Hugging Face's logo

Team-PIXEL
/
pixel-base-bigrams

Transformers
PyTorch
pixel
Model card Files
xet
 Community
1
jflotz commited on
Commit
2ce75ec
·
1 Parent(s): ede1815

Training in progress, step 550000

Browse files
Files changed (13) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/rng_state_4.pth +1 -1
  8. last-checkpoint/rng_state_5.pth +1 -1
  9. last-checkpoint/rng_state_6.pth +1 -1
  10. last-checkpoint/rng_state_7.pth +1 -1
  11. last-checkpoint/scheduler.pt +1 -1
  12. last-checkpoint/trainer_state.json +203 -3
  13. pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1b31bd7dde490a5110587d96c397be4c71707a6ecb631cd33ee86c661a68ad1
3
  size 893439185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ed2d2ebacd7c7bc94a9d5b359875612bcd82c11229aa6d78716aa5ee16a33b
3
  size 893439185
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbfb5da6ba6005b792e538207aa26a055cb4e4f7a70c384ed7bc2a20c6abef6f
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b156aacca311d8af63ef36e1ded9f1bccccc04c94ee9871c381f73fe7e5ad577
3
  size 449471589
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
3
  size 14503
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
3
  size 14503
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
3
  size 14503
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
3
  size 14503
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
3
  size 14503
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
3
  size 14503
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
3
  size 14503
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:312a9240a59bfb6f588851dc4640a2bea628ee45c54031017e35bcac8788a581
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de7df7ff53e44669a043f69e39b55baa82d81ac1777f09e2f6159ffcb51dd66
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 6.0225511080378755,
5
- "global_step": 540000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -10806,11 +10806,211 @@
10806
  "eval_samples_per_second": 912.43,
10807
  "eval_steps_per_second": 14.3,
10808
  "step": 540000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10809
  }
10810
  ],
10811
  "max_steps": 1000000,
10812
  "num_train_epochs": 12,
10813
- "total_flos": 3.785381236953652e+22,
10814
  "trial_name": null,
10815
  "trial_params": null
10816
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 6.134079832260799,
5
+ "global_step": 550000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
10806
  "eval_samples_per_second": 912.43,
10807
  "eval_steps_per_second": 14.3,
10808
  "step": 540000
10809
+ },
10810
+ {
10811
+ "epoch": 6.03,
10812
+ "learning_rate": 7.641354145023687e-05,
10813
+ "loss": 0.2072,
10814
+ "step": 540500
10815
+ },
10816
+ {
10817
+ "epoch": 6.03,
10818
+ "learning_rate": 7.629795553284005e-05,
10819
+ "loss": 0.2071,
10820
+ "step": 541000
10821
+ },
10822
+ {
10823
+ "epoch": 6.03,
10824
+ "eval_loss": 0.19721636176109314,
10825
+ "eval_runtime": 2.791,
10826
+ "eval_samples_per_second": 822.988,
10827
+ "eval_steps_per_second": 12.898,
10828
+ "step": 541000
10829
+ },
10830
+ {
10831
+ "epoch": 6.04,
10832
+ "learning_rate": 7.61823797366914e-05,
10833
+ "loss": 0.2071,
10834
+ "step": 541500
10835
+ },
10836
+ {
10837
+ "epoch": 6.04,
10838
+ "learning_rate": 7.606681437777081e-05,
10839
+ "loss": 0.2067,
10840
+ "step": 542000
10841
+ },
10842
+ {
10843
+ "epoch": 6.04,
10844
+ "eval_loss": 0.19431854784488678,
10845
+ "eval_runtime": 2.5424,
10846
+ "eval_samples_per_second": 903.464,
10847
+ "eval_steps_per_second": 14.16,
10848
+ "step": 542000
10849
+ },
10850
+ {
10851
+ "epoch": 6.05,
10852
+ "learning_rate": 7.595125977202952e-05,
10853
+ "loss": 0.207,
10854
+ "step": 542500
10855
+ },
10856
+ {
10857
+ "epoch": 6.06,
10858
+ "learning_rate": 7.583571623538939e-05,
10859
+ "loss": 0.2073,
10860
+ "step": 543000
10861
+ },
10862
+ {
10863
+ "epoch": 6.06,
10864
+ "eval_loss": 0.1961280107498169,
10865
+ "eval_runtime": 2.5047,
10866
+ "eval_samples_per_second": 917.065,
10867
