End of training

README.md

@@ -1,10 +1,10 @@
 ---
-base_model: facebook/wav2vec2-large-960h-lv60-self
 license: apache-2.0
-metrics:
-- wer
+base_model: facebook/wav2vec2-large-960h-lv60-self
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: wav2vec2-large-960h-lv60-self-dysarthria
   results: []
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-large-960h-lv60-self](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3289
+- Loss: 2.2385
 - Wer: 1.0
 
 ## Model description
@@ -37,37 +37,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.0003
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 1000
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
 - num_epochs: 30
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer   |
-|:-------------:|:-----:|:----:|:---------------:|:-----:|
-| 102.5595      | 1.6   | 200  | 96.4849         | 1.044 |
-| 96.3152       | 3.2   | 400  | 90.3864         | 1.03  |
-| 86.9312       | 4.8   | 600  | 76.0484         | 1.004 |
-| 62.5942       | 6.4   | 800  | 48.2334         | 1.0   |
-| 38.3278       | 8.0   | 1000 | 23.9740         | 1.0   |
-| 5.5117        | 9.6   | 1200 | 3.4634          | 1.0   |
-| 4.9465        | 11.2  | 1400 | 3.3772          | 1.0   |
-| 3.5841        | 12.8  | 1600 | 3.3593          | 1.0   |
-| 3.9731        | 14.4  | 1800 | 3.3459          | 1.0   |
-| 3.4886        | 16.0  | 2000 | 3.3371          | 1.0   |
-| 3.5821        | 17.6  | 2200 | 3.3355          | 1.0   |
-| 3.6743        | 19.2  | 2400 | 3.3327          | 1.0   |
-| 3.5593        | 20.8  | 2600 | 3.3311          | 1.0   |
-| 3.5576        | 22.4  | 2800 | 3.3288          | 1.0   |
-| 3.5099        | 24.0  | 3000 | 3.3272          | 1.0   |
-| 4.2208        | 25.6  | 3200 | 3.3270          | 1.0   |
-| 3.5336        | 27.2  | 3400 | 3.3316          | 1.0   |
-| 3.5272        | 28.8  | 3600 | 3.3289          | 1.0   |
+| Training Loss | Epoch | Step | Validation Loss | Wer |
+|:-------------:|:-----:|:----:|:---------------:|:---:|
+| 20.9703       | 3.2   | 200  | 3.5607          | 1.0 |
+| 3.4216        | 6.4   | 400  | 3.3741          | 1.0 |
+| 3.3062        | 9.6   | 600  | 3.1419          | 1.0 |
+| 2.994         | 12.8  | 800  | 2.6835          | 1.0 |
+| 2.7361        | 16.0  | 1000 | 2.4129          | 1.0 |
+| 2.6005        | 19.2  | 1200 | 2.2973          | 1.0 |
+| 2.5724        | 22.4  | 1400 | 2.2520          | 1.0 |
+| 2.619         | 25.6  | 1600 | 2.2435          | 1.0 |
+| 2.5278        | 28.8  | 1800 | 2.2385          | 1.0 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07496b5f8eac5f6f6051e996a8a0950537a718c495a6d6c1eb5ef3510ac5f8e1
+oid sha256:5de2cdaab72ef149c0de2f5dd39e115930e37e9b9b9129c1f8060a90fb0b0d4f
 size 630993726

runs/Jul31_16-58-35_ip-10-192-10-83/events.out.tfevents.1722445141.ip-10-192-10-83.2517.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71dda18caf9470eba84b70d89e408489e58214aea1b02095a855b8622620ae64
-size 11610
+oid sha256:8d731f72341c2e55775b56839ff3794b0782013a6b3df0b328975c3ff4b891b9
+size 13444