End of training

README.md

@@ -16,12 +16,7 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.6698
-- eval_runtime: 7.0899
-- eval_samples_per_second: 0.987
-- eval_steps_per_second: 0.282
-- epoch: 16.0
-- step: 112
+- Loss: 0.6328
 
 ## Model description
 
@@ -46,10 +41,41 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 10
+- lr_scheduler_warmup_steps: 18
 - num_epochs: 25
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.983         | 1.0   | 7    | 0.6322          |
+| 0.6898        | 2.0   | 14   | 0.5551          |
+| 0.3441        | 3.0   | 21   | 0.5087          |
+| 0.2457        | 4.0   | 28   | 0.4763          |
+| 0.1372        | 5.0   | 35   | 0.4975          |
+| 0.109         | 6.0   | 42   | 0.4832          |
+| 0.0663        | 7.0   | 49   | 0.4969          |
+| 0.0452        | 8.0   | 56   | 0.5020          |
+| 0.0322        | 9.0   | 63   | 0.5067          |
+| 0.0218        | 10.0  | 70   | 0.5277          |
+| 0.0147        | 11.0  | 77   | 0.5655          |
+| 0.0157        | 12.0  | 84   | 0.5682          |
+| 0.0214        | 13.0  | 91   | 0.6323          |
+| 0.0091        | 14.0  | 98   | 0.6149          |
+| 0.0105        | 15.0  | 105  | 0.5824          |
+| 0.0111        | 16.0  | 112  | 0.5962          |
+| 0.011         | 17.0  | 119  | 0.5991          |
+| 0.0078        | 18.0  | 126  | 0.6121          |
+| 0.0065        | 19.0  | 133  | 0.6199          |
+| 0.0054        | 20.0  | 140  | 0.6285          |
+| 0.0041        | 21.0  | 147  | 0.6269          |
+| 0.0051        | 22.0  | 154  | 0.6299          |
+| 0.003         | 23.0  | 161  | 0.6244          |
+| 0.0025        | 24.0  | 168  | 0.6320          |
+| 0.0035        | 25.0  | 175  | 0.6328          |
+
+
 ### Framework versions
 
 - PEFT 0.11.2.dev0

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 sha256:4f277db84ff64303f7516f8e595142b7262b8c11e8195162be27358158d2b102
+oid sha256:c40e0bb5892b210b63c739223e07c7d14ed6a8e9df8cb6b18a0bbdbde1e3160b
 size 62969640

runs/May19_10-19-59_95e6e7071282/events.out.tfevents.1716114035.95e6e7071282.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eb30ea57c398e977e9359c758e26a0d74462c39ec6ff98bd184b11301fda04b
+size 6023

runs/May19_10-23-29_95e6e7071282/events.out.tfevents.1716114220.95e6e7071282.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2923c58f7cf3a2c69b39d45d54ddc76d9dcf80b08f697b448f1e9c6587dccd76
+size 25132

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e517a076c2f21aedd8f79223f324a9d440bef10b76be1ee945b9b7e23644862a
+oid sha256:2c5150d9179768eccaf7272af9e0aad4f9f7068863c3143fc20a5b295f6f04e5
 size 5176