Transformers
PyTorch
English
pixel
pretraining
Inference Endpoints
plip commited on
Commit
946570d
1 Parent(s): c64c71a

Training in progress, step 630000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3b35f979d5fe4527b6f42c2add375e7239aec55be0317190f1a665e6ab5f35c
3
  size 893439185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d82e2070f1b6c3e7ba3ac4e05d24d0c3c44e21fea62b60f30dbcd4b8aea7947
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:a03035ba4bf151910d41d4c213cf2390c9903cf8cb85be4525c8f2b5574fe579
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa845416abb07e55de755c0df750468c782329996a5b84f0336b895c9a2baa1
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:bbb920f1348e13fdd02418f5a8bdde3a29115945de004c35412bd2480fdb9afa
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4acbb51e13aa598f4ce3e939d773ff547815a4a8c85e2bd41643e066b97a863b
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 sha256:154b8f14236fa636789c866c5bab186dc1c4e26fc03e987f1aabe66a3981e8a2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798c603bd32aeea05803afc8a5c1b8f53a6193b4dd4a2b5a26aa63e0065ce70e
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:a933eb9e98ce78bdca0e9e206bab865aad1983b58e12a370b79e23c847c34cac
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0fb0d506dd83556c6bb13f32358c5188773f715722e0fae2529869d20b06680
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 sha256:502983b98bc6a8911d0348894791667ff6481b824870d33d6fccaa23995ed7f4
3
- size 14439
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa6390e57fdd76fefb80f0c1ccc262a99cb2e588a24afb098b63de6015cd6400
3
+ size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87df12c543e6333a1257623848db6de543e5639171e7cc03225528d064da559b
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445023bf71af0013aa9e5796238ea2c1da2dcfc1e0064784bf2e5fc75bdc80c6
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": 9.467527906302013,
5
- "global_step": 620000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -4594,11 +4594,85 @@
4594
  "eval_samples_per_second": 944.48,
4595
  "eval_steps_per_second": 15.112,
4596
  "step": 620000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4597
  }
4598
  ],
4599
  "max_steps": 1000000,
4600
  "num_train_epochs": 16,
4601
- "total_flos": 4.346210270268184e+22,
4602
  "trial_name": null,
4603
  "trial_params": null
4604
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 9.620229969306886,
5
+ "global_step": 630000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
4594
  "eval_samples_per_second": 944.48,
4595
  "eval_steps_per_second": 15.112,
4596
  "step": 620000
4597
+ },
4598
+ {
4599
+ "epoch": 9.48,
4600
+ "learning_rate": 5.814877301838688e-05,
4601
+ "loss": 0.2523,
4602
+ "step": 621000
4603
+ },
4604
+ {
4605
+ "epoch": 9.5,
4606
+ "learning_rate": 5.7928974604537494e-05,
4607
+ "loss": 0.2522,
4608
+ "step": 622000
4609
+ },
4610
+ {
4611
+ "epoch": 9.51,
4612
+ "learning_rate": 5.770941755588573e-05,
4613
+ "loss": 0.2537,
4614
+ "step": 623000
4615
+ },
4616
+ {
4617
+ "epoch": 9.53,
4618
+ "learning_rate": 5.749010427347233e-05,
4619
+ "loss": 0.254,
4620
+ "step": 624000
4621
+ },
4622
+ {
4623
+ "epoch": 9.54,
4624
+ "learning_rate": 5.7271037155672156e-05,
4625
+ "loss": 0.2522,
4626
+ "step": 625000
4627
+ },
4628
+ {
4629
+ "epoch": 9.54,
4630
+ "eval_runtime": 1.0707,
4631
+ "eval_samples_per_second": 934.001,
4632
+ "eval_steps_per_second": 14.944,
4633
+ "step": 625000
4634
+ },
4635
+ {
4636
+ "epoch": 9.56,
4637
+ "learning_rate": 5.7052218598168154e-05,
4638
+ "loss": 0.2524,
4639
+ "step": 626000
4640
+ },
4641
+ {
4642
+ "epoch": 9.57,
4643
+ "learning_rate": 5.6833650993925016e-05,
4644
+ "loss": 0.2522,
4645
+ "step": 627000
4646
+ },
4647
+ {
4648
+ "epoch": 9.59,
4649
+ "learning_rate": 5.661533673316303e-05,
4650
+ "loss": 0.2522,
4651
+ "step": 628000
4652
+ },
4653
+ {
4654
+ "epoch": 9.6,
4655
+ "learning_rate": 5.639727820333198e-05,
4656
+ "loss": 0.2518,
4657
+ "step": 629000
4658
+ },
4659
+ {
4660
+ "epoch": 9.62,
4661
+ "learning_rate": 5.617947778908498e-05,
4662
+ "loss": 0.2517,
4663
+ "step": 630000
4664
+ },
4665
+ {
4666
+ "epoch": 9.62,
4667
+ "eval_runtime": 1.1949,
4668
+ "eval_samples_per_second": 836.899,
4669
+ "eval_steps_per_second": 13.39,
4670
+ "step": 630000
4671
  }
4672
  ],
4673
  "max_steps": 1000000,
4674
  "num_train_epochs": 16,
4675
+ "total_flos": 4.416310531298531e+22,
4676
  "trial_name": null,
4677
  "trial_params": null
4678
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a03035ba4bf151910d41d4c213cf2390c9903cf8cb85be4525c8f2b5574fe579
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa845416abb07e55de755c0df750468c782329996a5b84f0336b895c9a2baa1
3
  size 449471589