Token Classification
Safetensors
English
deberta-v2
shawnrushefsky commited on
Commit
d7b80b0
·
verified ·
1 Parent(s): 7618bdc

Training in progress, step 9400, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f771d7b5ffd0a8d7190364bbadf6af62c0db85637b8db11da9ee112cd87d9874
3
  size 735396724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a2586e38cb0c0c530aad2672eeefa524a32b2c8e235c1343d61b6a0555ab4d
3
  size 735396724
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:327f6bb8bcec07c5d4401fec1471b0745e6b8dd15458f9530e61bdb432684760
3
  size 1470915147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24567eb913cb31b7e595d12487252fead8cf325ba154d3ffba1a505ea4e8422d
3
  size 1470915147
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64327997d62356b0511b416e4d0fefaa151527fa6dedc8dd70a297f4f4c832d8
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcad41a59e34f913dac165ffa3a5e4e147287ef3e2a56d80f11e8d449daf65be
3
  size 16325
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fa0252a46646172eb26d1700fcaea8bd925a77dd50c805acb8128f84e6fd2d4
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71da57a410bde5eef7d2cf874fdd94772bffc81bcde7f741841f42e1e0f6b1d3
3
  size 16325
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca67274a2d3504766771d85596bfe994f3a0326e827bf542f52033d72568226a
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f803b1e9e013a327e86eb36a6264cef27656c5881ec165b74a338d2886b050b
3
  size 16325
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62f3403513092c99c8cdb6795941cae298da0d006383ed1e7eed75bff65d63a0
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440d59f70be2535a812b60bce4c82686e14e45df4bc80de6a80553542e5d19f4
3
  size 16325
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f171d2c2e97f8f2afff5cd59488f9fe54b8ff1a7106a97e2d9d2c087972e7882
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c5cdedeff55f31e8be8ce3affcb8bfe9adc7b7d2aeea51b995d562e16765d1
3
  size 16325
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a12522daf8b4d06a66f9e5bb4e517ba6dd31bc86c3c4183be7c670615fea178c
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dafad0486ae08cced73788248d7d41a5157d894bf92028750af0230cfee3864d
3
  size 16325
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe1f166c6172bcf9bfc8a0a55d67f945c0b4cfc10e402897e47626b664d4ba2c
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64a4a6876dc5ef93edbf786de849c8ef7648f11c63b978a894bdee23a5945d3b
3
  size 16325
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94a52c85cef4c9a787135b078449166d7cd6f87c54b0022bf71b252e13e95ebd
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:104acb326af9a056a57550d63fea4775c541735107e4ae7fbe64f15433bed015
3
  size 16325
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51b6dd7a170c90865f47d8c4e0b4edcba77f0c60d0b85a7d42e5fab1ac2ce087
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b750d4520fb4e0636b694986f10fd72ae31a4de007d84671fc1697478230b01d
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 8000,
3
  "best_metric": 0.7521935121655035,
4
  "best_model_checkpoint": "model/checkpoint-8000",
5
- "epoch": 2.3547478884054263,
6
  "eval_steps": 200,
7
- "global_step": 9200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1802,6 +1802,45 @@
1802
  "eval_samples_per_second": 1673.934,
1803
  "eval_steps_per_second": 26.155,
1804
  "step": 9200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1805
  }
1806
  ],
1807
  "logging_steps": 50,
@@ -1821,7 +1860,7 @@
1821
  "attributes": {}
1822
  }
1823
  },
1824
- "total_flos": 1.1637788598085878e+18,
1825
  "train_batch_size": 256,
1826
  "trial_name": null,
1827
  "trial_params": null
 
2
  "best_global_step": 8000,
3
  "best_metric": 0.7521935121655035,
4
  "best_model_checkpoint": "model/checkpoint-8000",
5
+ "epoch": 2.4059380598925006,
6
  "eval_steps": 200,
7
+ "global_step": 9400,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1802
  "eval_samples_per_second": 1673.934,
1803
  "eval_steps_per_second": 26.155,
1804
  "step": 9200
1805
+ },
1806
+ {
1807
+ "epoch": 2.3675454312771946,
1808
+ "grad_norm": 0.23878569900989532,
1809
+ "learning_rate": 2.804651489969351e-06,
1810
+ "loss": 0.0788,
1811
+ "step": 9250
1812
+ },
1813
+ {
1814
+ "epoch": 2.3803429741489635,
1815
+ "grad_norm": 0.1848394274711609,
1816
+ "learning_rate": 2.6965699132903825e-06,
1817
+ "loss": 0.0805,
1818
+ "step": 9300
1819
+ },
1820
+ {
1821
+ "epoch": 2.393140517020732,
1822
+ "grad_norm": 0.17279605567455292,
1823
+ "learning_rate": 2.590359735504931e-06,
1824
+ "loss": 0.0786,
1825
+ "step": 9350
1826
+ },
1827
+ {
1828
+ "epoch": 2.4059380598925006,
1829
+ "grad_norm": 0.22736063599586487,
1830
+ "learning_rate": 2.4860412313135184e-06,
1831
+ "loss": 0.0804,
1832
+ "step": 9400
1833
+ },
1834
+ {
1835
+ "epoch": 2.4059380598925006,
1836
+ "eval_entity_f1": 0.7479533875518636,
1837
+ "eval_entity_precision": 0.6699579882252567,
1838
+ "eval_entity_recall": 0.8846118566955841,
1839
+ "eval_loss": 0.08190065622329712,
1840
+ "eval_runtime": 479.9003,
1841
+ "eval_samples_per_second": 1667.013,
1842
+ "eval_steps_per_second": 26.047,
1843
+ "step": 9400
1844
  }
1845
  ],
1846
  "logging_steps": 50,
 
1860
  "attributes": {}
1861
  }
1862
  },
1863
+ "total_flos": 1.189037139422085e+18,
1864
  "train_batch_size": 256,
1865
  "trial_name": null,
1866
  "trial_params": null