Training in progress, step 10

24_10_23_config_test_5.csv

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

24_10_23_results_real.csv

@@ -10,4 +10,5 @@ run_number,items_per_minute,changed_settings,total_time_taken,rouge_scores_unnes
 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
 10,4535.835024326586,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
 11,414.6348899218345,max_tokens set 300,63.6704740524292,0,0.1036658616791158,0.4509069403064212,0.1604171913717259,0.1231034900935985,0.4927653826230481,0.1876565027825787,0.1450621467503176,0.5346234029929966,0.2163978589006886,0.0448793224180538,0.1701044771154594,0.0683517341604418,0.0570134552924645,0.2053617015027369,0.0863401271991256,0.0714855259069783,0.2472927214590566,0.1070059828658844
-12,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+12,204.32573718052336,max_tokens set 500,129.2054557800293,0,0.0865648503277925,0.537484522121256,0.144958692936355,0.0993220605517253,0.5776706001123082,0.1631500990375618,0.1139333668976341,0.6135557935103993,0.1822362653389549,0.0404341312259856,0.248172449895455,0.0676439704335958,0.0483331366667381,0.2836322635507246,0.0799268515563459,0.0567861735838364,0.3200714445367198,0.0929257458106047
+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

README.md

@@ -556,6 +556,18 @@ 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
@@ -615,5 +627,6 @@ 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 sha256:8fba75d305d335d106ad2fa560c631f08663ba829b31898daa262959e409bb36
+oid sha256:5523b7bc4a972966dd2d5b3e55f7063907d051cc9ad26e122d46d213a29745db
 size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:007ecd89f0aa8794ead1f5f9d1cf00b2f12b52f91eeea115b04821a9bf1d5c79
+oid sha256:ea892aa214116ce1621b62fa1c6124e131cefb744b0847898bfa237c6735bd0f
 size 100690288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc3eab1d36907713527d9a6f8f88999750f520284dd62ba3536fb9eccb57903
+oid sha256:ba943e7eb19b0c140b40a340daadd3e507f341959cbd4bff8e4b59dc8d0cf2c2
 size 4283