+ "eval_steps_per_second": 14.373,
10868
+ "step": 543000
10869
+ },
10870
+ {
10871
+ "epoch": 6.06,
10872
+ "learning_rate": 7.572018408374208e-05,
10873
+ "loss": 0.2069,
10874
+ "step": 543500
10875
+ },
10876
+ {
10877
+ "epoch": 6.07,
10878
+ "learning_rate": 7.560466363294806e-05,
10879
+ "loss": 0.2068,
10880
+ "step": 544000
10881
+ },
10882
+ {
10883
+ "epoch": 6.07,
10884
+ "eval_loss": 0.19669890403747559,
10885
+ "eval_runtime": 2.4907,
10886
+ "eval_samples_per_second": 922.238,
10887
+ "eval_steps_per_second": 14.454,
10888
+ "step": 544000
10889
+ },
10890
+ {
10891
+ "epoch": 6.07,
10892
+ "learning_rate": 7.548915519883582e-05,
10893
+ "loss": 0.2066,
10894
+ "step": 544500
10895
+ },
10896
+ {
10897
+ "epoch": 6.08,
10898
+ "learning_rate": 7.537365909720104e-05,
10899
+ "loss": 0.2065,
10900
+ "step": 545000
10901
+ },
10902
+ {
10903
+ "epoch": 6.08,
10904
+ "eval_loss": 0.1973814219236374,
10905
+ "eval_runtime": 2.6437,
10906
+ "eval_samples_per_second": 868.843,
10907
+ "eval_steps_per_second": 13.617,
10908
+ "step": 545000
10909
+ },
10910
+ {
10911
+ "epoch": 6.08,
10912
+ "learning_rate": 7.525817564380562e-05,
10913
+ "loss": 0.2068,
10914
+ "step": 545500
10915
+ },
10916
+ {
10917
+ "epoch": 6.09,
10918
+ "learning_rate": 7.514270515437691e-05,
10919
+ "loss": 0.2062,
10920
+ "step": 546000
10921
+ },
10922
+ {
10923
+ "epoch": 6.09,
10924
+ "eval_loss": 0.19645407795906067,
10925
+ "eval_runtime": 2.6493,
10926
+ "eval_samples_per_second": 867.035,
10927
+ "eval_steps_per_second": 13.589,
10928
+ "step": 546000
10929
+ },
10930
+ {
10931
+ "epoch": 6.1,
10932
+ "learning_rate": 7.502724794460685e-05,
10933
+ "loss": 0.2066,
10934
+ "step": 546500
10935
+ },
10936
+ {
10937
+ "epoch": 6.1,
10938
+ "learning_rate": 7.491180433015101e-05,
10939
+ "loss": 0.2062,
10940
+ "step": 547000
10941
+ },
10942
+ {
10943
+ "epoch": 6.1,
10944
+ "eval_loss": 0.19736704230308533,
10945
+ "eval_runtime": 2.5133,
10946
+ "eval_samples_per_second": 913.953,
10947
+ "eval_steps_per_second": 14.324,
10948
+ "step": 547000
10949
+ },
10950
+ {
10951
+ "epoch": 6.11,
10952
+ "learning_rate": 7.479637462662786e-05,
10953
+ "loss": 0.2065,
10954
+ "step": 547500
10955
+ },
10956
+ {
10957
+ "epoch": 6.11,
10958
+ "learning_rate": 7.468095914961777e-05,
10959
+ "loss": 0.2063,
10960
+ "step": 548000
10961
+ },
10962
+ {
10963
+ "epoch": 6.11,
10964
+ "eval_loss": 0.19768109917640686,
10965
+ "eval_runtime": 2.5796,
10966
+ "eval_samples_per_second": 890.452,
10967
+ "eval_steps_per_second": 13.956,
10968
+ "step": 548000
10969
+ },
10970
+ {
10971
+ "epoch": 6.12,
10972
+ "learning_rate": 7.456555821466225e-05,
10973
+ "loss": 0.2063,
10974
+ "step": 548500
10975
+ },
10976
+ {
10977
+ "epoch": 6.12,
10978
+ "learning_rate": 7.445017213726307e-05,
10979
+ "loss": 0.2068,
10980
+ "step": 549000
10981
+ },
10982
+ {
10983
+ "epoch": 6.12,
10984
+ "eval_loss": 0.19542047381401062,
10985
+ "eval_runtime": 2.4958,
10986
+ "eval_samples_per_second": 920.364,
10987
+ "eval_steps_per_second": 14.425,
10988
+ "step": 549000
10989
+ },
10990
+ {
10991
+ "epoch": 6.13,
10992
+ "learning_rate": 7.433480123288138e-05,
10993
+ "loss": 0.2065,
10994
+ "step": 549500
10995
+ },
10996
+ {
10997
+ "epoch": 6.13,
10998
+ "learning_rate": 7.421944581693674e-05,
10999
+ "loss": 0.2062,
11000
+ "step": 550000
11001
+ },
11002
+ {
11003
+ "epoch": 6.13,
11004
+ "eval_loss": 0.19721828401088715,
11005
+ "eval_runtime": 2.5551,
11006
+ "eval_samples_per_second": 898.971,
11007
+ "eval_steps_per_second": 14.089,
11008
+ "step": 550000
11009
  }
11010
  ],
11011
  "max_steps": 1000000,
11012
  "num_train_epochs": 12,
11013
+ "total_flos": 3.855481497983999e+22,
11014
  "trial_name": null,
11015
  "trial_params": null
11016
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbfb5da6ba6005b792e538207aa26a055cb4e4f7a70c384ed7bc2a20c6abef6f
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b156aacca311d8af63ef36e1ded9f1bccccc04c94ee9871c381f73fe7e5ad577
3
  size 449471589