End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: meta-llama/Llama-3.2-1B-Instruct
+base_model: meta-llama/Llama-3.2-3B-Instruct
 datasets:
 - generator
 library_name: peft
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the generator dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the generator dataset.
 
 ## Model description
 
@@ -44,7 +44,8 @@ The following hyperparameters were used during training:
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 1
 - mixed_precision_training: Native AMP
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bcc52aedbe039c01ff79bfd7db92da7d5f52546e3a255ab15d2976c902084aa
-size 27271552
+oid sha256:0e5ceb216599113955fb046366e338dd7e36152aa88fd5b332d2e6b3c507beb0
+size 73415408

runs/Oct02_08-11-06_4de3b946ecd5/events.out.tfevents.1727856718.4de3b946ecd5.5062.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f9c7bb010d5a8e76a438e8bdfc0922f60d5f1478ce0ffe5591a11d14444819
+size 8806

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9da11dc689976993c99065fde89e17f2fad8a21f755456177ead23d26628563
+oid sha256:4fcf876aad706f024be5e4df0f9caa8b0cc643c4c59d036ce47ee3e9dc7d781b
 size 5432