Samandards/uzbek-5k-data

README.md

@@ -16,7 +16,7 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3786
+- Loss: nan
 
 ## Model description
 
@@ -36,8 +36,8 @@ 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
@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.5445        | 1.0   | 2320 | 0.4583          |
-| 0.346         | 2.0   | 4640 | 0.3786          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 5.9724        | 1.0   | 21515 | 5.8390          |
+| 0.0           | 2.0   | 43030 | nan             |
 
 
 ### Framework versions
 
 - PEFT 0.12.1.dev0
 - Transformers 4.45.0.dev0
-- Pytorch 2.3.1+cu121
-- Datasets 2.20.0
+- Pytorch 2.2.0
+- Datasets 2.21.0
 - 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": 4,
+  "lora_alpha": 512,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 2,
+  "r": 256,
   "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:c930fffc950177897f70d99f05bc5c8f722350fcf2b1f6a944bd7fa80ee35b22
-size 3986008
+oid sha256:e44e164b334acc605158e2551cba118f40072a8caf2a7281654602861e16d017
+size 503398792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e96f263e115c72f14036d0887505cd38883cae2d591e9b603dba92f7dee20d
+oid sha256:f204cea93238f5d3d9cbaa06cade764c0ffa6cf89fd9430fa2ef49efeb4c54a4
 size 5304