Training in progress, step 10

24_10_23_config_test_5.csv

@@ -4,7 +4,7 @@ run_number,comment,peformed_already,num_train_epochs,max_tokens,temperature,stop
 3,num_train_epochs set 4,True,4,100,0.8,False
 4,temperature set 0.1,True,2,100,0.1,False
 5,temperature set 0.5,True,2,100,0.5,False
-6,temperature set 0.95,False,2,100,0.95,False
+6,temperature set 0.95,True,2,100,0.95,False
 7,max_tokens set 10,False,2,10,0.8,False
 8,max_tokens set 30,False,2,30,0.8,False
 9,max_tokens set 300,False,2,300,0.8,False

24_10_23_results_real.csv

@@ -6,4 +6,5 @@ run_number,items_per_minute,changed_settings,total_time_taken,rouge_scores_unnes
 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
 6,1527.832714984196,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
 7,1520.1783121784651,temperature set 0.5,17.36638379096985,0,0.2171684144819638,0.2796526632931748,0.229555721072754,0.2657758702124259,0.325561701915657,0.2741816672483476,0.3124402945667981,0.3742653583799557,0.3180416119348384,0.084309129128651,0.0950885066931036,0.0841922348430965,0.1097482578115943,0.1216660656915193,0.1094137741028614,0.1394859462287843,0.1521687324132882,0.1369193067464648
-8,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+8,1522.6253025648766,temperature set 0.95,17.33847451210022,0,0.1358318375162381,0.2367233918316699,0.1608590624915817,0.1684281758375314,0.2753995807236896,0.1957692397202891,0.2017753107078927,0.3158922152664998,0.231842660328347,0.0348253941650094,0.053243827263793,0.0397742520737331,0.0504060301453853,0.0741161939034151,0.0569579405303325,0.0665651758039863,0.0972012308295898,0.0754698873782298
+9,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0

README.md

@@ -508,6 +508,18 @@ 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
@@ -563,5 +575,6 @@ 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:ee9e2359224ad3acf0c72f4c77493c36f0c97db4ef0f4e0e2f54d00d420964d7
+oid sha256:dd060bc900549a9ffbda5d85fa1b20f90a9aa76215ac2a91fed8c25c101809e1
 size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d584be801d4f1b5de7a3194da90afd60d27e9054201f30f8b26ce51849e5f8
+oid sha256:4b944f840285b97fb81dd1a78eb47c89fc0ea5e447a2f917c3aceca6fad13eb9
 size 100690288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d66e48a06e0160235cd1f3e628a522c63485a8601e1b47bac427713588e38245
+oid sha256:78b37c8a624b8aa17607cac6bd1abaca2abb2c72bd897d054862070d3e3ee3e4
 size 4283