Model save

README.md

@@ -15,13 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # qwen-lyrics-monitored
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the None dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 3.1399
-- eval_runtime: 89.6869
-- eval_samples_per_second: 38.222
-- eval_steps_per_second: 4.783
-- epoch: 1.0372
-- step: 2000
 
 ## Model description
 
@@ -40,14 +33,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 8e-05
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
 - optimizer: Use 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: 100
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a781fe3301d270a915cbdc88132718f869ed7a318fcbb199edc4f88482047de0
+oid sha256:77686e121a029ab1841ed5d019ffb3b7e751003aec073913a2a05a41fad96274
 size 14764792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9530022ade4f7e578922810a3a647f6450d5bd8550a1d29551ed65415c305e0
+oid sha256:4886603543f6320af853a9ae0d5441636cfa6ce17378292bdbc1cd0f4dc53ca3
 size 5368