Model save

README.md

@@ -1,6 +1,6 @@
 ---
-library_name: peft
 base_model: TinyPixel/small-llama2
+library_name: peft
 tags:
 - generated_from_trainer
 model-index:
@@ -36,9 +36,12 @@ The following hyperparameters were used during training:
 - train_batch_size: 5
 - eval_batch_size: 5
 - seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
 - gradient_accumulation_steps: 5
-- total_train_batch_size: 25
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- total_train_batch_size: 100
+- total_eval_batch_size: 20
+- 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_ratio: 0.1
 - num_epochs: 1
@@ -49,8 +52,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.2
+- PEFT 0.12.0
 - Transformers 4.46.0
-- Pytorch 2.5.1
-- Datasets 3.1.0
+- Pytorch 2.4.0+cu118
+- Datasets 3.0.0
 - Tokenizers 0.20.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad894d996181ffe0f2bffed914f0b784410190c7aa8a8dc26255d50b1741f972
+oid sha256:295fbb6912088e76227fdd91a6b85ca49225304bb0ef961fa0ec23e73b1aef67
 size 3160464

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b937698134236189d0943ec068aedfcc0534d9c7e93cbcf62d616f8394a7076
-size 5176
+oid sha256:cbfa9dbe3b714e5e01f73c5e480df616663aca49b5819d36459e038d0a510ef7
+size 5240