BarraHome commited on
Commit
4ec4a90
·
verified ·
1 Parent(s): 86d1abe

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -171,8 +171,12 @@ The fine-tuned model shows consistent improvements across all metrics:
171
  - **Training Strategy:** Contrastive learning with hard negative mining
172
  - **Epochs:** 1
173
  - **Batch Size:** 64
174
- - **Learning Rate:** 2e-5
175
  - **Training Samples:** 671,972 query-document pairs
 
 
 
 
176
  - **Precision:** FP16
177
  - **Hardware:** NVIDIA RTX A6000 (49GB VRAM)
178
 
 
171
  - **Training Strategy:** Contrastive learning with hard negative mining
172
  - **Epochs:** 1
173
  - **Batch Size:** 64
174
+ - **Learning Rate:** 2e-5 (with 10% warmup)
175
  - **Training Samples:** 671,972 query-document pairs
176
+ - **Total Steps:** 10,500
177
+ - **Training Duration:** 4 hours 6 minutes
178
+ - **Throughput:** 45.4 samples/second
179
+ - **Final Loss:** 2.245
180
  - **Precision:** FP16
181
  - **Hardware:** NVIDIA RTX A6000 (49GB VRAM)
182