Hugging Face's logo

SaladTechnologies
/
fable-base

Token Classification
Safetensors
English
deberta-v2
Model card Files
xet
 Community
shawnrushefsky commited on
Commit
7577c21
·
1 Parent(s): de9d1a6

checkpoint

Browse files
Files changed (6) hide show
  1. {checkpoint-5018 → checkpoint-6176}/added_tokens.json +0 -0
  2. {checkpoint-5018 → checkpoint-6176}/config.json +0 -0
  3. {checkpoint-5018 → checkpoint-6176}/special_tokens_map.json +0 -0
  4. {checkpoint-5018 → checkpoint-6176}/tokenizer.json +0 -0
  5. {checkpoint-5018 → checkpoint-6176}/tokenizer_config.json +0 -0
  6. {checkpoint-5018 → checkpoint-6176}/trainer_state.json +164 -3
{checkpoint-5018 → checkpoint-6176}/added_tokens.json RENAMED
File without changes
{checkpoint-5018 → checkpoint-6176}/config.json RENAMED
File without changes
{checkpoint-5018 → checkpoint-6176}/special_tokens_map.json RENAMED
File without changes
{checkpoint-5018 → checkpoint-6176}/tokenizer.json RENAMED
File without changes
{checkpoint-5018 → checkpoint-6176}/tokenizer_config.json RENAMED
File without changes
{checkpoint-5018 → checkpoint-6176}/trainer_state.json RENAMED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.651603687832749,
6
  "eval_steps": 500,
7
- "global_step": 5018,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -708,6 +708,167 @@
708
  "learning_rate": 1.7632416787264833e-05,
709
  "loss": 0.1984,
710
  "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
711
  }
712
  ],
713
  "logging_steps": 50,
@@ -727,7 +888,7 @@
727
  "attributes": {}
728
  }
729
  },
730
- "total_flos": 4.196367688836055e+17,
731
  "train_batch_size": 40,
732
  "trial_name": null,
733
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8019737696403064,
6
  "eval_steps": 500,
7
+ "global_step": 6176,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
708
  "learning_rate": 1.7632416787264833e-05,
709
  "loss": 0.1984,
710
  "step": 5000
711
+ },
712
+ {
713
+ "epoch": 0.6557589923386573,
714
+ "grad_norm": 0.8022367358207703,
715
+ "learning_rate": 1.7606104459939485e-05,
716
+ "loss": 0.2053,
717
+ "step": 5050
718
+ },
719
+ {
720
+ "epoch": 0.6622516556291391,
721
+ "grad_norm": 0.6432430148124695,
722
+ "learning_rate": 1.757979213261413e-05,
723
+ "loss": 0.1991,
724
+ "step": 5100
725
+ },
726
+ {
727
+ "epoch": 0.6687443189196208,
728
+ "grad_norm": 0.7671304941177368,
729
+ "learning_rate": 1.755347980528878e-05,
730
+ "loss": 0.2064,
731
+ "step": 5150
732
+ },
733
+ {
734
+ "epoch": 0.6752369822101025,
735
+ "grad_norm": 0.5107030272483826,
736
+ "learning_rate": 1.7527167477963426e-05,
737
+ "loss": 0.2049,
738
+ "step": 5200
739
+ },
740
+ {
741
+ "epoch": 0.6817296455005843,
742
+ "grad_norm": 0.7239235639572144,
743
+ "learning_rate": 1.7500855150638075e-05,
744
+ "loss": 0.2001,
745
+ "step": 5250
746
+ },
747
+ {
748
+ "epoch": 0.688222308791066,
749
+ "grad_norm": 0.6116129755973816,
750
+ "learning_rate": 1.7474542823312723e-05,
751
+ "loss": 0.2193,
752
+ "step": 5300
753
+ },
754
+ {
755
+ "epoch": 0.6947149720815479,
756
+ "grad_norm": 0.5425911545753479,
757
+ "learning_rate": 1.744823049598737e-05,
