End of training

README.md

@@ -24,7 +24,7 @@ model-index:
  args: default
  metrics:
  - type: wer
- value: 95.578231292517
+ value: 106.7911714770798
  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: 0.5910
-- Wer: 95.5782
+- Loss: 3.9473
+- Wer: 106.7912
 
 ## Model description
 
@@ -55,26 +55,38 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
-- train_batch_size: 16
-- eval_batch_size: 8
+- learning_rate: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 2
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 64
-- training_steps: 512
+- lr_scheduler_warmup_steps: 128
+- training_steps: 1024
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer |
-|:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 1.6117 | 8.6780 | 128 | 0.8544 | 68.3673 |
-| 0.0478 | 17.3559 | 256 | 0.7632 | 62.0748 |
-| 0.0213 | 26.0339 | 384 | 1.0346 | 66.8367 |
-| 0.0134 | 34.7119 | 512 | 0.5910 | 95.5782 |
+| Training Loss | Epoch | Step | Validation Loss | Wer |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| 7.4432 | 4.2667 | 64 | 7.9570 | 167.9117 |
+| 6.9871 | 8.5333 | 128 | 7.0858 | 167.5722 |
+| 6.1972 | 12.8 | 192 | 6.3333 | 205.2632 |
+| 5.9006 | 17.0667 | 256 | 6.0843 | 203.5654 |
+| 5.61 | 21.3333 | 320 | 5.8153 | 168.7606 |
+| 5.2344 | 25.6 | 384 | 5.4746 | 168.0815 |
+| 4.8067 | 29.8667 | 448 | 5.0913 | 168.2513 |
+| 4.3927 | 34.1333 | 512 | 4.7586 | 201.5280 |
+| 4.1103 | 38.4 | 576 | 4.5158 | 164.5161 |
+| 3.8975 | 42.6667 | 640 | 4.3460 | 108.4890 |
+| 3.7471 | 46.9333 | 704 | 4.2178 | 109.1681 |
+| 3.6146 | 51.2 | 768 | 4.1226 | 108.3192 |
+| 3.53 | 55.4667 | 832 | 4.0471 | 107.9796 |
+| 3.4579 | 59.7333 | 896 | 3.9927 | 107.4703 |
+| 3.4061 | 64.0 | 960 | 3.9594 | 106.9610 |
+| 3.3577 | 68.2667 | 1024 | 3.9473 | 106.7912 |
 
 
 ### Framework versions

adapter_config.json

@@ -13,18 +13,18 @@
  "layers_pattern": null,
  "layers_to_transform": null,
  "loftq_config": {},
- "lora_alpha": 32,
+ "lora_alpha": 16,
  "lora_dropout": 0.01,
  "megatron_config": null,
  "megatron_core": "megatron.core",
  "modules_to_save": null,
  "peft_type": "LORA",
- "r": 32,
+ "r": 16,
  "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 sha256:14bb6b76a7f312a2d545d14d635e6f4ba449b3f63163c1144a019c47528c526d
-size 37789960
+oid sha256:1aeb882533eba03b542ed0bb46eb9db32b7dc782bd6fee502cc8a8fc6d583cf9
+size 18915424

runs/Sep29_17-51-50_fd95e0b5707e/events.out.tfevents.1727632327.fd95e0b5707e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c07be74b2b9347e57ab046e69868c46923f5f70d0acad1ba266d8a6057649e
+size 9734

runs/Sep29_20-39-23_fd95e0b5707e/events.out.tfevents.1727642388.fd95e0b5707e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf26f2074ae09da0a2c8c8c3c4984101bde1cd1b514e6ac1ecfae1ed113f61d
+size 14637

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8cf0fda6caef9742436093fd18ebb1d3219bb897a807ae63e04fb6c1927de2
+oid sha256:23815f753814c6fa06c941b85aa50078574dca65e331b33048cc31379b12fea2
 size 5304