2325597187273
 size 1337669572

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e6ae08ab82d6b68328ff7198ab1dbc5e2c7ea89c40905af49f4fd3820c16bfd
-size 5304
+oid sha256:4797d5bf6b58135626b4722c2d423f9e9724462cd0b4e8f75b6786dbd5a72964
+size 5240