Hugging Face's logo

Nadav
/
pixel-intermediate-final

Transformers
PyTorch
pixel
Model card Files
xet
Community
Nadav commited on
Commit
1173dbd
·
1 Parent(s): ae04072

Training in progress, step 80000

Browse files
Files changed (7) 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/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +139 -3
  7. 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:fa88874d16a939070903a93d5ba329854e46aadf2f7f7ea1a61905c517a19385
3
  size 893439185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb0ca75676c80a3c5fd59d0ac1080da68135ad1e20368aa04168b08561f3f84c
3
  size 893439185
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7df44f87e5182a482c9b6d3a619d67eba073218906e5c075beb6e29b9896b503
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5335ac4e09dbab38db400a30c96e423b02cd136b1548c7b0e7c7dba23f440f1
3
  size 449471589
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c007293227ea685a1b33f33dc58e5de97e57e2743aa81629ff6475f1a3723ca2
3
  size 15523
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:211fb59b20f9f9f47cec52d841a7a8969719bf6f46a4a3c547f8fd9c6b81c01d
3
  size 15523
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a7310bd5c1439c4bb35c49bf02221c2d3a79d6f2845dd008a516ce1038c5377
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c9fe17fd2766bc47b158d8b9c3151501d7d3c0213ab927e2871c909d3a891a
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:069e42e1515a55f52067d0327eb65014273d332079adda47ed8ce25758c61f85
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6997ee26ce92dcc6722ecbaf41fc375e207a59eb322cd715ff89e49540d1928e
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": 6.09596795262562,
5
- "global_step": 70000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -958,11 +958,147 @@
958
  "eval_samples_per_second": 94.174,
959
  "eval_steps_per_second": 1.488,
960
  "step": 70000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
961
  }
962
  ],
963
  "max_steps": 100000,
964
  "num_train_epochs": 9,
965
- "total_flos": 3.296694285295811e+21,
966
  "trial_name": null,
967
  "trial_params": null
968
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 6.966820517286424,
5
+ "global_step": 80000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
958
  "eval_samples_per_second": 94.174,
959
  "eval_steps_per_second": 1.488,
960
  "step": 70000
961
+ },
962
+ {
963
+ "epoch": 6.14,
964
+ "learning_rate": 2.8164551641684633e-05,
965
+ "loss": 0.3894,
966
+ "step": 70500
967
+ },
968
+ {
969
+ "epoch": 6.18,
970
+ "learning_rate": 2.75974407207991e-05,
971
+ "loss": 0.3898,
972
+ "step": 71000
973
+ },
974
+ {
975
+ "epoch": 6.23,
976
+ "learning_rate": 2.7037187352256104e-05,
977
+ "loss": 0.3908,
978
+ "step": 71500
979
+ },
980
+ {
981
+ "epoch": 6.27,
982
+ "learning_rate": 2.6483929770191072e-05,
983
+ "loss": 0.3889,
984
+ "step": 72000
985
+ },
986
+ {
987
+ "epoch": 6.31,
988
+ "learning_rate": 2.593888952531986e-05,
989
+ "loss": 0.3893,
990
+ "step": 72500
991
+ },
992
+ {
993
+ "epoch": 6.36,
994
+ "learning_rate": 2.5400016613135313e-05,
995
+ "loss": 0.389,
996
+ "step": 73000
997
+ },
998
+ {
999
+ "epoch": 6.4,
1000
+ "learning_rate": 2.486959890876619e-05,
1001
+ "loss": 0.3883,
1002
+ "step": 73500
1003
+ },
1004
+ {
1005
+ "epoch": 6.44,
1006
+ "learning_rate": 2.4345641405981582e-05,
1007
+ "loss": 0.3876,
1008
+ "step": 74000
1009
+ },
1010
+ {
1011
+ "epoch": 6.49,
1012
+ "learning_rate": 2.3829343788362732e-05,
1013
+ "loss": 0.3873,
1014
+ "step": 74500
1015
+ },
1016
+ {
1017
+ "epoch": 6.53,
1018
+ "learning_rate": 2.3320833444621267e-05,
1019
+ "loss": 0.3879,
1020
+ "step": 75000
1021
+ },
1022
+ {
1023
+ "epoch": 6.53,
1024
+ "eval_loss": 0.36915621161460876,
1025
+ "eval_runtime": 92.6839,
1026
+ "eval_samples_per_second": 53.947,
1027
+ "eval_steps_per_second": 0.852,
1028
+ "step": 75000
1029
+ },
1030
+ {
1031
+ "epoch": 6.57,
1032
+ "learning_rate": 2.2820235842075488e-05,
1033
+ "loss": 0.387,
1034
+ "step": 75500
1035
+ },
1036
+ {
1037
+ "epoch": 6.62,
1038
+ "learning_rate": 2.232767449569324e-05,
1039
+ "loss": 0.3879,
1040
+ "step": 76000
1041
+ },
1042
+ {
1043
+ "epoch": 6.66,
1044
+ "learning_rate": 2.1844231523481044e-05,
1045
+ "loss": 0.3864,
1046
+ "step": 76500
1047
+ },
1048
+ {
1049
+ "epoch": 6.71,
1050
+ "learning_rate": 2.136808860049628e-05,
1051
+ "loss": 0.3866,
1052
+ "step": 77000
1053
+ },
1054
+ {
1055
+ "epoch": 6.75,
1056
+ "learning_rate": 2.090034022927794e-05,
1057
+ "loss": 0.3859,
1058
+ "step": 77500
1059
+ },
1060
+ {
1061
+ "epoch": 6.79,
1062
+ "learning_rate": 2.044110181973758e-05,
1063
+ "loss": 0.3865,
1064
+ "step": 78000
1065
+ },
1066
+ {
1067
+ "epoch": 6.84,
1068
+ "learning_rate": 1.9990486682081012e-05,
1069
+ "loss": 0.3857,
1070
+ "step": 78500
1071
+ },
1072
+ {
1073
+ "epoch": 6.88,
1074
+ "learning_rate": 1.954860599885074e-05,
1075
+ "loss": 0.3855,
1076
+ "step": 79000
1077
+ },
1078
+ {
1079
+ "epoch": 6.92,
1080
+ "learning_rate": 1.9115568797493368e-05,
1081
+ "loss": 0.3852,
1082
+ "step": 79500
1083
+ },
1084
+ {
1085
+ "epoch": 6.97,
1086
+ "learning_rate": 1.8691481923458633e-05,
1087
+ "loss": 0.3852,
1088
+ "step": 80000
1089
+ },
1090
+ {
1091
+ "epoch": 6.97,
1092
+ "eval_loss": 0.36661282181739807,
1093
+ "eval_runtime": 95.3348,
1094
+ "eval_samples_per_second": 52.447,
1095
+ "eval_steps_per_second": 0.829,
1096
+ "step": 80000
1097
  }
1098
  ],
1099
  "max_steps": 100000,
1100
  "num_train_epochs": 9,
1101
+ "total_flos": 3.767680420025334e+21,
1102
  "trial_name": null,
1103
  "trial_params": null
1104
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7df44f87e5182a482c9b6d3a619d67eba073218906e5c075beb6e29b9896b503
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5335ac4e09dbab38db400a30c96e423b02cd136b1548c7b0e7c7dba23f440f1
3
  size 449471589