Token Classification
Safetensors
English
deberta-v2
shawnrushefsky commited on
Commit
531126e
·
verified ·
1 Parent(s): 18fecfc

Training in progress, step 7800, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55cd19f8a2015f70a54cc50e40cb883729cc170da6a401f887faa2ec0a4c8e2b
3
  size 735396724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c9caaf500315caabe3d6ab398496111fd79143166fd34fe4928a7d216b2b1b
3
  size 735396724
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eee9f791e1d58c0b7d489f46c5ef4fa0adf43609bacdb045c06a68fc37da3eff
3
  size 1470915147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f555ed8ae7e4dd911c856567abd68da482e2e587664626aa52c779f484bceb59
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:fddad012eb3897f6f0cdd137b2a7c5427a24e25625c46a986a7f1d96b3075809
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09fa342e4e31c9f0af3c0680e21614838f6434eda0bb06df0a82b124b568833f
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 sha256:4f0d69afafef0d710f86a249eaa9390eb39790fff4aed09a2cd53ce637e3407c
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86d2c83be86c05ac4f161b558f67d573491eb7cf69b114a8d95f134dfe3d6791
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:d73a14b30adb25cb46d77ae66d89a99e6e5105365ae26bbc94842d0582b6b3c7
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7726ca33163853da2951b395b798a292beb4980dd4a89bb3d3aa69feee67fde
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 sha256:2662bb462a1ca5f53142dd3a4604dcc9d5555c428c1ad6497e2da1c66b5e0946
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:045571212ab03f4fa82c1b0b888620ca00eccf9abeb6a0a6207d83f48b60c659
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 sha256:1d6e13c368f6e0f5954826b377ac2b5d09852ad78f21e438840cb35cb9a01386
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699a29a9c1a467b8fd7afd013b34d51db782b44e947fe165477f157a9f0d5bd2
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 sha256:3657d830163c017f80a67a0a6819cd10f5aeaf1c24bc0b55be529ef8cde949cb
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39eab2157603beeb5e422aadde82180c5d59833876cda34b62b628e22fa0d2a6
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 sha256:72a950e03a13d3e97163a50f42f8aeed0c68ca42cd5ca5f8e14b6fbdcd9cb974
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:460d5dc224d5276ded33bba692f0113c7782365d355907c27235d21887452902
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 sha256:255561264b49b25907929ea27d4f265b7b7a24599c97e554dccb6b8c0a68499c
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5543b31d53a86e7d958eb8cf5d6131c2529ba495237a6e749f1dc648507af3ab
3
  size 16325
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b27a9d07be2cf0bd17286e4dd9a08ee004504028361c208abb791695d17c1810
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38426de61f4b1df2179833548229f6925ca20ff338eca0e07db44082dcf93ae4
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 7400,
3
  "best_metric": 0.7516107925055505,
4
  "best_model_checkpoint": "model/checkpoint-7400",
5
- "epoch": 1.9452265165088303,
6
  "eval_steps": 200,
7
- "global_step": 7600,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1490,6 +1490,45 @@
1490
  "eval_samples_per_second": 1679.361,
1491
  "eval_steps_per_second": 26.24,
1492
  "step": 7600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1493
  }
1494
  ],
1495
  "logging_steps": 50,
@@ -1509,7 +1548,7 @@
1509
  "attributes": {}
1510
  }
1511
  },
1512
- "total_flos": 9.614641048185733e+17,
1513
  "train_batch_size": 256,
1514
  "trial_name": null,
1515
  "trial_params": null
 
2
  "best_global_step": 7400,
3
  "best_metric": 0.7516107925055505,
4
  "best_model_checkpoint": "model/checkpoint-7400",
5
+ "epoch": 1.9964166879959047,
6
  "eval_steps": 200,
7
+ "global_step": 7800,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1490
  "eval_samples_per_second": 1679.361,
1491
  "eval_steps_per_second": 26.24,
1492
  "step": 7600
1493
+ },
1494
+ {
1495
+ "epoch": 1.958024059380599,
1496
+ "grad_norm": 0.2235766500234604,
1497
+ "learning_rate": 7.1127144910229375e-06,
1498
+ "loss": 0.0841,
1499
+ "step": 7650
1500
+ },
1501
+ {
1502
+ "epoch": 1.9708216022523675,
1503
+ "grad_norm": 0.18436911702156067,
1504
+ "learning_rate": 6.957390566460964e-06,
1505
+ "loss": 0.0842,
1506
+ "step": 7700
1507
+ },
1508
+ {
1509
+ "epoch": 1.9836191451241363,
1510
+ "grad_norm": 0.21478892862796783,
1511
+ "learning_rate": 6.80312468312225e-06,
1512
+ "loss": 0.081,
1513
+ "step": 7750
1514
+ },
1515
+ {
1516
+ "epoch": 1.9964166879959047,
1517
+ "grad_norm": 0.16581684350967407,
1518
+ "learning_rate": 6.649946289169416e-06,
1519
+ "loss": 0.0819,
1520
+ "step": 7800
1521
+ },
1522
+ {
1523
+ "epoch": 1.9964166879959047,
1524
+ "eval_entity_f1": 0.7503771605165714,
1525
+ "eval_entity_precision": 0.6743199498465626,
1526
+ "eval_entity_recall": 0.8823676293131564,
1527
+ "eval_loss": 0.08185352385044098,
1528
+ "eval_runtime": 477.7259,
1529
+ "eval_samples_per_second": 1674.601,
1530
+ "eval_steps_per_second": 26.166,
1531
+ "step": 7800
1532
  }
1533
  ],
1534
  "logging_steps": 50,
 
1548
  "attributes": {}
1549
  }
1550
  },
1551
+ "total_flos": 9.867759577066373e+17,
1552
  "train_batch_size": 256,
1553
  "trial_name": null,
1554
  "trial_params": null