Samandards/uzbek-5k-data

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6205
+- Loss: 0.6751
 
 ## Model description
 
@@ -36,8 +36,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.9053        | 1.0   | 86   | 0.7960          |
-| 0.4624        | 2.0   | 172  | 0.6205          |
+| 2.8854        | 1.0   | 43   | 0.8982          |
+| 0.6677        | 2.0   | 86   | 0.6751          |
 
 
 ### Framework versions

adapter_config.json

@@ -23,8 +23,8 @@
   "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 sha256:0c70dc16e421ce9c14edfff25e79a0ba1a9076036582337030091fb959a09e04
+oid sha256:2e8d0e98f1fe2c7a3c6ec140d3dbc0f76dcfc24bf3fd579777c54bc4cb9e81eb
 size 125884424

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee1414c90d40234d4ebd6ad3e96fc3c927ed04e302a0aa52cf54a76b20cf0f41
+oid sha256:ea9e4aa37e9beaab37d3a185f5b7bcfcfa423d2b7db037acee2cb08c42af18da
 size 5304