Training in progress, step 10

25_10_23_config_test_2.csv

@@ -1,5 +1,5 @@
 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
+1,no variations,True,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
 4,classification_of_valuems set True,False,2,100,0.8,False,True,False,False

25_10_23_results_real_1.csv

@@ -1,3 +1,4 @@
 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
-2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+1,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+2,1521.309333394151,no variations,17.35347270965576,0,0.177371713651783,0.2550923602206023,0.1915303932252859,0.2162296594727927,0.2943577256872228,0.2292635261246988,0.2578354974529445,0.3348748371724032,0.2689393478592398,0.0611264081931369,0.0770329338911831,0.064154405302722,0.082857683902168,0.1017829295957176,0.0858572417823811,0.1078800549812877,0.1294471350521465,0.1105378521683605,0.25,0.25,0.25
+3,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0

README.md

@@ -640,6 +640,18 @@ 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
@@ -706,5 +718,6 @@ 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 sha256:0bf4d2f85484c4b6b7eb717bc8a00353f667d920e30a0aa7ddf0a33e262e374b
+oid sha256:ab96094ce4183778691414be2e9db3082ac5e6069d77f3b80d05111483620319
 size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f24a31bf80360e505636d8424b9931cff01274b92ecaedbbd0590321fd681d6a
+oid sha256:8f054a450b735198e815bfdf1c6e2e5b6c14cf3f9f234017b6bdec44e1e55a42
 size 100690288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde72a63056d670c29f80ad8c5b9aa6efa0445a1d2e70853d26f5091133822bd
+oid sha256:83ecccae8b2e74cb5025034fff27c410e46e8f739907e5d91360290c9afcede9
 size 4283