End of training

README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2-Audio-7B-Instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: Qwen-das-1
+  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. -->
+
+# Qwen-das-1
+
+This model is a fine-tuned version of [Qwen/Qwen2-Audio-7B-Instruct](https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0012
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- 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
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8766        | 0.2222 | 8    | 0.0931          |
+| 0.0336        | 0.4444 | 16   | 0.0023          |
+| 0.0007        | 0.6667 | 24   | 0.0015          |
+| 0.0002        | 0.8889 | 32   | 0.0012          |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.54.0.dev0
+- Pytorch 2.7.1+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.2

adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-Audio-7B-Instruct",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "fc2",
+    "up_proj",
+    "out_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "fc1",
+    "down_proj",
+    "linear"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe2eec1bf5ffea730a8486b7b35eb4d6eff356ab0bf19636ec9ad657d16df23
+size 414995696

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed7b1fce4cef7b09894e965782332eb77d423f47cd189d2e3a1cb5bb3951706
+size 5841