Transformers
PyTorch
English
pixel
pretraining
Inference Endpoints
plip commited on
Commit
5a7e722
1 Parent(s): 96ed7e3

Training in progress, step 260000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:981f9cd48efb9aa651b5446906cfef65e3f5e49845175ea67dca9f635e9c1038
3
  size 893439185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80fb9af3e1214502ea925d3599d3b6efda5d8711659b2c90eec052ea369703f7
3
  size 893439185
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22078b7cadf342376e128bb1b061228e01c38cac2488c2ab30ca05231e48ad59
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab3051ab890d6ef671960c94245505fe32b7894ead10b5d7877e9fabce99ffc
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:ac406c207b2f7429e3395f91a987edf514c0aeff745dd88acf0897c2d8c0d2f5
3
- size 14439
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72757db14fb233c9a7d81cef99ff1e84d48a76f7d40a8342399239cffc8c3e9f
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:a150bbb8b25e860b9b4e4d20308c75cd4211d4f66e73ca0ae830a1483ae3793d
3
- size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8fbef78331483305594b3f85c6f32ce7bab8b9f165e2fb904f362fb3239105f
3
+ size 14567
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba99bff5574a5463122f2331dbbdbc3c75f9c55701d70a2ea0f51810fd185527
3
- size 14439
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b31003ab7fcda6d6f6ff162f700b04d49c90c118129057bd1f4ee624c393e588
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 sha256:4b4ebfa40194a9690e4a04456095f6b6e0d44abd914d615940586748348af8ed
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1da43c666b0af3cbe77f19371961622ab99b1114e6beec7303d695cd496caee4
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1301777ffe2dc7d45e2808f549b6c6f37d8616c9227a415a7757312ea67a80a1
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04396ff3c1feb0819b380c26b60d419205385a8e624d7c59a71eaea179611c46
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": 3.81755157512178,
5
- "global_step": 250000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -1856,11 +1856,85 @@
1856
  "eval_samples_per_second": 983.434,
1857
  "eval_steps_per_second": 15.735,
1858
  "step": 250000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1859
  }
1860
  ],
1861
  "max_steps": 1000000,
1862
  "num_train_epochs": 16,
1863
- "total_flos": 1.7525045545542324e+22,
1864
  "trial_name": null,
1865
  "trial_params": null
1866
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.970253638126651,
5
+ "global_step": 260000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
1856
  "eval_samples_per_second": 983.434,
1857
  "eval_steps_per_second": 15.735,
1858
  "step": 250000
1859
+ },
1860
+ {
1861
+ "epoch": 3.83,
1862
+ "learning_rate": 0.00013509735236440766,
1863
+ "loss": 0.3003,
1864
+ "step": 251000
1865
+ },
1866
+ {
1867
+ "epoch": 3.85,
1868
+ "learning_rate": 0.00013495426653524972,
1869
+ "loss": 0.3,
1870
+ "step": 252000
1871
+ },
1872
+ {
1873
+ "epoch": 3.86,
1874
+ "learning_rate": 0.00013481057973503742,
1875
+ "loss": 0.3,
1876
+ "step": 253000
1877
+ },
1878
+ {
1879
+ "epoch": 3.88,
1880
+ "learning_rate": 0.00013466629353510651,
1881
+ "loss": 0.2997,
1882
+ "step": 254000
1883
+ },
1884
+ {
1885
+ "epoch": 3.89,
1886
+ "learning_rate": 0.00013452140951334787,
1887
+ "loss": 0.2995,
1888
+ "step": 255000
1889
+ },
1890
+ {
1891
+ "epoch": 3.89,
1892
+ "eval_runtime": 0.8192,
1893
+ "eval_samples_per_second": 1220.744,
1894
+ "eval_steps_per_second": 19.532,
1895
+ "step": 255000
1896
+ },
1897
+ {
1898
+ "epoch": 3.91,
1899
+ "learning_rate": 0.00013437592925418985,
1900
+ "loss": 0.2996,
1901
+ "step": 256000
1902
+ },
1903
+ {
1904
+ "epoch": 3.92,
1905
+ "learning_rate": 0.00013422985434858133,
1906
+ "loss": 0.299,
1907
+ "step": 257000
1908
+ },
1909
+ {
1910
+ "epoch": 3.94,
1911
+ "learning_rate": 0.00013408318639397405,
1912
+ "loss": 0.2987,
1913
+ "step": 258000
1914
+ },
1915
+ {
1916
+ "epoch": 3.95,
1917
+ "learning_rate": 0.00013393592699430525,
1918
+ "loss": 0.2986,
1919
+ "step": 259000
1920
+ },
1921
+ {
1922
+ "epoch": 3.97,
1923
+ "learning_rate": 0.00013378807775998012,
1924
+ "loss": 0.2984,
1925
+ "step": 260000
1926
+ },
1927
+ {
1928
+ "epoch": 3.97,
1929
+ "eval_runtime": 1.0461,
1930
+ "eval_samples_per_second": 955.963,
1931
+ "eval_steps_per_second": 15.295,
1932
+ "step": 260000
1933
  }
1934
  ],
1935
  "max_steps": 1000000,
1936
  "num_train_epochs": 16,
1937
+ "total_flos": 1.8226048155845795e+22,
1938
  "trial_name": null,
1939
  "trial_params": null
1940
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22078b7cadf342376e128bb1b061228e01c38cac2488c2ab30ca05231e48ad59
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab3051ab890d6ef671960c94245505fe32b7894ead10b5d7877e9fabce99ffc
3
  size 449471589