758
+ "loss": 0.2001,
759
+ "step": 5350
760
+ },
761
+ {
762
+ "epoch": 0.7012076353720296,
763
+ "grad_norm": 0.6464748382568359,
764
+ "learning_rate": 1.742191816866202e-05,
765
+ "loss": 0.1963,
766
+ "step": 5400
767
+ },
768
+ {
769
+ "epoch": 0.7077002986625114,
770
+ "grad_norm": 0.8812252879142761,
771
+ "learning_rate": 1.7395605841336668e-05,
772
+ "loss": 0.196,
773
+ "step": 5450
774
+ },
775
+ {
776
+ "epoch": 0.7141929619529931,
777
+ "grad_norm": 0.6928241848945618,
778
+ "learning_rate": 1.7369293514011316e-05,
779
+ "loss": 0.2011,
780
+ "step": 5500
781
+ },
782
+ {
783
+ "epoch": 0.7206856252434749,
784
+ "grad_norm": 0.6892450451850891,
785
+ "learning_rate": 1.7342981186685965e-05,
786
+ "loss": 0.1949,
787
+ "step": 5550
788
+ },
789
+ {
790
+ "epoch": 0.7271782885339566,
791
+ "grad_norm": 0.4782065749168396,
792
+ "learning_rate": 1.7316668859360613e-05,
793
+ "loss": 0.194,
794
+ "step": 5600
795
+ },
796
+ {
797
+ "epoch": 0.7336709518244384,
798
+ "grad_norm": 0.6438505053520203,
799
+ "learning_rate": 1.729035653203526e-05,
800
+ "loss": 0.1967,
801
+ "step": 5650
802
+ },
803
+ {
804
+ "epoch": 0.7401636151149201,
805
+ "grad_norm": 0.5797818899154663,
806
+ "learning_rate": 1.726404420470991e-05,
807
+ "loss": 0.2185,
808
+ "step": 5700
809
+ },
810
+ {
811
+ "epoch": 0.7466562784054019,
812
+ "grad_norm": 0.6884586811065674,
813
+ "learning_rate": 1.7237731877384554e-05,
814
+ "loss": 0.1977,
815
+ "step": 5750
816
+ },
817
+ {
818
+ "epoch": 0.7531489416958836,
819
+ "grad_norm": 0.648883581161499,
820
+ "learning_rate": 1.7211419550059206e-05,
821
+ "loss": 0.1964,
822
+ "step": 5800
823
+ },
824
+ {
825
+ "epoch": 0.7596416049863655,
826
+ "grad_norm": 0.6440086960792542,
827
+ "learning_rate": 1.718510722273385e-05,
828
+ "loss": 0.2014,
829
+ "step": 5850
830
+ },
831
+ {
832
+ "epoch": 0.7661342682768472,
833
+ "grad_norm": 0.5619300007820129,
834
+ "learning_rate": 1.71587948954085e-05,
835
+ "loss": 0.1909,
836
+ "step": 5900
837
+ },
838
+ {
839
+ "epoch": 0.7726269315673289,
840
+ "grad_norm": 0.6859204769134521,
841
+ "learning_rate": 1.7132482568083147e-05,
842
+ "loss": 0.2049,
843
+ "step": 5950
844
+ },
845
+ {
846
+ "epoch": 0.7791195948578107,
847
+ "grad_norm": 0.6132592558860779,
848
+ "learning_rate": 1.7106170240757796e-05,
849
+ "loss": 0.2,
850
+ "step": 6000
851
+ },
852
+ {
853
+ "epoch": 0.7856122581482924,
854
+ "grad_norm": 0.7050901055335999,
855
+ "learning_rate": 1.7079857913432444e-05,
856
+ "loss": 0.189,
857
+ "step": 6050
858
+ },
859
+ {
860
+ "epoch": 0.7921049214387742,
861
+ "grad_norm": 0.6752614974975586,
862
+ "learning_rate": 1.7053545586107092e-05,
863
+ "loss": 0.2248,
864
+ "step": 6100
865
+ },
866
+ {
867
+ "epoch": 0.7985975847292559,
868
+ "grad_norm": 0.7186923623085022,
869
+ "learning_rate": 1.702723325878174e-05,
870
+ "loss": 0.1903,
871
+ "step": 6150
872
  }
873
  ],
874
  "logging_steps": 50,
 
888
  "attributes": {}
889
  }
890
  },
891
+ "total_flos": 5.1647602330330726e+17,
892
  "train_batch_size": 40,
893
  "trial_name": null,
894
  "trial_params": null