Simonom/uzbek-stt-v2-3k-data

README.md

@@ -9,8 +9,6 @@ datasets:
 model-index:
 - name: temp
   results: []
-language:
-- uz
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -20,7 +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: 0.6938
+- Loss: 0.8801
 
 ## Model description
 
@@ -40,8 +38,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -53,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8861        | 1.0   | 189  | 0.7931          |
-| 0.5809        | 2.0   | 378  | 0.6938          |
+| 1.1475        | 1.0   | 604  | 1.0288          |
+| 0.6366        | 2.0   | 1208 | 0.8801          |
 
 
 ### Framework versions
@@ -62,5 +60,5 @@ The following hyperparameters were used during training:
 - PEFT 0.11.2.dev0
 - Transformers 4.42.0.dev0
 - Pytorch 2.3.0+cu121
-- Datasets 2.19.1
+- Datasets 2.19.2
 - Tokenizers 0.19.1

adapter_config.json

@@ -1,10 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "PeftModel",
-    "parent_library": "peft.peft_model"
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
   },
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "openai/whisper-large-v2",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -13,13 +13,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d6f931bab68e449a5f041b7b521fe6147eba1f59b2d3bdaef1ba2fffe180f0
-size 62976168
+oid sha256:2fa321b89f4be63edef21522512d29aed96195d8313a5904f591e375d3f37d11
+size 15782928

runs/Jun05_07-54-05_9e0960f27b2e/events.out.tfevents.1717574046.9e0960f27b2e.255.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b149120b90f8b045c9913cca28fb5e5686cafef681282b503d3ab1f2c75e1b1b
+size 4184

runs/Jun05_07-59-36_9e0960f27b2e/events.out.tfevents.1717574377.9e0960f27b2e.5050.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bf8f5cca55114554969c73a3e92fc8e726a48eafe10e71737dc62e14ca62f30
+size 17134

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe94d8a6fe9a79bc68aa0ff884729f1068cb3d5495d760d00e016f711b1a0155
+oid sha256:bd8f2faebce869f7c0ec1cbd287a5ff1fa267edd505d8da47488e2106401f87a
 size 5240