Token Classification
Safetensors
English
deberta-v2
shawnrushefsky commited on
Commit
646cd73
·
verified ·
1 Parent(s): fbd4739

Training in progress, step 8200, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35234e98563d57ed724de722b529352dfc5091a9c3d6e86ffa755b26f4cfa372
3
  size 735396724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86b23122c2d6b3e2475ec6d64a26a3bbee4dcc449500fcbaadea18fc9d7664d
3
  size 735396724
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:132a89e9954ceb888694e764eac4b5df670d6ba01b38f97f2278d5f7cfd19678
3
  size 1470915147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2861a8dacff687135e932b24e86c7e925f8c8c947ab0daf5841068c4d3b2ee05
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:aad2772f1b5fc488fbc7aed0f82f804296b1c150e9c065867d738f64df646311
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a7134456600138a178dd6c7975af5eb82bda5d6f504154e6036cf5e56d2aff3
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 sha256:735462b38fce539f4bd65b823ab4ffc3771515b0c97a8e2bc96bce55f28460db
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef379979ae52a4a6dcf0672ae734f2abfcd4bb37ca8bd49b8e77316d6df729bd
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:d159518eb2fc98590eaf0238be52a1240c990a0cb1ceab7a0200d8d4bdfbe837
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c5b9ba5fb61c4c352dd3899aa4aa435c8f17da0f38c6037bd3dfbec88c58a6
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:ddfa200939ed344d19b0a7b90be2611afa89c7744cb18ae6b8753449d5e5fc49
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a9d153c2487018eb9bbfeb36d552586ada0e6595243f0d08dd86c0437695f2
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:dfce25a343ef9b93d6a6bb88ddab560106eef75776eddcd5b4e274dfedf6a634
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c98dfe343a69c84bf3f3dc83d809b64ce940205805d943ec3bcf67c75962278
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 sha256:0430fb60d02ccc5835124a657ff50555c5d1caf18b93c39f8feedf8bf140bc17
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e0f5a442bfdf7ba09b07e899da41f737056188d7c12a180aca5aaa5df6c5840
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:e214cc998c3e93fac8993ed4b8d41d2d8e2d027fe81d2e97f78146e4a002681a
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b00eb8ecebbc2f4ee3f63dc10ee4b0e13177cea6e377ffddba50025f27650e
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 sha256:687a57204632a3872b4f057c04a3f825960fef66d882a02a73d9a028467cd559
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75caf2be8b3e0b2c0d25c2cc43dc8c1d9809ed3cc08e051ad61cc3687652d6f0
3
  size 16325
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:571decbfd1584e97038ff0987fd62646b7f00e27353e20ce662dbad267f49694
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f175c5bbbf0e2dc192b0dfd85702412099ba268ea2e1e3d6cfe6b30270f05963
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": 2.047606859482979,
6
  "eval_steps": 200,
7
- "global_step": 8000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1568,6 +1568,45 @@
1568
  "eval_samples_per_second": 1670.455,
1569
  "eval_steps_per_second": 26.101,
1570
  "step": 8000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1571
  }
1572
  ],
1573
  "logging_steps": 50,
@@ -1587,7 +1626,7 @@
1587
  "attributes": {}
1588
  }
1589
  },
1590
- "total_flos": 1.0121067562323149e+18,
1591
  "train_batch_size": 256,
1592
  "trial_name": null,
1593
  "trial_params": null
 
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,
 
1568
  "eval_samples_per_second": 1670.455,
1569
  "eval_steps_per_second": 26.101,
1570
  "step": 8000
1571
+ },
1572
+ {
1573
+ "epoch": 2.060404402354748,
1574
+ "grad_norm": 0.1903725117444992,
1575
+ "learning_rate": 5.901382502920917e-06,
1576
+ "loss": 0.0815,
1577
+ "step": 8050
1578
+ },
1579
+ {
1580
+ "epoch": 2.0732019452265167,
1581
+ "grad_norm": 0.21677176654338837,
1582
+ "learning_rate": 5.7553354430558175e-06,
1583
+ "loss": 0.0786,
1584
+ "step": 8100
1585
+ },
1586
+ {
1587
+ "epoch": 2.085999488098285,
1588
+ "grad_norm": 0.20070292055606842,
1589
+ "learning_rate": 5.610575887429269e-06,
1590
+ "loss": 0.0819,
1591
+ "step": 8150
1592
+ },
1593
+ {
1594
+ "epoch": 2.098797030970054,
1595
+ "grad_norm": 0.23013773560523987,
1596
+ "learning_rate": 5.467131469519539e-06,
1597
+ "loss": 0.0787,
1598
+ "step": 8200
1599
+ },
1600
+ {
1601
+ "epoch": 2.098797030970054,
1602
+ "eval_entity_f1": 0.7467361335473326,
1603
+ "eval_entity_precision": 0.6691935746638842,
1604
+ "eval_entity_recall": 0.8844498075794143,
1605
+ "eval_loss": 0.08263843506574631,
1606
+ "eval_runtime": 477.2941,
1607
+ "eval_samples_per_second": 1676.116,
1608
+ "eval_steps_per_second": 26.189,
1609
+ "step": 8200
1610
  }
1611
  ],
1612
  "logging_steps": 50,
 
1626
  "attributes": {}
1627
  }
1628
  },
1629
+ "total_flos": 1.0373421672924447e+18,
1630
  "train_batch_size": 256,
1631
  "trial_name": null,
1632
  "trial_params": null