End of training

README.md

@@ -0,0 +1,66 @@
+---
+library_name: peft
+language:
+- ms
+- zh
+- en
+license: mit
+base_model: openai/whisper-large-v3-turbo
+tags:
+- generated_from_trainer
+datasets:
+- CheeseES/LLM_FINE_TUNING_1
+model-index:
+- name: Whisper_Large_V3_Turbo_Tune
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Whisper_Large_V3_Turbo_Tune
+
+This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the LLM Fine Tuning Dataset dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.0558
+- eval_wer: 48.2143
+- eval_runtime: 216.6063
+- eval_samples_per_second: 1.08
+- eval_steps_per_second: 0.139
+- epoch: 10.2564
+- step: 1200
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 33
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 300
+- training_steps: 3000
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.51.3
+- Pytorch 2.8.0.dev20250319+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
+  },
+  "base_model_name_or_path": "openai/whisper-large-v3-turbo",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc1",
+    "q_proj",
+    "fc2",
+    "out_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d63d7ab94f79b29fc6f959573df5c889aafb45c950dc6f2a6da961b973e514
+size 27916528

preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d1137e7a3b20a887997470a211a01efcce3749d35275a32598a5ab41a125d4
+size 5841