End of training

README.md

@@ -10,6 +10,7 @@ metrics:
 model-index:
 - name: Llama-2-7b-hf-finetuned-mrpc-v5
   results: []
+library_name: peft
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -37,6 +38,17 @@ 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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -59,6 +71,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
+- PEFT 0.4.0
 - Transformers 4.31.0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5

runs/Sep26_13-04-56_6470e25f5c24/events.out.tfevents.1695738444.6470e25f5c24.1187.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6d98dadb445b3263b14394851775392a70aa4c7d82cc4c21ec7309525b2401
-size 6557
+oid sha256:1bf69aa719dbd7b01cea69d14fe7350d31778da150f31c1444718f1b2db445b9
+size 6911