Transformers
PyTorch
English
pixel
pretraining
Inference Endpoints
plip commited on
Commit
61e8915
1 Parent(s): ab34e00

Training in progress, step 670000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d1b9c3dadef4c83eaa6444ae31d8e46ec85073c61b37dd61844f05913236e16
3
  size 893439185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965860eaf3c3ea343e75b1d82190f39b5bb62e76f36d4448a6618790db6ff870
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:c2fc5b645a51764da4f8ff98e3c407a8e3b54b7f2ebf4044514e81a387a44685
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5578b4d4e33e87af6d4056fd17ea4c7b1d31f9e365318710f084d9f8ad6a9e7a
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:cdc9f2d6c7b188b0a4e60257b0a8bd84c335d50dfde13a7917d3ec48da9a1694
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e83b18565bb157c89e4103ebdca556e5a6af6a5fd5614439ee11638b091ec95
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:f55bf132d9f9827e3128928d8dd16bab60642cd4846a79818e1304f0d9048138
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413c5c9b29f5423e3974277660424767e4053296a5d316f7bd214cca3e9c3452
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:c250144fe49ffdfe7647f695a0d687d07a9a35cdce7fa106343ed4f42beb24af
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027e092b1b60566b466a15ddaa84a08bd53806c1b3cde5871142648013620d30
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 sha256:9d99a97fa7df68e7130dee285dc72156e57930a619ecb49b136dff7611919aa2
3
- size 14439
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f44ecad91e276e5983fd17d83f87c8abed938c6303227829dce7483dd60c92
3
+ size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e668d5f010f36e9bc3681300c074ae1cd82ec8d3466f5c0bcb0eb7c6db53f6b
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651f855ada6fd7cfa09b534ad266032caacaa52b90009ef1696c08e67fbed919
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": 10.078336158321498,
5
- "global_step": 660000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -4890,11 +4890,85 @@
4890
  "eval_samples_per_second": 957.361,
4891
  "eval_steps_per_second": 15.318,
4892
  "step": 660000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4893
  }
4894
  ],
4895
  "max_steps": 1000000,
4896
  "num_train_epochs": 16,
4897
- "total_flos": 4.626610657321424e+22,
4898
  "trial_name": null,
4899
  "trial_params": null
4900
  }
 
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,
 
4890
  "eval_samples_per_second": 957.361,
4891
  "eval_steps_per_second": 15.318,
4892
  "step": 660000
4893
+ },
4894
+ {
4895
+ "epoch": 10.09,
4896
+ "learning_rate": 4.956856283426728e-05,
4897
+ "loss": 0.2487,
4898
+ "step": 661000
4899
+ },
4900
+ {
4901
+ "epoch": 10.11,
4902
+ "learning_rate": 4.936026312555037e-05,
4903
+ "loss": 0.248,
4904
+ "step": 662000
4905
+ },
4906
+ {
4907
+ "epoch": 10.12,
4908
+ "learning_rate": 4.915229848808698e-05,
4909
+ "loss": 0.2478,
4910
+ "step": 663000
4911
+ },
4912
+ {
4913
+ "epoch": 10.14,
4914
+ "learning_rate": 4.8944671196145136e-05,
4915
+ "loss": 0.2484,
4916
+ "step": 664000
4917
+ },
4918
+ {
4919
+ "epoch": 10.15,
4920
+ "learning_rate": 4.8737383520303546e-05,
4921
+ "loss": 0.2485,
4922
+ "step": 665000
4923
+ },
4924
+ {
4925
+ "epoch": 10.15,
4926
+ "eval_runtime": 1.1085,
4927
+ "eval_samples_per_second": 902.106,
4928
+ "eval_steps_per_second": 14.434,
4929
+ "step": 665000
4930
+ },
4931
+ {
4932
+ "epoch": 10.17,
4933
+ "learning_rate": 4.853043772742709e-05,
4934
+ "loss": 0.248,
4935
+ "step": 666000
4936
+ },
4937
+ {
4938
+ "epoch": 10.19,
4939
+ "learning_rate": 4.832383608064172e-05,
4940
+ "loss": 0.2476,
4941
+ "step": 667000
4942
+ },
4943
+ {
4944
+ "epoch": 10.2,
4945
+ "learning_rate": 4.811758083931005e-05,
4946
+ "loss": 0.2478,
4947
+ "step": 668000
4948
+ },
4949
+ {
4950
+ "epoch": 10.22,
4951
+ "learning_rate": 4.791167425900632e-05,
4952
+ "loss": 0.2481,
4953
+ "step": 669000
4954
+ },
4955
+ {
4956
+ "epoch": 10.23,
4957
+ "learning_rate": 4.770611859149185e-05,
4958
+ "loss": 0.2508,
4959
+ "step": 670000
4960
+ },
4961
+ {
4962
+ "epoch": 10.23,
4963
+ "eval_runtime": 1.1412,
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
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2fc5b645a51764da4f8ff98e3c407a8e3b54b7f2ebf4044514e81a387a44685
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5578b4d4e33e87af6d4056fd17ea4c7b1d31f9e365318710f084d9f8ad6a9e7a
3
  size 449471589