FunPang/whisper-large-V3-QLoRA-Cantones

README.md

@@ -1,15 +1,15 @@
----
-base_model: openai/whisper-large-v3
-datasets:
-- common_voice_13_0
-library_name: peft
-license: apache-2.0
-tags:
-- generated_from_trainer
-model-index:
-- name: whisper-large-V3-QLoRA-Cantones
-  results: []
----
+---
+base_model: openai/whisper-large-v3
+datasets:
+- common_voice_13_0
+library_name: peft
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: whisper-large-V3-QLoRA-Cantones
+  results: []
+---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
@@ -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](https://huggingface.co/openai/whisper-large-v3) on the common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8906
+- Loss: 3.0897
 
 ## Model description
 
@@ -44,14 +44,16 @@ 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: 50
-- num_epochs: 1
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.0483        | 1.0   | 1753 | 2.8906          |
+| 3.7995        | 1.0   | 1753 | 3.7999          |
+| 3.5221        | 2.0   | 3506 | 3.3667          |
+| 3.0697        | 3.0   | 5259 | 3.0897          |
 
 
 ### 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 sha256:7e57b9a1b5b41c1fa8316b569182af238de1cee4835ed9c0aaa7da2d16c0df51
+oid sha256:0c5235a2a30dfb9048014ac5ad649b0b97060c14c66982a4fc8b333df42376a0
 size 62969640

runs/Sep18_22-31-10_asus2/events.out.tfevents.1726723871.asus2.30204.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118c7c822bb8325ef0e2cf30cc32e025ce6f9269df9410cc47f9bf10aa543a85
+size 18493

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1c36d13c1801623da05d42e7cb25ec5261f9ffce8cdf4e2d71d66df7c2e6d18
+oid sha256:737e92a55cdc463cffc7cc3606bbe4baefefb28640cf40e31a62c45f85fb845b
 size 5432