Samandards/uzbek-stt-vast-v2-3k-data

README.md

@@ -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-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_14_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0663
+- Loss: 3.8422
 
 ## Model description
 
@@ -38,8 +38,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.2676        | 1.0   | 151  | 1.1656          |
-| 0.8175        | 2.0   | 302  | 1.0663          |
+| No log        | 1.0   | 4    | 4.3669          |
+| No log        | 2.0   | 8    | 3.8422          |
 
 
 ### Framework versions
 
 - PEFT 0.11.2.dev0
-- Transformers 4.42.0.dev0
+- Transformers 4.43.0.dev0
 - Pytorch 2.3.0+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -1,10 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "WhisperForConditionalGeneration",
-    "parent_library": "transformers.models.whisper.modeling_whisper"
+    "base_model_class": "PeftModel",
+    "parent_library": "peft.peft_model"
   },
-  "base_model_name_or_path": "openai/whisper-large-v2",
+  "base_model_name_or_path": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -13,18 +13,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 64,
   "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:b875ad4e6b7a923bc700444a532ca1c8eda88c100c009f22e1b1d7f5199bb57e
-size 7918280
+oid sha256:8cc57393601ed4b827a871eabad12e946079b04158d33d30682ed59dcd304d79
+size 125890952

runs/Jul01_10-10-07_7af5b129fa96/events.out.tfevents.1719828610.7af5b129fa96.322.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2083d72c63ab84a6a2841924280225f25796fb2c5b7f31cca33e665e2e7860
+size 7047

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ea730e8e63071c7043b70dff341110d268b6fc3cc25a9e49e8d0f02367edc1
-size 5240
+oid sha256:bbe931e1ea9f4bec02decb2ce2b87af873026e32d79203c45007bde377e7c5b1
+size 5304