Hugging Face's logo

Team-PIXEL
/
pixel-base

Transformers
PyTorch
English
pixel
pretraining
Inference Endpoints
Model card Files Community
plip commited on
Commit
4ef2863
•
1 Parent(s): 61e8915

Training in progress, step 680000

Browse files
Files changed (11) 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/scheduler.pt +1 -1
  8. last-checkpoint/trainer_state.json +77 -3
  9. last-checkpoint/training_args.bin +1 -1
  10. pytorch_model.bin +1 -1
  11. training_args.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:965860eaf3c3ea343e75b1d82190f39b5bb62e76f36d4448a6618790db6ff870
3
  size 893439185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b0820fc6b350986b719e550b35d09a69f533f4c17c09f1fc4dcc51eee4deaf
3
  size 893439185
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5578b4d4e33e87af6d4056fd17ea4c7b1d31f9e365318710f084d9f8ad6a9e7a
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bad34c9686a45968effd10ffe093593240a68e27baf1e992462f0c39c5a1154f
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 sha256:6e83b18565bb157c89e4103ebdca556e5a6af6a5fd5614439ee11638b091ec95
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5303f8d69702e89a1f09b78b9ce543e8c95fc0bc0f0edba191465caf3a91d92a
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 sha256:413c5c9b29f5423e3974277660424767e4053296a5d316f7bd214cca3e9c3452
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef09cba59e3953ac0ff77371a062cedb407170faeac834b4f4e7690a6546000
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 sha256:027e092b1b60566b466a15ddaa84a08bd53806c1b3cde5871142648013620d30
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b74b641ea212d2246cddaeb018c081c477c99608fb3a2c0685286bdcc4bf7cde
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 sha256:20f44ecad91e276e5983fd17d83f87c8abed938c6303227829dce7483dd60c92
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e039e987a11ac43b108942b16a0127488a54c01eff95956d54d2613b30129dbd
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:651f855ada6fd7cfa09b534ad266032caacaa52b90009ef1696c08e67fbed919
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d737cb5c8a42fd478f2f6309865787d8315dbe8632150ec0b5dc4840a67a78da
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": 10.23103822132637,
5
- "global_step": 670000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -4964,11 +4964,85 @@
4964
  "eval_samples_per_second": 876.243,
4965
  "eval_steps_per_second": 14.02,
4966
  "step": 670000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4967
  }
4968
  ],
4969
  "max_steps": 1000000,
4970
  "num_train_epochs": 16,
4971
- "total_flos": 4.696710918351771e+22,
4972
  "trial_name": null,
4973
  "trial_params": null
4974
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 10.38374028433124,
5
+ "global_step": 680000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
4964
  "eval_samples_per_second": 876.243,
4965
  "eval_steps_per_second": 14.02,
4966
  "step": 670000
4967
+ },
4968
+ {
4969
+ "epoch": 10.25,
4970
+ "learning_rate": 4.7500916084690564e-05,
4971
+ "loss": 0.2542,
4972
+ "step": 671000
4973
+ },
4974
+ {
4975
+ "epoch": 10.26,
4976
+ "learning_rate": 4.729606898266411e-05,
4977
+ "loss": 0.2507,
4978
+ "step": 672000
4979
+ },
4980
+ {
4981
+ "epoch": 10.28,
4982
+ "learning_rate": 4.709157952558768e-05,
4983
+ "loss": 0.2478,
4984
+ "step": 673000
4985
+ },
4986
+ {
4987
+ "epoch": 10.29,
4988
+ "learning_rate": 4.688744994972514e-05,
4989
+ "loss": 0.2482,
4990
+ "step": 674000
4991
+ },
4992
+ {
4993
+ "epoch": 10.31,
4994
+ "learning_rate": 4.668368248740485e-05,
4995
+ "loss": 0.247,
4996
+ "step": 675000
4997
+ },
4998
+ {
4999
+ "epoch": 10.31,
5000
+ "eval_runtime": 0.9224,
5001
+ "eval_samples_per_second": 1084.145,
5002
+ "eval_steps_per_second": 17.346,
5003
+ "step": 675000
5004
+ },
5005
+ {
5006
+ "epoch": 10.32,
5007
+ "learning_rate": 4.6480279366995116e-05,
5008
+ "loss": 0.2472,
5009
+ "step": 676000
5010
+ },
5011
+ {
5012
+ "epoch": 10.34,
5013
+ "learning_rate": 4.6277242812879914e-05,
5014
+ "loss": 0.2473,
5015
+ "step": 677000
5016
+ },
5017
+ {
5018
+ "epoch": 10.35,
5019
+ "learning_rate": 4.607457504543447e-05,
5020
+ "loss": 0.2471,
5021
+ "step": 678000
5022
+ },
5023
+ {
5024
+ "epoch": 10.37,
5025
+ "learning_rate": 4.5872278281000955e-05,
5026
+ "loss": 0.2469,
5027
+ "step": 679000
5028
+ },
5029
+ {
5030
+ "epoch": 10.38,
5031
+ "learning_rate": 4.567035473186444e-05,
5032
+ "loss": 0.2469,
5033
+ "step": 680000
5034
+ },
5035
+ {
5036
+ "epoch": 10.38,
5037
+ "eval_runtime": 0.7393,
5038
+ "eval_samples_per_second": 1352.617,
5039
+ "eval_steps_per_second": 21.642,
5040
+ "step": 680000
5041
  }
5042
  ],
5043
  "max_steps": 1000000,
5044
  "num_train_epochs": 16,
5045
+ "total_flos": 4.766811179382118e+22,
5046
  "trial_name": null,
5047
  "trial_params": null
5048
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69d9dd505c56ab02fdd4405a013eaa211c194bd407e1877bba9642905743e82c
3
  size 3311
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266f63e45a1817b41dc068c262baa2af3cee153bdb768839f58f4ee888697edd
3
  size 3311
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5578b4d4e33e87af6d4056fd17ea4c7b1d31f9e365318710f084d9f8ad6a9e7a
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bad34c9686a45968effd10ffe093593240a68e27baf1e992462f0c39c5a1154f
3
  size 449471589
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69d9dd505c56ab02fdd4405a013eaa211c194bd407e1877bba9642905743e82c
3
  size 3311
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266f63e45a1817b41dc068c262baa2af3cee153bdb768839f58f4ee888697edd
3
  size 3311