Token Classification
Safetensors
English
deberta-v2
shawnrushefsky commited on
Commit
4d6652a
·
verified ·
1 Parent(s): 7d1dbf6

Training in progress, step 8400, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f86b23122c2d6b3e2475ec6d64a26a3bbee4dcc449500fcbaadea18fc9d7664d
3
  size 735396724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1b9ab492567c0861179ecbd5d956a4d88e04e1c91b51205ee056092e9f7d143
3
  size 735396724
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2861a8dacff687135e932b24e86c7e925f8c8c947ab0daf5841068c4d3b2ee05
3
  size 1470915147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0100ec640555a82b79a6275d0255ee396bf507aa7d37457fd04bfd770a9cde2
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 sha256:9a7134456600138a178dd6c7975af5eb82bda5d6f504154e6036cf5e56d2aff3
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f31deabde9774d7b715ebb37f8a5b05132e70b8fba9b7b7cc9e1863c4755401
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:ef379979ae52a4a6dcf0672ae734f2abfcd4bb37ca8bd49b8e77316d6df729bd
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2133fc09ca0dde8484eb6ada85dafe76f2d21205bae59aa3ca55fb2cbd67a64a
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:a1c5b9ba5fb61c4c352dd3899aa4aa435c8f17da0f38c6037bd3dfbec88c58a6
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95fe7ee67716c44d007ac2ff7b404ef42b1dbeeac0eedc1ff802f818ea7402a2
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 sha256:68a9d153c2487018eb9bbfeb36d552586ada0e6595243f0d08dd86c0437695f2
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1a3792988c6545abf00083c1c7536ac7d9b5c93da01bd80566c001d2cf7d273
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 sha256:3c98dfe343a69c84bf3f3dc83d809b64ce940205805d943ec3bcf67c75962278
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69f1850da370a0d9ce9e8185ef6584b93e2aca80d502af41524c2b7600b76eca
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 sha256:1e0f5a442bfdf7ba09b07e899da41f737056188d7c12a180aca5aaa5df6c5840
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:508a2598b331a6b6138feb5154513b5386ab091d2a66cf18462b906ddcc12608
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 sha256:79b00eb8ecebbc2f4ee3f63dc10ee4b0e13177cea6e377ffddba50025f27650e
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e90f868b1bcecdc53f0e44d0bb626a4a73ba91c764560e8f19b86df62f0135
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 sha256:75caf2be8b3e0b2c0d25c2cc43dc8c1d9809ed3cc08e051ad61cc3687652d6f0
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9b103d30c41f30ba900fee5e71bb030d08a84aedb5576448c5d7160a3ac972
3
  size 16325
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f175c5bbbf0e2dc192b0dfd85702412099ba268ea2e1e3d6cfe6b30270f05963
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5417d850f6448b73079a6225cb8b70a3e5319d3a239d5933026cfa75283b5cf2
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": 2.098797030970054,
6
  "eval_steps": 200,
7
- "global_step": 8200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1607,6 +1607,45 @@
1607
  "eval_samples_per_second": 1676.116,
1608
  "eval_steps_per_second": 26.189,
1609
  "step": 8200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1610
  }
1611
  ],
1612
  "logging_steps": 50,
@@ -1626,7 +1665,7 @@
1626
  "attributes": {}
1627
  }
1628
  },
1629
- "total_flos": 1.0373421672924447e+18,
1630
  "train_batch_size": 256,
1631
  "trial_name": null,
1632
  "trial_params": null
 
2
  "best_global_step": 8000,
3
  "best_metric": 0.7521935121655035,
4
  "best_model_checkpoint": "model/checkpoint-8000",
5
+ "epoch": 2.1499872024571283,
6
  "eval_steps": 200,
7
+ "global_step": 8400,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1607
  "eval_samples_per_second": 1676.116,
1608
  "eval_steps_per_second": 26.189,
1609
  "step": 8200
1610
+ },
1611
+ {
1612
+ "epoch": 2.1115945738418223,
1613
+ "grad_norm": 0.19033853709697723,
1614
+ "learning_rate": 5.325029571755283e-06,
1615
+ "loss": 0.0802,
1616
+ "step": 8250
1617
+ },
1618
+ {
1619
+ "epoch": 2.124392116713591,
1620
+ "grad_norm": 0.25540676712989807,
1621
+ "learning_rate": 5.184297320288461e-06,
1622
+ "loss": 0.0801,
1623
+ "step": 8300
1624
+ },
1625
+ {
1626
+ "epoch": 2.1371896595853594,
1627
+ "grad_norm": 0.2815502882003784,
1628
+ "learning_rate": 5.044961579816158e-06,
1629
+ "loss": 0.0802,
1630
+ "step": 8350
1631
+ },
1632
+ {
1633
+ "epoch": 2.1499872024571283,
1634
+ "grad_norm": 0.2073817402124405,
1635
+ "learning_rate": 4.907048948452328e-06,
1636
+ "loss": 0.0818,
1637
+ "step": 8400
1638
+ },
1639
+ {
1640
+ "epoch": 2.1499872024571283,
1641
+ "eval_entity_f1": 0.7482286403320351,
1642
+ "eval_entity_precision": 0.6697158894027595,
1643
+ "eval_entity_recall": 0.8849257631596112,
1644
+ "eval_loss": 0.0820288360118866,
1645
+ "eval_runtime": 477.2072,
1646
+ "eval_samples_per_second": 1676.42,
1647
+ "eval_steps_per_second": 26.194,
1648
+ "step": 8400
1649
  }
1650
  ],
1651
  "logging_steps": 50,
 
1665
  "attributes": {}
1666
  }
1667
  },
1668
+ "total_flos": 1.0625957423061402e+18,
1669
  "train_batch_size": 256,
1670
  "trial_name": null,
1671
  "trial_params": null