Hugging Face's logo

genshiai-daichi
/
med-ruri-v3-70m-v2-from-ruri

Sentence Similarity
sentence-transformers
Safetensors
Japanese
modernbert
medical
japanese
ruri
embedding
text-embeddings-inference
Model card Files
xet
 Community
genshiai-daichi commited on
Commit
8251514
·
verified ·
1 Parent(s): 45258dd

latest = step 4500 (nDCG@10=0.4773)

Browse files
Files changed (2) hide show
  1. model.safetensors +1 -1
  2. trainer_state.json +94 -5
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fc86a9adb931d8156ecfd4ed2b56add71480fff05643cc048b7e04d7aeb1cbd
3
  size 280019040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ac99815f060d8a4c0706c9f7dee2a75eb400f3f3112fb6c244d179c52b0ce78
3
  size 280019040
trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 4000,
3
- "best_metric": 0.4708195055654097,
4
- "best_model_checkpoint": "checkpoints/med-ruri-v3-70m-v2-from-ruri/checkpoint-4000",
5
- "epoch": 0.649456080532554,
6
  "eval_steps": 500,
7
- "global_step": 4000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -720,6 +720,95 @@
720
  "eval_samples_per_second": 0.0,
721
  "eval_steps_per_second": 0.0,
722
  "step": 4000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
723
  }
724
  ],
725
  "logging_steps": 50,
 
1
  {
2
+ "best_global_step": 4500,
3
+ "best_metric": 0.4772869175667747,
4
+ "best_model_checkpoint": "checkpoints/med-ruri-v3-70m-v2-from-ruri/checkpoint-4500",
5
+ "epoch": 0.7306380905991232,
6
  "eval_steps": 500,
7
+ "global_step": 4500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
720
  "eval_samples_per_second": 0.0,
721
  "eval_steps_per_second": 0.0,
722
  "step": 4000
723
+ },
724
+ {
725
+ "epoch": 0.6575742815392109,
726
+ "grad_norm": 23.990192413330078,
727
+ "learning_rate": 3.606221158776278e-06,
728
+ "loss": 0.46084171295166015,
729
+ "step": 4050
730
+ },
731
+ {
732
+ "epoch": 0.6656924825458679,
733
+ "grad_norm": 21.707965850830078,
734
+ "learning_rate": 3.520765681080158e-06,
735
+ "loss": 0.4574726486206055,
736
+ "step": 4100
737
+ },
738
+ {
739
+ "epoch": 0.6738106835525247,
740
+ "grad_norm": 24.35520362854004,
741
+ "learning_rate": 3.4353102033840373e-06,
742
+ "loss": 0.4719329833984375,
743
+ "step": 4150
744
+ },
745
+ {
746
+ "epoch": 0.6819288845591817,
747
+ "grad_norm": 25.474735260009766,
748
+ "learning_rate": 3.3498547256879173e-06,
749
+ "loss": 0.45231922149658205,
750
+ "step": 4200
751
+ },
752
+ {
753
+ "epoch": 0.6900470855658386,
754
+ "grad_norm": 21.702571868896484,
755
+ "learning_rate": 3.2643992479917963e-06,
756
+ "loss": 0.46607505798339843,
757
+ "step": 4250
758
+ },
759
+ {
760
+ "epoch": 0.6981652865724955,
761
+ "grad_norm": 26.492374420166016,
762
+ "learning_rate": 3.178943770295676e-06,
763
+ "loss": 0.4621200180053711,
764
+ "step": 4300
765
+ },
766
+ {
767
+ "epoch": 0.7062834875791525,
768
+ "grad_norm": 28.608844757080078,
769
+ "learning_rate": 3.0934882925995557e-06,
770
+ "loss": 0.4604476547241211,
771
+ "step": 4350
772
+ },
773
+ {
774
+ "epoch": 0.7144016885858094,
775
+ "grad_norm": 26.382740020751953,
776
+ "learning_rate": 3.0080328149034357e-06,
777
+ "loss": 0.463820686340332,
778
+ "step": 4400
779
+ },
780
+ {
781
+ "epoch": 0.7225198895924663,
782
+ "grad_norm": 21.732534408569336,
783
+ "learning_rate": 2.922577337207315e-06,
784
+ "loss": 0.4446089172363281,
785
+ "step": 4450
786
+ },
787
+ {
788
+ "epoch": 0.7306380905991232,
789
+ "grad_norm": 24.14549446105957,
790
+ "learning_rate": 2.837121859511195e-06,
791
+ "loss": 0.4710216903686523,
792
+ "step": 4500
793
+ },
794
+ {
795
+ "epoch": 0.7306380905991232,
796
+ "eval_med-ir_cosine_accuracy@1": 0.2635,
797
+ "eval_med-ir_cosine_accuracy@10": 0.7215,
798
+ "eval_med-ir_cosine_accuracy@5": 0.5965,
799
+ "eval_med-ir_cosine_map@10": 0.4007440476190476,
800
+ "eval_med-ir_cosine_mrr@10": 0.4007440476190481,
801
+ "eval_med-ir_cosine_ndcg@10": 0.4772869175667747,
802
+ "eval_med-ir_cosine_precision@1": 0.2635,
803
+ "eval_med-ir_cosine_precision@10": 0.07215,
804
+ "eval_med-ir_cosine_precision@5": 0.1193,
805
+ "eval_med-ir_cosine_recall@1": 0.2635,
806
+ "eval_med-ir_cosine_recall@10": 0.7215,
807
+ "eval_med-ir_cosine_recall@5": 0.5965,
808
+ "eval_runtime": 53.0236,
809
+ "eval_samples_per_second": 0.0,
810
+ "eval_steps_per_second": 0.0,
811
+ "step": 4500
812
  }
813
  ],
814
  "logging_steps": 50,