gglabs/stt-turbo-1226-v1

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the custom dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1651
+- Loss: 0.8044
 
 ## Model description
 
@@ -44,23 +44,14 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10
-- training_steps: 100
+- training_steps: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.5394        | 0.1471 | 10   | 0.8112          |
-| 0.1056        | 0.2941 | 20   | 0.4434          |
-| 0.0545        | 0.4412 | 30   | 0.3495          |
-| 0.0352        | 0.5882 | 40   | 0.2854          |
-| 0.0407        | 0.7353 | 50   | 0.2502          |
-| 0.0349        | 0.8824 | 60   | 0.2219          |
-| 0.0272        | 1.0294 | 70   | 0.1950          |
-| 0.0214        | 1.1765 | 80   | 0.1786          |
-| 0.0236        | 1.3235 | 90   | 0.1688          |
-| 0.0204        | 1.4706 | 100  | 0.1651          |
+| 0.5435        | 0.1471 | 10   | 0.8044          |
 
 
 ### Framework versions

adapter_config.json

@@ -26,8 +26,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35618e77fd82abdbbd155bac2ef0fa381decf5e5e79cabf363d278de03900312
+oid sha256:3c6f2fa49fd9830f42bd3b5d430c1e3bad945b56ab2d72b7272dd2528e0a3c5a
 size 26237160

runs/Dec26_09-25-48_gglabs-a6000/events.out.tfevents.1735223148.gglabs-a6000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3acc4080124831b13e33f1c0bdef47e89f7e1c6c6604992083a60542b07d874
+size 7228

runs/Dec26_09-28-45_gglabs-a6000/events.out.tfevents.1735223325.gglabs-a6000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae60274ea54c49b6aa36eabd1d0b3f8c62fe842b0a65ae4d502dd9ec47c2be0e
+size 7102

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c7b5bb3cab18ae3dd06be1f551255d4039899380c6e06e424e797199854580d
+oid sha256:f28442e5c332ec01ed05c41960b93e9a1128580b42672fd6bc64bc9d4d79a902
 size 5496