Hugging Face's logo

Team-PIXEL
/
pixel-tiny-continuous

Transformers
PyTorch
pixel
masked-auto-encoding
generated_from_trainer
Inference Endpoints
Model card Files Community
plip commited on
Commit
bb9af02
•
1 Parent(s): 6faaef4

Training in progress, step 210000

Browse files
Files changed (17) hide show
  1. config.json +1 -0
  2. last-checkpoint/config.json +1 -0
  3. last-checkpoint/optimizer.pt +1 -1
  4. last-checkpoint/pytorch_model.bin +1 -1
  5. last-checkpoint/rng_state_0.pth +1 -1
  6. last-checkpoint/rng_state_1.pth +1 -1
  7. last-checkpoint/rng_state_2.pth +1 -1
  8. last-checkpoint/rng_state_3.pth +1 -1
  9. last-checkpoint/rng_state_4.pth +1 -1
  10. last-checkpoint/rng_state_5.pth +1 -1
  11. last-checkpoint/rng_state_6.pth +1 -1
  12. last-checkpoint/rng_state_7.pth +1 -1
  13. last-checkpoint/scheduler.pt +1 -1
  14. last-checkpoint/trainer_state.json +203 -3
  15. last-checkpoint/training_args.bin +1 -1
  16. pytorch_model.bin +1 -1
  17. training_args.bin +1 -1
config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "PIXELForPreTraining"
4
  ],
 
1
  {
2
+ "_name_or_path": "/scratch/project/dd-23-53/experiments/pixel-tiny/checkpoint-200000",
3
  "architectures": [
4
  "PIXELForPreTraining"
5
  ],
last-checkpoint/config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "PIXELForPreTraining"
4
  ],
 
