Training in progress, epoch 1

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: Geotrend/bert-base-th-cased
+base_model: google-bert/bert-base-multilingual-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -10,22 +10,22 @@ metrics:
 - precision
 - recall
 model-index:
-- name: bert-base-th-cased-intent-booking
+- name: bert-base-multilingual-cased-intent-booking
   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. -->
 
-# bert-base-th-cased-intent-booking
+# bert-base-multilingual-cased-intent-booking
 
-This model is a fine-tuned version of [Geotrend/bert-base-th-cased](https://huggingface.co/Geotrend/bert-base-th-cased) on an unknown dataset.
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3126
-- Accuracy: 0.9144
-- F1: 0.9133
-- Precision: 0.9257
-- Recall: 0.9144
+- Loss: 0.2607
+- Accuracy: 0.9234
+- F1: 0.9203
+- Precision: 0.9338
+- Recall: 0.9234
 
 ## Model description
 
@@ -51,17 +51,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 64
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 1.9427        | 1.0   | 65   | 0.7129          | 0.8964   | 0.8947 | 0.9055    | 0.8964 |
-| 0.5012        | 2.0   | 130  | 0.2128          | 0.9505   | 0.9501 | 0.9552    | 0.9505 |
-| 0.2135        | 3.0   | 195  | 0.4644          | 0.8829   | 0.8812 | 0.9208    | 0.8829 |
-| 0.1301        | 4.0   | 260  | 0.1812          | 0.9459   | 0.9463 | 0.9543    | 0.9459 |
-| 0.0785        | 5.0   | 325  | 0.2287          | 0.9459   | 0.9462 | 0.9517    | 0.9459 |
+| 2.1492        | 1.0   | 65   | 1.4697          | 0.6982   | 0.6538 | 0.7798    | 0.6982 |
+| 0.778         | 2.0   | 130  | 0.3384          | 0.9234   | 0.9247 | 0.9330    | 0.9234 |
+| 0.2369        | 3.0   | 195  | 0.2147          | 0.9414   | 0.9421 | 0.9513    | 0.9414 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd7c8907af381ad37b7bce93b28c044ed8f9e11d7e99aa6e8c3785b53f270bf
+oid sha256:452a0412982742cfb5f04483cafc470db04b417ca80dac8cb890027c4d6d9989
 size 370350032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4781e599d8d3c9e02fcd4c1b919705def427445bd281fdb22eac4325cb23cf4
+oid sha256:ad4e9a78545ce6b81b8495f01b419f538a06a7ec9143abe160a7bc7b69d6fd72
 size 5240