End of training

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: transformers
-base_model: microsoft/infoxlm-base
+base_model: microsoft/infoxlm-large
 tags:
 - generated_from_trainer
 metrics:
@@ -9,22 +9,22 @@ metrics:
 - precision
 - recall
 model-index:
-- name: vp-infoxlm-base-dsc
+- name: vp-infoxlm-large-dsc
   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. -->
 
-# vp-infoxlm-base-dsc
+# vp-infoxlm-large-dsc
 
-This model is a fine-tuned version of [microsoft/infoxlm-base](https://huggingface.co/microsoft/infoxlm-base) on the None dataset.
+This model is a fine-tuned version of [microsoft/infoxlm-large](https://huggingface.co/microsoft/infoxlm-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4642
-- Accuracy: 0.8251
-- F1: 0.8249
-- Precision: 0.8259
-- Recall: 0.8251
+- Loss: 0.6113
+- Accuracy: 0.8706
+- F1: 0.8705
+- Precision: 0.8713
+- Recall: 0.8706
 
 ## Model description
 
@@ -44,8 +44,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -54,13 +54,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.9971        | 1.0   | 1590 | 0.8708          | 0.5664   | 0.5565 | 0.6042    | 0.5664 |
-| 0.7175        | 2.0   | 3180 | 0.5943          | 0.7631   | 0.7626 | 0.7713    | 0.7631 |
-| 0.5942        | 3.0   | 4770 | 0.5007          | 0.8069   | 0.8069 | 0.8075    | 0.8069 |
-| 0.4981        | 4.0   | 6360 | 0.4676          | 0.8188   | 0.8182 | 0.8218    | 0.8188 |
-| 0.4669        | 5.0   | 7950 | 0.4642          | 0.8251   | 0.8249 | 0.8259    | 0.8251 |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.8771        | 1.0   | 3180  | 0.8099          | 0.6890   | 0.6914 | 0.7003    | 0.6890 |
+| 0.5911        | 2.0   | 6360  | 0.5717          | 0.8014   | 0.8007 | 0.8107    | 0.8014 |
+| 0.4608        | 3.0   | 9540  | 0.5323          | 0.8442   | 0.8442 | 0.8449    | 0.8442 |
+| 0.407         | 4.0   | 12720 | 0.5047          | 0.8680   | 0.8679 | 0.8683    | 0.8680 |
+| 0.3372        | 5.0   | 15900 | 0.6113          | 0.8706   | 0.8705 | 0.8713    | 0.8706 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5762f19428c6ac10284c7800f392c10ae1ea86e48bba89b771f08021bc9400c3
+oid sha256:0ee8ea16aa227918316176fb62f6471edda8613b0933373abda285efaaf3aec9
 size 2239622772