End of training

README.md

@@ -4,6 +4,7 @@ tags:
 model-index:
 - name: secllama
   results: []
+library_name: peft
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,6 +28,17 @@ More information needed
 
 ## Training procedure
 
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- load_in_4bit: False
+- 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: float16
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -46,6 +58,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
+- PEFT 0.4.0
 - Transformers 4.30.2
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.4

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa4c1b81f63fef00f43c8857d7cc1c6b98e9f37f9f2cef14b2a561bb558e356
+oid sha256:779aa17670e7d197f1c883311b2056ec0e5701d62704f25820e0afcbcf5f08f2
 size 134263757

runs/Aug30_07-16-40_000ecf9ae97a/events.out.tfevents.1693379813.000ecf9ae97a.313.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a673df50e280af8bf77f1be64f425008cb285f77db0f8c3f1d437515ef27efe1
-size 4476
+oid sha256:4d77fdf53764123875d0a4f9ee1199562f0375ba46736f5d141ead88b2d7a513
+size 4824