End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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
+- Loss: 0.0000
 
 ## Model description
 
@@ -36,21 +36,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 6
+- eval_batch_size: 6
 - 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
+- num_epochs: 2
 
 ### 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          |
+| 0.0044        | 0.4167 | 10   | 0.0002          |
+| 0.0           | 0.8333 | 20   | 0.0000          |
+| 0.0           | 1.25   | 30   | 0.0000          |
+| 0.0           | 1.6667 | 40   | 0.0000          |
 
 
 ### Framework versions

adapter_config.json

@@ -24,17 +24,17 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "linear",
     "k_proj",
-    "q_proj",
-    "fc2",
-    "up_proj",
-    "out_proj",
-    "gate_proj",
-    "o_proj",
     "v_proj",
     "fc1",
+    "fc2",
+    "o_proj",
+    "out_proj",
+    "q_proj",
     "down_proj",
-    "linear"
+    "gate_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbe2eec1bf5ffea730a8486b7b35eb4d6eff356ab0bf19636ec9ad657d16df23
+oid sha256:17516d3e47bc607c2ce9c23f5692eb2fdec1b6068e189ccb4ff4feefbfd7527d
 size 414995696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ed7b1fce4cef7b09894e965782332eb77d423f47cd189d2e3a1cb5bb3951706
+oid sha256:cfff33f64eb743309f506b228f3674ac60bdbae18cc334bf9573cd8699aa694e
 size 5841