Model save

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: google/umt5-small
+base_model: urarik/t5-asr-CV16
 tags:
 - generated_from_trainer
 metrics:
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # t5-asr-CV16
 
-This model is a fine-tuned version of [google/umt5-small](https://huggingface.co/google/umt5-small) on an unknown dataset.
+This model is a fine-tuned version of [urarik/t5-asr-CV16](https://huggingface.co/urarik/t5-asr-CV16) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 20.7094
-- Wer: 3.7797
+- Loss: 17.9832
+- Wer: 3.9749
 
 ## Model description
 
@@ -38,7 +38,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
+- learning_rate: 0.0001
 - train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
@@ -47,22 +47,23 @@ The following hyperparameters were used during training:
 - optimizer: Use paged_lion_8bit and the args are:
 No additional optimizer arguments
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.08333333333333333
-- num_epochs: 3
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
-| 62.4704       | 0.3279 | 10   | 15.1946         | 3.7820 |
-| 60.6268       | 0.6557 | 20   | 16.9860         | 3.7589 |
-| 58.4451       | 0.9836 | 30   | 18.5103         | 4.0257 |
-| 53.5537       | 1.2951 | 40   | 19.5617         | 4.2520 |
-| 54.9241       | 1.6230 | 50   | 20.1924         | 4.1488 |
-| 53.9461       | 1.9508 | 60   | 20.4946         | 3.9207 |
-| 50.5189       | 2.2623 | 70   | 20.6034         | 3.8890 |
-| 52.8163       | 2.5902 | 80   | 20.6852         | 3.8316 |
-| 52.9224       | 2.9180 | 90   | 20.7094         | 3.7797 |
+| 61.3853       | 0.4918 | 15   | 15.5590         | 3.7388 |
+| 60.7398       | 0.9836 | 30   | 16.0317         | 3.8106 |
+| 57.146        | 1.4590 | 45   | 16.5961         | 3.8483 |
+| 59.4602       | 1.9508 | 60   | 17.0526         | 3.7376 |
+| 56.0474       | 2.4262 | 75   | 17.4439         | 3.9441 |
+| 58.6886       | 2.9180 | 90   | 17.6277         | 3.7956 |
+| 55.4761       | 3.3934 | 105  | 17.8121         | 3.9299 |
+| 58.2042       | 3.8852 | 120  | 17.8014         | 3.9418 |
+| 55.1715       | 4.3607 | 135  | 17.8874         | 4.0185 |
+| 58.111        | 4.8525 | 150  | 17.9832         | 3.9749 |
 
 
 ### Framework versions

runs/Feb10_19-04-32_c0e556c53359/events.out.tfevents.1739214274.c0e556c53359.18.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cc823ffe86c9abf73626acbbb013b7b8a72db7c336fec8bacb868dcdd85bc5
-size 6143
+oid sha256:4930d66a2f7b89a93af759bb746fe9b7fc1cc7e9af82e0fe06d2349923ccc300
+size 12227