Training in progress, step 10

25_10_23_config_test_1.csv

@@ -2,4 +2,4 @@ run_number,comment,peformed_already,num_train_epochs,max_tokens,temperature,stop
 1,no variations,True,2,100,0.8,False,False,False,False
 2,lemmatization set True,True,2,100,0.8,False,False,False,True
 3,stemming set True,True,2,100,0.8,False,False,True,False
-4,classification_of_valuems set True,False,2,100,0.8,False,True,False,False
+4,classification_of_valuems set True,True,2,100,0.8,False,True,False,False

25_10_23_results_real.csv

@@ -9,4 +9,6 @@ run_number,items_per_minute,changed_settings,total_time_taken,rouge_scores_unnes
 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
 9,1527.7772954831448,stemming set True,17.28000545501709,0,0.1983957450904019,0.2519780089622217,0.2098971903962357,0.2402826270196343,0.2928000782881022,0.2490765635230842,0.2850926200202243,0.3364948588993159,0.2903129396144104,0.0723938258535772,0.0800337747692468,0.0729619311369439,0.0946682401043626,0.1041986615172271,0.0940029666330387,0.118932059220299,0.1294571703280245,0.1171713046848759
 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
-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
+11,1521.609931137608,classification_of_valuems set True,17.35004448890686,0,0.3097912503061737,0.3117918619129387,0.2985123093297854,0.3692864464982227,0.3657660910086977,0.3510613139478704,0.4322932016041544,0.4194092516901677,0.4034142346670022,0.1853986019402615,0.1767452335316192,0.1744893735961138,0.2321160496220204,0.2189556994085239,0.2145193605708969,0.2770436971412456,0.2594983484442184,0.2537992371891699
+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
+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

@@ -616,6 +616,18 @@ 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
@@ -680,5 +692,6 @@ 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:d4885ebc38f3b225eede3c0aec89c26944fd73f363b887431c2517c6fafcb09b
+oid sha256:ce1f1a82ee3bdd7ed19236720cbc3352ab1892f399a5ff37bb980570ee1a3178
 size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:226ac5ca591c12b5c82dffad22b901a4a13f0bf0f1133767bde5c66fc9b56950
+oid sha256:5a3480b947478c17d5df359b02a08abb839a59e985f611c4c15b2f0b3a0cb324
 size 100690288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db0866b30686144c47b08695b1a99d3431e7a665a2e0405212e33a457bf233a0
+oid sha256:91c44e8dc8169fffdaa1ca9accb53d71deab0240c8b8ce38c8f9a2dcce55449d
 size 4283