Training in progress, step 10

24_10_23_config_test_5.csv

@@ -6,7 +6,7 @@ run_number,comment,peformed_already,num_train_epochs,max_tokens,temperature,stop
 5,temperature set 0.5,True,2,100,0.5,False
 6,temperature set 0.95,True,2,100,0.95,False
 7,max_tokens set 10,True,2,10,0.8,False
-8,max_tokens set 30,False,2,30,0.8,False
+8,max_tokens set 30,True,2,30,0.8,False
 9,max_tokens set 300,False,2,300,0.8,False
 10,max_tokens set 500,False,2,500,0.8,False
 11,stop_token set True,False,2,100,0.8,True

24_10_23_results_real.csv

@@ -8,4 +8,5 @@ run_number,items_per_minute,changed_settings,total_time_taken,rouge_scores_unnes
 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
 8,1522.6253025648766,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
 9,8137.253778897434,max_tokens set 10,3.244337797164917,0,0.1297367298173749,0.0248065965409596,0.0394931695780917,0.1776028332479944,0.0319881335779764,0.0503325526395891,0.2305753968253968,0.0398045284176508,0.0623919220801066,0.021505376344086,0.0012679576629888,0.0022182435535744,0.0615292712066905,0.003434056688616,0.0059725196216856,0.1129256272401433,0.0066200549176752,0.0109573554493896
-10,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+10,4535.835024326586,max_tokens set 30,5.820317506790161,0,0.2422416346899768,0.0977982875121211,0.1325246370842857,0.2880002239989636,0.1154357218367962,0.1561017908481051,0.339886078686101,0.1336154477253922,0.1801894525067171,0.072104162735737,0.0225936047273112,0.033723979023946,0.10640965444612,0.0328642617088289,0.0488049972899845,0.1415701399984359,0.0435389639524036,0.0644875164681592
+11,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0

README.md

@@ -532,6 +532,18 @@ 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
@@ -589,5 +601,6 @@ 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:dc3649368db97d0e084d69e7b988307f4ab51494e051c599e156241ad5359017
+oid sha256:82254fe924f9c96ce62567e0374967cf2149ed933e0acfab1cebea0b600d1abf
 size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc124817399e701f648910c5eca91fccdc40719c08befb3a5359627e5ef35ffc
+oid sha256:60ce81dfc4c6e390510baa0a253c9daf0ad5c7354c9152e7d0b748c7fb6eb8b1
 size 100690288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf83eeceb5ce1c413aa4e6fb54e48dd54db58e34101ffdcb4940d2f2fc81b67
+oid sha256:57067655398e3a7e24c43c0422197d5137b7fca6e0886ae4d6e05b55472bb0a8
 size 4283