End of training

README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: ['classifier', 'pre_classifier']
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.4.0

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649500ca48f1fa3eab338ad1bbeee1bba7ffcc8a631930fc62218cd36aea3f68
+oid sha256:c88377f957837dcc9a495a805e08ee99580fe861f4655fa94cc43ce14f68d39a
 size 453130578

runs/Dec05_16-18-06_DESKTOP-P79TL96/events.out.tfevents.1733433494.DESKTOP-P79TL96

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad4cdde40d9f10e9842a131e2f7c22b7570411dda0d3b425c17b94f9840213f
-size 18810
+oid sha256:b2288a76f163c00ccc9e439b89d089618e55489fef4b28c89ae6814a3d7dc90e
+size 19478