End of training

README.md

@@ -18,9 +18,6 @@ should probably proofread and complete it, then remove this comment. -->
 # Common Voice 16 - Guarani8
 
 This model is a fine-tuned version of [glob-asr/wav2vec2-large-xls-r-300m-guarani-small](https://huggingface.co/glob-asr/wav2vec2-large-xls-r-300m-guarani-small) on the Common Voice 16 dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3202
-- Cer: 7.2954
 
 ## Model description
 
@@ -45,19 +42,12 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
-- lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- lr_scheduler_warmup_steps: 1
+- training_steps: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Cer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.4174        | 1.01  | 100  | 0.3535          | 8.1385 |
-| 0.3411        | 2.02  | 200  | 0.3387          | 7.8574 |
-| 0.2905        | 3.03  | 300  | 0.3278          | 7.6076 |
-| 0.2591        | 4.04  | 400  | 0.3214          | 7.3734 |
-| 0.251         | 5.05  | 500  | 0.3202          | 7.2954 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda199778771c0fdf0265eb4b5518e5089593dbc0a3ac2c83e72dd179fa5c6bc
+oid sha256:d7f57b7561a07d92c5d9ac68eb8b7a84c26f73542ea6660f8baf8c49298dd2df
 size 1261996080

runs/Mar12_21-56-38_17f88833bc48/events.out.tfevents.1710280599.17f88833bc48.52926.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ccb37161b80cb1203686da09e215325ca9c4ae03b9f1a6c8ea8d442197d4a3
+size 6560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e71adfe03c9a54667966014f76d7c5ddb0fa892e4824805c4f3b0f51156d82a6
+oid sha256:2fb79b9b5b356dc78e12e10811a378caf0ec14a03187db6d2a5bae44f94e146a
 size 5048