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
bfc56ba
·
verified ·
1 Parent(s): ffa9c57

latest = step 5000 (nDCG@10=0.4835)

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 sha256:6ac99815f060d8a4c0706c9f7dee2a75eb400f3f3112fb6c244d179c52b0ce78
3
  size 280019040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aca00d4230b13011e91ba90c5489154fbdd2cffc3ee2ebedce3d24ba9aa01417
3
  size 280019040
trainer_state.json CHANGED
@@ -1,10 +1,10 @@
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,
@@ -809,6 +809,95 @@
809
  "eval_samples_per_second": 0.0,
810
  "eval_steps_per_second": 0.0,
811
  "step": 4500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
812
  }
813
  ],
814
  "logging_steps": 50,
 
1
  {
2
+ "best_global_step": 5000,
3
+ "best_metric": 0.48354546858168634,
4
+ "best_model_checkpoint": "checkpoints/med-ruri-v3-70m-v2-from-ruri/checkpoint-5000",
5
+ "epoch": 0.8118201006656924,
6
  "eval_steps": 500,
7
+ "global_step": 5000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
809
  "eval_samples_per_second": 0.0,
810
  "eval_steps_per_second": 0.0,
811
  "step": 4500
812
+ },
813
+ {
814
+ "epoch": 0.7387562916057802,
815
+ "grad_norm": 31.583993911743164,
816
+ "learning_rate": 2.7516663818150746e-06,
817
+ "loss": 0.4457337188720703,
818
+ "step": 4550
819
+ },
820
+ {
821
+ "epoch": 0.7468744926124371,
822
+ "grad_norm": 27.630840301513672,
823
+ "learning_rate": 2.6662109041189545e-06,
824
+ "loss": 0.4375724792480469,
825
+ "step": 4600
826
+ },
827
+ {
828
+ "epoch": 0.754992693619094,
829
+ "grad_norm": 23.815793991088867,
830
+ "learning_rate": 2.580755426422834e-06,
831
+ "loss": 0.44040355682373045,
832
+ "step": 4650
833
+ },
834
+ {
835
+ "epoch": 0.7631108946257509,
836
+ "grad_norm": 24.27130699157715,
837
+ "learning_rate": 2.4952999487267135e-06,
838
+ "loss": 0.4479870986938477,
839
+ "step": 4700
840
+ },
841
+ {
842
+ "epoch": 0.7712290956324078,
843
+ "grad_norm": 27.412614822387695,
844
+ "learning_rate": 2.4098444710305934e-06,
845
+ "loss": 0.4310578155517578,
846
+ "step": 4750
847
+ },
848
+ {
849
+ "epoch": 0.7793472966390648,
850
+ "grad_norm": 26.207399368286133,
851
+ "learning_rate": 2.324388993334473e-06,
852
+ "loss": 0.4327563858032227,
853
+ "step": 4800
854
+ },
855
+ {
856
+ "epoch": 0.7874654976457217,
857
+ "grad_norm": 29.552608489990234,
858
+ "learning_rate": 2.238933515638353e-06,
859
+ "loss": 0.4346369934082031,
860
+ "step": 4850
861
+ },
862
+ {
863
+ "epoch": 0.7955836986523787,
864
+ "grad_norm": 26.583375930786133,
865
+ "learning_rate": 2.1534780379422323e-06,
866
+ "loss": 0.45013832092285155,
867
+ "step": 4900
868
+ },
869
+ {
870
+ "epoch": 0.8037018996590356,
871
+ "grad_norm": 23.350200653076172,
872
+ "learning_rate": 2.068022560246112e-06,
873
+ "loss": 0.42036319732666017,
874
+ "step": 4950
875
+ },
876
+ {
877
+ "epoch": 0.8118201006656924,
878
+ "grad_norm": 27.207698822021484,
879
+ "learning_rate": 1.9825670825499917e-06,
880
+ "loss": 0.4029704666137695,
881
+ "step": 5000
882
+ },
883
+ {
884
+ "epoch": 0.8118201006656924,
885
+ "eval_med-ir_cosine_accuracy@1": 0.264,
886
+ "eval_med-ir_cosine_accuracy@10": 0.7295,
887
+ "eval_med-ir_cosine_accuracy@5": 0.604,
888
+ "eval_med-ir_cosine_map@10": 0.4062333333333333,
889
+ "eval_med-ir_cosine_mrr@10": 0.40623333333333406,
890
+ "eval_med-ir_cosine_ndcg@10": 0.48354546858168634,
891
+ "eval_med-ir_cosine_precision@1": 0.264,
892
+ "eval_med-ir_cosine_precision@10": 0.07294999999999999,
893
+ "eval_med-ir_cosine_precision@5": 0.12079999999999998,
894
+ "eval_med-ir_cosine_recall@1": 0.264,
895
+ "eval_med-ir_cosine_recall@10": 0.7295,
896
+ "eval_med-ir_cosine_recall@5": 0.604,
897
+ "eval_runtime": 53.0815,
898
+ "eval_samples_per_second": 0.0,
899
+ "eval_steps_per_second": 0.0,
900
+ "step": 5000
901
  }
902
  ],
903
  "logging_steps": 50,