Training in progress, step 10

25_10_23_config_test_3.csv

@@ -1,7 +1,7 @@
 run_number,comment,peformed_already,num_train_epochs,max_tokens,temperature,stop_token,classification_of_valuems,stemming,lemmatization
-1,no variations,False,2,100,0.8,False,False,False,False
-2,lemmatization set True,False,2,100,0.8,False,False,False,True
-3,stemming set True,False,2,100,0.8,False,False,True,False
+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
 5,lemmatization set True    stemming set True    classification_of_valuems set True,False,2,100,0.8,False,True,True,True
 6,lemmatization set True    classification_of_valuems set True,False,2,100,0.8,False,True,False,True

25_10_23_results_real_2.csv

@@ -1,2 +1,6 @@
 run_number,items_per_minute,changed_settings,total_time_taken,rouge_scores_unnest,rouge1 low Precision,rouge1 low Recall,rouge1 low F1 Score,rouge1 mid Precision,rouge1 mid Recall,rouge1 mid F1 Score,rouge1 high Precision,rouge1 high Recall,rouge1 high F1 Score,rouge2 low Precision,rouge2 low Recall,rouge2 low F1 Score,rouge2 mid Precision,rouge2 mid Recall,rouge2 mid F1 Score,rouge2 high Precision,rouge2 high Recall,rouge2 high F1 Score,min_cosine_sim_value,max_cosine_sim_value,mean_cosine_sim_value
-1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+1,1521.039672112574,no variations,17.35654926300049,0,0.1552139511291539,0.2368507842572497,0.1758862537048713,0.1906187415334918,0.2710603746035208,0.2103572106865446,0.2255849554785979,0.3125126862967795,0.2481360663560843,0.0430050127944396,0.0560971961077292,0.0467414986373149,0.0614798240950588,0.07652299205128,0.0654048416224262,0.0810943842103584,0.1003619737952392,0.0860744249037617,0.25,0.25,0.25
+2,1136.364890350167,lemmatization set True,23.231974363327023,0,0.2307835506591375,0.2822055548193336,0.2395607755891657,0.2723445337757645,0.3246601928313445,0.2792584474329001,0.3163835510859958,0.3672026648812247,0.321044755950184,0.0841251377427491,0.0946263082112953,0.0857343191461291,0.1090190764009911,0.120293835463903,0.1089806582745458,0.1336966853511748,0.1489721772053463,0.1326446754287497,0.25,0.25,0.25
+3,1145.0176842390404,0,23.0564124584198,0,0.1730499979812359,0.2277026758240191,0.1858254651225511,0.212789200180657,0.2683422907619309,0.2232479731938355,0.2546800467209451,0.3105154697037164,0.262393150946411,0.058362967482097,0.0706768796948392,0.060915053779653,0.0803296520070838,0.0916407157837064,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+4,1527.343732952156,stemming set True,17.284910678863525,0,0.1911494203017184,0.2419710105894565,0.1948045905449602,0.2281876386974067,0.2813295670232863,0.2290824875148726,0.2705361036165559,0.3227142209122678,0.2671129627936631,0.0571428445786132,0.065709860476325,0.0569749957140094,0.076490117488329,0.0869568156026996,0.0754744439809639,0.0998431774841167,0.1106401685930721,0.0960294744450772,0.25,0.25,0.25
+5,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0

README.md

@@ -724,6 +724,18 @@ 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
@@ -797,5 +809,6 @@ 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 sha256:73d6a4e0846975989b3efe8a9c9547db7abe938c3e87e45bd1e368da3d89aeb6
+oid sha256:5ba82506577f7e9fb6e4088f6e345fb33294ebfb8db5ee586d7b9ed63b98d390
 size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaa5b373a447766c8ae809d0e4bc892dbab990c48180f40a4f9fec29f94fd1ae
+oid sha256:22c6571abcdc9ce9d29a98eb4a0d0e0061ce27b21071ed1416e878638e8c4d17
 size 100690288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1e60b9bc95167a4476f9789e703c72923edffbe10e599d7636464152a3b36ea
+oid sha256:882c8f3ea6c07e04b9da20ab7eb6e86da62654cf93175c77e0bed0f94a950d91
 size 4283