Training in progress, step 10

24_10_23_results.csv

@@ -0,0 +1,13 @@
+Column1,Column2,Column3
+0,0,0
+0,0,0
+0,0,0
+0,0,0
+10,0,0
+10,0,0
+30,0,0
+30,0,0
+0,0,0
+0,wer,0
+0,0,0
+0,wer,0

24_10_23_results_test.csv

@@ -0,0 +1,2 @@
+run_number,items_per_minute,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,learning_settings,preidiction_settings,additional_settings
+1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,,,

README.md

@@ -376,6 +376,18 @@ 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
@@ -420,5 +432,6 @@ 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 sha256:9b0a0a93b3077aa6205dffe63f3b78745229a0bb1ab38322ccde596b37cea291
+oid sha256:cfbc873f4370004bff02bc73eb12eb0b949381663fb0c60e580dd0eadab215ac
 size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631ec82f0d2ba5f140e6a52d11ab8314e7dfdb6755333f2d0005b1e01fa20b1c
+oid sha256:c3292de5daf82aa621eb25f07ff15897b54cb831503d2378e6e5b897e5d6c32a
 size 100690288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc3ddac7736daf5a0b783f70b6067e997f8d8d9cf537928371dda9625cf6c7a
+oid sha256:8a4935782e34e08b6a1cfb759d92a5aece09454b2b0a6e52cb1bd9da3f51bad3
 size 4091