llama-3.2-1B-personality-detection-C

README.md

@@ -50,14 +50,14 @@ The following `bitsandbytes` quantization config was used during training:
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 2e-05
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 50
+- num_epochs: 80
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9854d8ca7b6b7e8d2c1299cffaafefea134217e00cf9a850c5f36a4ee5add6df
+oid sha256:75486f1fe6f394aa2e69bf2b652fd8e7f306eeee000f67d9de274781728dedae
 size 27271552

runs/Oct14_01-26-34_bcm-dgxa100-0006/events.out.tfevents.1728887207.bcm-dgxa100-0006

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b8ab1bd76f7b75fc24799b177ff9d2ba0bb0a55daf11ac00b08b295429c4ae
+size 188576

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc14b742c77bd897a07b8fa4ce0e7ab18395ce4e2c93cc88e1aca2ed144a9970
+oid sha256:efbd37fe3e67e74cca883ceeb452c2cb4de76d81fb81567d28ae5a581e581acf
 size 5496