1
  {
2
+ "_name_or_path": "/scratch/project/dd-23-53/experiments/pixel-tiny/checkpoint-200000",
3
  "architectures": [
4
  "PIXELForPreTraining"
5
  ],
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58f5bbc2fa5a6564ba72b2ae51852d2cf5c1476db0b209d90ec27efd86c1832a
3
  size 50044689
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66ea72ff9e74c18693c50d5eb4597b71e5592e11fe45a57df3b66e628d51f20
3
  size 50044689
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:814e92d04e78b6c50be49334aded8445cc7160900174a209d8b6a93d4efe04ca
3
  size 25761253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b982cc265a7352e00ddc20a71748aff08f14dba0f3f3245909d1fbdbc876456
3
  size 25761253
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
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 sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
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 sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
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 sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
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 sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
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 sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
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 sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
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 sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c550723a62ae0c4012004470c1ebd8187b99ec43cbd02d108f19a1f1901da5d8
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e266918cfc5cefb1731026fc3b803b3fe8a8f730b53e3407c9a310dee0fdb3
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": 12.254901960784313,
5
- "global_step": 200000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -4006,11 +4006,211 @@
4006
  "eval_samples_per_second": 787.882,
4007
  "eval_steps_per_second": 12.606,
4008
  "step": 200000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4009
  }
4010
  ],
4011
  "max_steps": 250000,
4012
  "num_train_epochs": 16,
4013
- "total_flos": 3.2032399312727006e+21,
4014
  "trial_name": null,
4015
  "trial_params": null
4016
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 12.867647058823529,
5
+ "global_step": 210000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
4006
  "eval_samples_per_second": 787.882,
4007
  "eval_steps_per_second": 12.606,
4008
  "step": 200000
4009
+ },
4010
+ {
4011
+ "epoch": 12.29,
4012
+ "learning_rate": 7.101026312557103e-05,
4013
+ "loss": 0.4433,
4014
+ "step": 200500
4015
+ },
4016
+ {
4017
+ "epoch": 12.32,
4018
+ "learning_rate": 6.982721199219075e-05,
4019
+ "loss": 0.4434,
4020
+ "step": 201000
4021
+ },
4022
+ {
4023
+ "epoch": 12.32,
4024
+ "eval_loss": 0.8013458251953125,
4025
+ "eval_runtime": 1.4369,
4026
+ "eval_samples_per_second": 695.945,
4027
+ "eval_steps_per_second": 11.135,
4028
+ "step": 201000
4029
+ },
4030
+ {
4031
+ "epoch": 12.35,
4032
+ "learning_rate": 6.865444807841203e-05,
4033
+ "loss": 0.4434,
4034
+ "step": 201500
4035
+ },
4036
+ {
4037
+ "epoch": 12.38,
4038
+ "learning_rate": 6.749202268472787e-05,
4039
+ "loss": 0.4432,
4040
+ "step": 202000
4041
+ },
4042
+ {
4043
+ "epoch": 12.38,
4044
+ "eval_loss": 0.7986797094345093,
4045
+ "eval_runtime": 1.2992,
4046
+ "eval_samples_per_second": 769.697,
4047
+ "eval_steps_per_second": 12.315,
4048
+ "step": 202000
4049
+ },
4050
+ {
4051
+ "epoch": 12.41,
4052
+ "learning_rate": 6.633998665939053e-05,
4053
+ "loss": 0.4433,
4054
+ "step": 202500
4055
+ },
4056
+ {
4057
+ "epoch": 12.44,
4058
+ "learning_rate": 6.519839039618793e-05,
4059
+ "loss": 0.443,
4060
+ "step": 203000
4061
+ },
4062
+ {
4063
+ "epoch": 12.44,
4064
+ "eval_loss": 0.7961978316307068,
4065
+ "eval_runtime": 1.3561,
4066
+ "eval_samples_per_second": 737.396,
4067
+ "eval_steps_per_second": 11.798,
4068
+ "step": 203000
4069
+ },
4070
+ {
4071
+ "epoch": 12.47,
4072
+ "learning_rate": 6.406728383223897e-05,
4073
+ "loss": 0.4431,
4074
+ "step": 203500
4075
+ },
4076
+ {
4077
+ "epoch": 12.5,
4078
+ "learning_rate": 6.294671644580888e-05,
