Training in progress, step 10

25_10_23_config_test_3.csv

@@ -3,7 +3,7 @@ run_number,comment,peformed_already,num_train_epochs,max_tokens,temperature,stop
 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,True,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
+5,lemmatization set True    stemming set True    classification_of_valuems set True,True,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
 7,lemmatization set True    stemming set True    classification_of_valuems set True,False,2,100,0.8,False,True,True,True
 8,lemmatization set True,False,2,100,0.8,False,False,False,True

25_10_23_results_real_3.csv

@@ -1,2 +1,2 @@
 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
+1,1528.7511051142055,lemmatization set True    stemming set True    classification_of_valuems set True,17.26899814605713,0,0.3205886579057058,0.3461841100712408,0.3125968527399897,0.3764311496085647,0.4044306368763413,0.3640179039142892,0.4301562757727841,0.4601529897517745,0.4126958041031095,0.1996173843814712,0.2104996883636505,0.192256615234812,0.2413141280963179,0.2545138712016493,0.2304351345215164,0.2861403205265476,0.2982544029556617,0.2700016871324253,0.5,0.5,0.5

26_10_23_config_test_3.csv

@@ -0,0 +1,8 @@
+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
+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
+7,lemmatization set True    stemming set True    classification_of_valuems set True,False,2,100,0.8,False,True,True,True

26_10_23_results_real_3.csv

@@ -0,0 +1,2 @@
+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

README.md

@@ -772,6 +772,18 @@ 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
@@ -849,5 +861,6 @@ 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 sha256:6f1535bdce45611b7c8dd8b76df934b71ea6411f0626963821c7f1e86eab7268
+oid sha256:f348d9366304dcbd989170b04cfa3a9857fb30ca63ae781ad718ac26b5e80715
 size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298a6501c2d4d1c335ef16a4889cbb9d1c5c974c7476bf66dba3d7fb987dc159
+oid sha256:ca35f0e5e1d64176a903c22233e6905b8a4329facee988779a1711a6f032fdb6
 size 100690288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7cc8608f946e94c67ae3c73ed233c2a0d38e3de1484b4a0021cfabb0d8f1cbc
+oid sha256:c08d61647aec8c95dd98fb2b1140c42969afe88b805f4cb4d75476262cc57141
 size 4283