Training in progress, step 10

24_10_23_config_test_5.csv

@@ -2,7 +2,7 @@ run_number,comment,peformed_already,num_train_epochs,max_tokens,temperature,stop
 1,no variations,True,2,100,0.8,False
 2,num_train_epochs set 1,True,1,100,0.8,False
 3,num_train_epochs set 4,True,4,100,0.8,False
-4,temperature set 0.1,False,2,100,0.1,False
+4,temperature set 0.1,True,2,100,0.1,False
 5,temperature set 0.5,False,2,100,0.5,False
 6,temperature set 0.95,False,2,100,0.95,False
 7,max_tokens set 10,False,2,10,0.8,False

24_10_23_results_real.csv

@@ -4,4 +4,5 @@ run_number,items_per_minute,changed_settings,total_time_taken,rouge_scores_unnes
 3,1523.9837159869403,no variations,17.3230197429657,0,0.1636485914474813,0.2442045694140484,0.1797223166652443,0.2022430465904158,0.2801373375823723,0.2116393486309779,0.2415684051660303,0.3169552846418265,0.2454148877244572,0.0478798760618172,0.0576684379443441,0.0477967373151322,0.0678391323266069,0.077928569151534,0.0650191619264259,0.0907738130484548,0.0998870507246741,0.0832964711085375
 4,1522.2178865206856,num_train_epochs set 1,17.343115091323853,0,0.2376625242385059,0.3023553491885417,0.2466419847811962,0.2778790955613333,0.3401289752720904,0.2821571102236015,0.3180027377972204,0.3798165334049617,0.3179549121145006,0.0837484346025289,0.0937113595049826,0.0827357329003541,0.1063890214298248,0.1180185594384271,0.1035788259198791,0.1323456462690016,0.1424547541923625,0.1257800923415455
 5,1518.6126627544304,num_train_epochs set 4,17.38428807258606,0,0.204501142924171,0.2631263501640951,0.216296517806529,0.2438945463294087,0.3035055536430592,0.2535604474093736,0.284314980672076,0.3439781569199127,0.2897906500879131,0.068449643154325,0.0784628470108706,0.0694609697778577,0.0902097337430753,0.1011023693641125,0.0899452487768021,0.113679310178906,0.1256319688818133,0.110997966723548
-6,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+6,1527.832714984196,temperature set 0.1,17.279378652572632,0,0.1976528832961626,0.2467135274850016,0.2058575375878128,0.2409779467117316,0.2882065660284059,0.2442224680649742,0.2898388010112335,0.3293633439583997,0.286402550490794,0.0718838497030716,0.0803139894900771,0.0722726446083685,0.0995882205581848,0.1065136908080851,0.0965880380354894,0.1279108884546315,0.136023948720788,0.1229532335611118
+7,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0

README.md

@@ -484,6 +484,18 @@ 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
@@ -537,5 +549,6 @@ 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 sha256:7825b0b27f1d503de4e47c1edc44d58ab374f1389e13e3538902d0bb110984fa
+oid sha256:02682686ce4a0955a56ab946e1a4c5b56f66353629712b846adc556510d565c7
 size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fcb718ad0dc8680d2bc428ae6f85088b7a39ed01569569f16d220e8e2673b9c
+oid sha256:ef20aeb158a7f937de6ccafe6d216d5cc24429a2bb9c0f5b57b0d839534aace4
 size 100690288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:450e2794a4e314586a2a69fe7a83cc035f0a855c9bd0569e496ec1416d4158ae
+oid sha256:fb418f7fce37effb817e6436caa1341bb38d03d51c65379788dace320f93d043
 size 4283