End of training
Browse files- README.md +22 -0
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
|
@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# uaspeech-large-finetune-shorter-evals
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -45,6 +47,26 @@ The following hyperparameters were used during training:
|
|
| 45 |
- lr_scheduler_warmup_steps: 100
|
| 46 |
- training_steps: 1500
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- Transformers 4.45.2
|
|
|
|
| 16 |
# uaspeech-large-finetune-shorter-evals
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.2762
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 47 |
- lr_scheduler_warmup_steps: 100
|
| 48 |
- training_steps: 1500
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 0.316 | 0.0828 | 200 | 0.3907 |
|
| 55 |
+
| 0.2478 | 0.1242 | 300 | 0.3199 |
|
| 56 |
+
| 0.2129 | 0.1656 | 400 | 0.3282 |
|
| 57 |
+
| 0.1667 | 0.2070 | 500 | 0.3194 |
|
| 58 |
+
| 0.1534 | 0.2483 | 600 | 0.3327 |
|
| 59 |
+
| 0.1208 | 0.2897 | 700 | 0.2923 |
|
| 60 |
+
| 0.0987 | 0.3311 | 800 | 0.3048 |
|
| 61 |
+
| 0.103 | 0.3725 | 900 | 0.2841 |
|
| 62 |
+
| 0.0893 | 0.4139 | 1000 | 0.2759 |
|
| 63 |
+
| 0.0757 | 0.4553 | 1100 | 0.2625 |
|
| 64 |
+
| 0.068 | 0.4967 | 1200 | 0.2784 |
|
| 65 |
+
| 0.0608 | 0.5381 | 1300 | 0.2813 |
|
| 66 |
+
| 0.0404 | 0.5795 | 1400 | 0.2739 |
|
| 67 |
+
| 0.0422 | 0.6209 | 1500 | 0.2762 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
### Framework versions
|
| 71 |
|
| 72 |
- Transformers 4.45.2
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4993448880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe1c1f46e6dd8ebfecab1c4c8eb308747accb73dbf6ef0da379b82a8bf395646
|
| 3 |
size 4993448880
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1180663192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:535c3eaa258fc5d82c0cc84dbd72c84cb12c8b8ca34e484d0a408af5592eb2c3
|
| 3 |
size 1180663192
|