Simonom/uzbek-stt-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: 0.7569
+- Loss: 0.6899
 
 ## 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 |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.9643        | 1.0   | 1209 | 0.8721          |
-| 0.5618        | 2.0   | 2418 | 0.7569          |
+| 0.8857        | 1.0   | 189  | 0.7888          |
+| 0.5781        | 2.0   | 378  | 0.6899          |
 
 
 ### Framework versions
 
 - PEFT 0.11.2.dev0
 - Transformers 4.42.0.dev0
-- Pytorch 2.2.1+cu121
+- Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - 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": 16,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "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:e1e1467526d306e2b68c4234a07301dfafd11e24c6df0f420149274ef431d28c
-size 15782928
+oid sha256:276851e435ed059c7165e0f9d81dc4b3fb05ca8dacd6a77162852bfbf42413be
+size 62976168

runs/May30_06-34-15_acbe26610649/events.out.tfevents.1717050858.acbe26610649.873.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9956d9346446ebe2e950ff6ac67881794bbd4633ec03a1b6c65ceb2a9ae986c
+size 10147

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef957a6ecf94163d88a231546fede3ea59eb17da7a023438b7bb8a9908bae2f
+oid sha256:8f4294fc7ebd466924228624b535f6860df0af48cf742258cdafb156230b6543
 size 5240