End of training

README.md

@@ -24,7 +24,7 @@ model-index:
       args: default
     metrics:
     - type: wer
-      value: 68.88888888888889
+      value: 20.578778135048232
       name: Wer
 ---
 
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the miosipof/asr_en dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3857
-- Wer: 68.8889
+- Loss: 0.3170
+- Wer: 20.5788
 
 ## Model description
 
@@ -64,45 +64,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 32
-- training_steps: 1024
+- training_steps: 128
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer      |
-|:-------------:|:-------:|:----:|:---------------:|:--------:|
-| 5.6529        | 1.0847  | 32   | 2.0524          | 41.1111  |
-| 1.2225        | 2.1695  | 64   | 0.6093          | 52.0635  |
-| 0.2888        | 3.2542  | 96   | 0.4636          | 48.5714  |
-| 0.1701        | 4.3390  | 128  | 0.4190          | 43.0159  |
-| 0.1729        | 5.4237  | 160  | 0.5561          | 61.9048  |
-| 0.0846        | 6.5085  | 192  | 0.3515          | 57.3016  |
-| 0.0678        | 7.5932  | 224  | 0.3795          | 47.9365  |
-| 0.0578        | 8.6780  | 256  | 0.5905          | 56.9841  |
-| 0.0457        | 9.7627  | 288  | 0.4444          | 73.0159  |
-| 0.0432        | 10.8475 | 320  | 0.5010          | 59.2063  |
-| 0.0407        | 11.9322 | 352  | 0.5758          | 63.4921  |
-| 0.0341        | 13.0169 | 384  | 0.6487          | 50.3175  |
-| 0.0308        | 14.1017 | 416  | 0.4682          | 45.8730  |
-| 0.0304        | 15.1864 | 448  | 0.4518          | 65.5556  |
-| 0.0241        | 16.2712 | 480  | 0.5138          | 64.2857  |
-| 0.029         | 17.3559 | 512  | 0.5460          | 66.5079  |
-| 0.0169        | 18.4407 | 544  | 0.6139          | 64.7619  |
-| 0.0196        | 19.5254 | 576  | 0.6055          | 54.4444  |
-| 0.0148        | 20.6102 | 608  | 0.4502          | 65.7143  |
-| 0.0153        | 21.6949 | 640  | 0.4179          | 81.7460  |
-| 0.0149        | 22.7797 | 672  | 0.4491          | 108.7302 |
-| 0.0188        | 23.8644 | 704  | 0.3885          | 75.3968  |
-| 0.0115        | 24.9492 | 736  | 0.4070          | 182.6984 |
-| 0.0111        | 26.0339 | 768  | 0.4429          | 128.7302 |
-| 0.0124        | 27.1186 | 800  | 0.3827          | 69.2063  |
-| 0.0096        | 28.2034 | 832  | 0.4028          | 70.0     |
-| 0.0121        | 29.2881 | 864  | 0.3651          | 63.8095  |
-| 0.0083        | 30.3729 | 896  | 0.3906          | 66.6667  |
-| 0.0085        | 31.4576 | 928  | 0.3861          | 66.8254  |
-| 0.0092        | 32.5424 | 960  | 0.3834          | 69.6825  |
-| 0.0095        | 33.6271 | 992  | 0.3861          | 68.8889  |
-| 0.007         | 34.7119 | 1024 | 0.3857          | 68.8889  |
+| Training Loss | Epoch  | Step | Validation Loss | Wer      |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 3.8843        | 1.0847 | 32   | 0.8819          | 135.0482 |
+| 0.3624        | 2.1695 | 64   | 0.3312          | 47.1061  |
+| 0.1637        | 3.2542 | 96   | 0.3231          | 22.1865  |
+| 0.0903        | 4.3390 | 128  | 0.3170          | 20.5788  |
 
 
 ### Framework versions

adapter_config.json

@@ -13,18 +13,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 64,
   "lora_dropout": 0.01,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d21652d7d1290ca5032878a69d8081441891ea1b33e81ea630ad9b7e51554c1
-size 18915424
+oid sha256:b63bbc35e54fcb30541cce9b497c111aa017ecc96d2397c9144b6a362e02a942
+size 37789960

runs/Oct03_18-55-20_fd95e0b5707e/events.out.tfevents.1727981760.fd95e0b5707e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6debac184266b65a12afa5fb26fc5a99ef8d9625216dba646b1785a365509411
+size 8267

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d8e304d4a0ab457402ff42f37ff7b96f2986612b0a5cbf51241b59b06eca3bc
+oid sha256:a6a94be65596d06f3b4f2f876507fd3e211278681e82ba9c76d47c2331f1c916
 size 5304