Hugging Face's logo

saracandu
/
stldec_arch

Feature Extraction
Transformers
PyTorch
stl_decoder
Generated from Trainer
custom_code
Model card Files
xet
 Community
saracandu commited on
Commit
e767df4
·
verified ·
1 Parent(s): 41024f9

Training in progress, step 1100, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +84 -6
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:989b199a9d30b337b57bc56dea8e60214c10e035fe531cbbb77ef727a3f82898
3
  size 1612184459
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fb4cd3b1d78cb0816c39ef003ab53b8ae08769e33615bf455f65ec403c41a76
3
  size 1612184459
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e8ecd4defca33a75595b9929eaa1e80d6bd7fbc3a99d5ae08a0f2f3ff2fce5f
3
  size 806069967
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8042cf773a88797bf12afa0e975656e63f2b356c607863a88446df0c831bf382
3
  size 806069967
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdf052ef21939bc7d4a1497b5f5612f3a9c9e43746d708d964a6b27b49c3879f
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:917e7ec1f1118c79f5f3a967a1e5f6ec4c23907e66646672e2d945c83b73cf00
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14c2c189e2a24b6b81578cf27a2f3af7ab219bb12f0077ef81162dfa79412318
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4859e92507ab2ef6badf77c5dcbe8ea573cb856ba5a1cb64d4fdd1ad8d5dbd02
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 1000,
3
- "best_metric": 1.2283990383148193,
4
- "best_model_checkpoint": "/share/ai-lab/scandussio/stldec_training/results/checkpoint-1000",
5
- "epoch": 6.454176804541768,
6
  "eval_steps": 100,
7
- "global_step": 1000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -795,6 +795,84 @@
795
  "eval_samples_per_second": 27.373,
796
  "eval_steps_per_second": 0.858,
797
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
798
  }
799
  ],
800
  "logging_steps": 10,
@@ -814,7 +892,7 @@
814
  "attributes": {}
815
  }
816
  },
817
- "total_flos": 3.151707290688553e+17,
818
  "train_batch_size": 32,
819
  "trial_name": null,
820
  "trial_params": null
 
1
  {
2
+ "best_global_step": 1100,
3
+ "best_metric": 1.1955561637878418,
4
+ "best_model_checkpoint": "/share/ai-lab/scandussio/stldec_training/results/checkpoint-1100",
5
+ "epoch": 7.097323600973236,
6
  "eval_steps": 100,
7
+ "global_step": 1100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
795
  "eval_samples_per_second": 27.373,
796
  "eval_steps_per_second": 0.858,
797
  "step": 1000
798
+ },
799
+ {
800
+ "epoch": 6.519059205190592,
801
+ "grad_norm": 61.72404098510742,
802
+ "learning_rate": 3.4903225806451617e-06,
803
+ "loss": 20.4522,
804
+ "step": 1010
805
+ },
806
+ {
807
+ "epoch": 6.583941605839416,
808
+ "grad_norm": 91.92382049560547,
809
+ "learning_rate": 3.4258064516129034e-06,
810
+ "loss": 20.4535,
811
+ "step": 1020
812
+ },
813
+ {
814
+ "epoch": 6.6488240064882405,
815
+ "grad_norm": 54.138492584228516,
816
+ "learning_rate": 3.3612903225806455e-06,
817
+ "loss": 20.2751,
818
+ "step": 1030
819
+ },
820
+ {
821
+ "epoch": 6.713706407137064,
822
+ "grad_norm": 79.81719970703125,
823
+ "learning_rate": 3.296774193548387e-06,
824
+ "loss": 20.127,
825
+ "step": 1040
826
+ },
827
+ {
828
+ "epoch": 6.778588807785888,
829
+ "grad_norm": 47.51918029785156,
830
+ "learning_rate": 3.2322580645161292e-06,
831
+ "loss": 20.0629,
832
+ "step": 1050
833
+ },
834
+ {
835
+ "epoch": 6.843471208434712,
836
+ "grad_norm": 80.06061553955078,
837
+ "learning_rate": 3.1677419354838713e-06,
838
+ "loss": 20.0692,
839
+ "step": 1060
840
+ },
841
+ {
842
+ "epoch": 6.9083536090835365,
843
+ "grad_norm": 37.80568313598633,
844
+ "learning_rate": 3.103225806451613e-06,
845
+ "loss": 19.9451,
846
+ "step": 1070
847
+ },
848
+ {
849
+ "epoch": 6.97323600973236,
850
+ "grad_norm": 123.99601745605469,
851
+ "learning_rate": 3.0387096774193555e-06,
852
+ "loss": 19.8684,
853
+ "step": 1080
854
+ },
855
+ {
856
+ "epoch": 7.032441200324412,
857
+ "grad_norm": 283.00970458984375,
858
+ "learning_rate": 2.974193548387097e-06,
859
+ "loss": 18.2299,
860
+ "step": 1090
861
+ },
862
+ {
863
+ "epoch": 7.097323600973236,
864
+ "grad_norm": 175.4154510498047,
865
+ "learning_rate": 2.909677419354839e-06,
866
+ "loss": 19.8532,
867
+ "step": 1100
868
+ },
869
+ {
870
+ "epoch": 7.097323600973236,
871
+ "eval_loss": 1.1955561637878418,
872
+ "eval_runtime": 109.5917,
873
+ "eval_samples_per_second": 27.374,
874
+ "eval_steps_per_second": 0.858,
875
+ "step": 1100
876
  }
877
  ],
878
  "logging_steps": 10,
 
892
  "attributes": {}
893
  }
894
  },
895
+ "total_flos": 3.465741725199237e+17,
896
  "train_batch_size": 32,
897
  "trial_name": null,
898
  "trial_params": null