4079
+ "loss": 0.443,
4080
+ "step": 204000
4081
+ },
4082
+ {
4083
+ "epoch": 12.5,
4084
+ "eval_loss": 0.8016523122787476,
4085
+ "eval_runtime": 1.3833,
4086
+ "eval_samples_per_second": 722.928,
4087
+ "eval_steps_per_second": 11.567,
4088
+ "step": 204000
4089
+ },
4090
+ {
4091
+ "epoch": 12.53,
4092
+ "learning_rate": 6.18367372541454e-05,
4093
+ "loss": 0.443,
4094
+ "step": 204500
4095
+ },
4096
+ {
4097
+ "epoch": 12.56,
4098
+ "learning_rate": 6.073739481133408e-05,
4099
+ "loss": 0.4429,
4100
+ "step": 205000
4101
+ },
4102
+ {
4103
+ "epoch": 12.56,
4104
+ "eval_loss": 0.7996025681495667,
4105
+ "eval_runtime": 1.274,
4106
+ "eval_samples_per_second": 784.9,
4107
+ "eval_steps_per_second": 12.558,
4108
+ "step": 205000
4109
+ },
4110
+ {
4111
+ "epoch": 12.59,
4112
+ "learning_rate": 5.96487372061749e-05,
4113
+ "loss": 0.4428,
4114
+ "step": 205500
4115
+ },
4116
+ {
4117
+ "epoch": 12.62,
4118
+ "learning_rate": 5.857081206007811e-05,
4119
+ "loss": 0.4428,
4120
+ "step": 206000
4121
+ },
4122
+ {
4123
+ "epoch": 12.62,
4124
+ "eval_loss": 0.7997360229492188,
4125
+ "eval_runtime": 1.3318,
4126
+ "eval_samples_per_second": 750.873,
4127
+ "eval_steps_per_second": 12.014,
4128
+ "step": 206000
4129
+ },
4130
+ {
4131
+ "epoch": 12.65,
4132
+ "learning_rate": 5.750366652498169e-05,
4133
+ "loss": 0.4426,
4134
+ "step": 206500
4135
+ },
4136
+ {
4137
+ "epoch": 12.68,
4138
+ "learning_rate": 5.6447347281288474e-05,
4139
+ "loss": 0.4425,
4140
+ "step": 207000
4141
+ },
4142
+ {
4143
+ "epoch": 12.68,
4144
+ "eval_loss": 0.801701009273529,
4145
+ "eval_runtime": 1.3022,
4146
+ "eval_samples_per_second": 767.911,
4147
+ "eval_steps_per_second": 12.287,
4148
+ "step": 207000
4149
+ },
4150
+ {
4151
+ "epoch": 12.71,
4152
+ "learning_rate": 5.540190053582401e-05,
4153
+ "loss": 0.4426,
4154
+ "step": 207500
4155
+ },
4156
+ {
4157
+ "epoch": 12.75,
4158
+ "learning_rate": 5.43673720198159e-05,
4159
+ "loss": 0.4424,
4160
+ "step": 208000
4161
+ },
4162
+ {
4163
+ "epoch": 12.75,
4164
+ "eval_loss": 0.8007999062538147,
4165
+ "eval_runtime": 1.3254,
4166
+ "eval_samples_per_second": 754.474,
4167
+ "eval_steps_per_second": 12.072,
4168
+ "step": 208000
4169
+ },
4170
+ {
4171
+ "epoch": 12.78,
4172
+ "learning_rate": 5.33438069868928e-05,
4173
+ "loss": 0.4425,
4174
+ "step": 208500
4175
+ },
4176
+ {
4177
+ "epoch": 12.81,
4178
+ "learning_rate": 5.2331250211105e-05,
4179
+ "loss": 0.4424,
4180
+ "step": 209000
4181
+ },
4182
+ {
4183
+ "epoch": 12.81,
4184
+ "eval_loss": 0.8051698207855225,
4185
+ "eval_runtime": 1.3459,
4186
+ "eval_samples_per_second": 742.979,
4187
+ "eval_steps_per_second": 11.888,
4188
+ "step": 209000
4189
+ },
4190
+ {
4191
+ "epoch": 12.84,
4192
+ "learning_rate": 5.13297459849662e-05,
4193
+ "loss": 0.4424,
4194
+ "step": 209500
4195
+ },
4196
+ {
4197
+ "epoch": 12.87,
4198
+ "learning_rate": 5.0339338117515696e-05,
4199
+ "loss": 0.4422,
4200
+ "step": 210000
4201
+ },
4202
+ {
4203
+ "epoch": 12.87,
4204
+ "eval_loss": 0.8003759980201721,
4205
+ "eval_runtime": 1.333,
4206
+ "eval_samples_per_second": 750.181,
4207
+ "eval_steps_per_second": 12.003,
4208
+ "step": 210000
4209
  }
4210
  ],
4211
  "max_steps": 250000,
4212
  "num_train_epochs": 16,
4213
+ "total_flos": 3.3634079341385047e+21,
4214
  "trial_name": null,
4215
  "trial_params": null
4216
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f93c7c276c93289bffe4373bac7c429f92d9efa91cbbce3f71bf9c56fe4737bc
3
  size 3247
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b8a2730f1715a1a69be5d50d288e678ba9489c02451a424b28677ab8614531
3
  size 3247
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:814e92d04e78b6c50be49334aded8445cc7160900174a209d8b6a93d4efe04ca
3
  size 25761253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b982cc265a7352e00ddc20a71748aff08f14dba0f3f3245909d1fbdbc876456
3
  size 25761253
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f93c7c276c93289bffe4373bac7c429f92d9efa91cbbce3f71bf9c56fe4737bc
3
  size 3247
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b8a2730f1715a1a69be5d50d288e678ba9489c02451a424b28677ab8614531
3
  size 3247