llama2 finished 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: None
+- 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.dev0

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ada01cb3162a90b40d7b03527da1bd6502b0276613c9bb53e443b62a973474
+oid sha256:41e88c0ecd3b1ba0c84680592c20e70e63f73e55c7f3c2fd2f2556a22cb781e9
 size 134263757

runs/Aug22_23-56-18_gpu02/events.out.tfevents.1692760027.gpu02.60783.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19575f66a3153a15cd0ebfea317a38c24fedd1d1032222a9cba741fcb0fd6bd6
-size 132031
+oid sha256:d57e62f98fe767ad49a0810d9f44e2fe03c1a906160ba2ab8955570215a8332c
+size 144003

runs/Aug22_23-56-18_gpu02/events.out.tfevents.1692794785.gpu02.60783.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c55bbd3fd0aac47c387f692b0ce4144bbc35dabd6f35aab5cb8357f122f6a39
+size 359