Training in progress, step 10

27_10_23_results_real_3.csv

@@ -14,3 +14,5 @@ run_number,items_per_minute,changed_settings,total_time_taken,rouge_scores_unnes
 13,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
 14,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
 15,1525.0886694068038,falcon-7b,17.310468912124634,0,0.1920312918488378,0.2733521510117445,0.2138076844496275,0.2305652154961202,0.3156654927521272,0.2504661514924052,0.2702267930741617,0.3602264110748507,0.2900150185250124,0.0735582107305615,0.0941018095302676,0.0777555255346162,0.0958480064326763,0.1239771466448827,0.1006577942336031,0.1223833190904904,0.1553484204589603,0.1266835299564551,0.5,0.5,0.5
+16,1528.3674276732831,no variations,17.273333311080933,0,0.1640760062712931,0.2175153345055349,0.1725490020930999,0.2175548930624185,0.2698052476479251,0.2214547853833987,0.2751894295776944,0.3271762866519473,0.2745785222632161,0.052758589847894,0.0584458059295757,0.0523754813514573,0.0802165683682858,0.0872847696883344,0.078952884715634,0.1150394431348748,0.1216036952539715,0.1129530848149091,0.5,0.5,0.5
+17,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0

README.md

@@ -1180,6 +1180,18 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_use_double_quant: True
 - bnb_4bit_compute_dtype: bfloat16
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- 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
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: False
@@ -1291,5 +1303,6 @@ The following `bitsandbytes` quantization config was used during training:
 - PEFT 0.5.0
 - PEFT 0.5.0
 - PEFT 0.5.0
+- PEFT 0.5.0
 
 - PEFT 0.5.0

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c4538d31789923da9a0b650eb93f1993ad06be791a6789fe6d850244b608b7
+oid sha256:0aa09321fd3143cbee0f0cfe8d234f234268dbeebbad01b1dc68f802322a68ae
 size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1350e2a653276de3f2af668c85b8304fd9a34404e72f8ab01376be3045d7ad0
+oid sha256:32ffb1c38f6654b724a68133415982ae2049adb52a90890ea40426159ac6655e
 size 100690288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e903b663cf132e59716e983b2a8f93318349882f473322455b12161809a58d3c
+oid sha256:d0238ab2a37699048f1d9e887956e38ba8e6cf8b4694f9ec45544bf3402e0e8b
 size 4283