Token Classification
Safetensors
English
deberta-v2
shawnrushefsky commited on
Commit
80dfd51
·
verified ·
1 Parent(s): 96ba399

Training in progress, step 7200, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d49948f3dace645a26e3c68ec76876236c64cfa35dcb3983d3be379521e217f3
3
  size 735396724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e549061b1ab7ed4b4caf706180d962aa1d702dbe82bdfde7fd381373fec4465
3
  size 735396724
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cea5d5f319e531fd1d6325444ffda1d17707d16e4faaf43351fa45c5f61c2e6
3
  size 1470915147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d60b57cafd58a804f155bbc18af1e68b4a7e6f89f49a419e2a914ffb8a8c9f2
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 sha256:22e51e5896f4d3a56c2b5b9538a6facb32ffe7418f7fe495e1833726b74b8e38
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e0661f62ad11ca23cdb3c6394ed24683acc7a22e7db7bcec0ad928453d6e1f
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:bec0e67093c6521ee56f018f9002db867c6340e9e5a9a0548f4e8985bdb75921
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:262fe7ef667e1bc160c7b7886b2a18e3e74e694bffbb58e2d25f05a0c2ff7514
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:c26f2145e6858bf7c9796344aa7d93c1089ae0223e4667565eff5dd2902294d5
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c1b5d7fab89a97676f70b0c34c738bad3cbe7dd6a7105c2514e087156ff23b
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 sha256:890511a847f741cfeceef069c8f17a4b0c53dbe81876743d67599ac362791cb1
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d4bbde4e37f8bd1d4e1fc1d8b088a34388e3ba6c09cb1fb9647c35bc224de7
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:e90dd383caa8bc9990753ecaea7d687eb541c1ae47da5f3089774a65a98fb53b
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c565b45172bade440fcfeb502e3f5e2f77e7a5f854fe1803b71085dbe3e2c1
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:fec6f9f94cd2162b18fccf80934a5263db4b994843d76c7f791fa037cf67d7d0
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc19227eb5548f5423baaedc7fa60457a226d861784276529626584b98acfee
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:d5761ea848d5cfe512ebf80b4e79e019932f15889e408ef37b0359b0a5ee3f23
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d6b81dfce538e0465de424199e6af6c3c111cc5b9cfa397a384b5fd4e1e9620
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 sha256:9fdd8df25e1096f10c7d75664d7f0df12140b30734aad0b984fce542e3f172f2
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c988ecad693d80d47e8cf13b78e9add339eb715d515e41680ccf7f383b7a2dbd
3
  size 16325
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79b80fe799e2689c8e2ecc882e29bd3fac354528db79cb563b28412067ec4b09
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba3598bde598a309226aefc483573a2fa317cde784fc0eb1a444c4c7c3acd02e
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 6800,
3
  "best_metric": 0.7503099306717591,
4
  "best_model_checkpoint": "model/checkpoint-6800",
5
- "epoch": 1.7916560020476069,
6
  "eval_steps": 200,
7
- "global_step": 7000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1373,6 +1373,45 @@
1373
  "eval_samples_per_second": 1674.339,
1374
  "eval_steps_per_second": 26.162,
1375
  "step": 7000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1376
  }
1377
  ],
1378
  "logging_steps": 50,
@@ -1392,7 +1431,7 @@
1392
  "attributes": {}
1393
  }
1394
  },
1395
- "total_flos": 8.856475876154409e+17,
1396
  "train_batch_size": 256,
1397
  "trial_name": null,
1398
  "trial_params": null
 
2
  "best_global_step": 6800,
3
  "best_metric": 0.7503099306717591,
4
  "best_model_checkpoint": "model/checkpoint-6800",
5
+ "epoch": 1.8428461735346815,
6
  "eval_steps": 200,
7
+ "global_step": 7200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1373
  "eval_samples_per_second": 1674.339,
1374
  "eval_steps_per_second": 26.162,
1375
  "step": 7000
1376
+ },
1377
+ {
1378
+ "epoch": 1.8044535449193755,
1379
+ "grad_norm": 0.16946418583393097,
1380
+ "learning_rate": 9.048151155817237e-06,
1381
+ "loss": 0.0809,
1382
+ "step": 7050
1383
+ },
1384
+ {
1385
+ "epoch": 1.817251087791144,
1386
+ "grad_norm": 0.24798162281513214,
1387
+ "learning_rate": 8.882495473647761e-06,
1388
+ "loss": 0.0827,
1389
+ "step": 7100
1390
+ },
1391
+ {
1392
+ "epoch": 1.8300486306629127,
1393
+ "grad_norm": 0.23165899515151978,
1394
+ "learning_rate": 8.71753034508126e-06,
1395
+ "loss": 0.0844,
1396
+ "step": 7150
1397
+ },
1398
+ {
1399
+ "epoch": 1.8428461735346815,
1400
+ "grad_norm": 0.22031931579113007,
1401
+ "learning_rate": 8.55328726068342e-06,
1402
+ "loss": 0.0832,
1403
+ "step": 7200
1404
+ },
1405
+ {
1406
+ "epoch": 1.8428461735346815,
1407
+ "eval_entity_f1": 0.7488711084341455,
1408
+ "eval_entity_precision": 0.671487774215859,
1409
+ "eval_entity_recall": 0.8834591676994326,
1410
+ "eval_loss": 0.08221779018640518,
1411
+ "eval_runtime": 477.8152,
1412
+ "eval_samples_per_second": 1674.287,
1413
+ "eval_steps_per_second": 26.161,
1414
+ "step": 7200
1415
  }
1416
  ],
1417
  "logging_steps": 50,
 
1431
  "attributes": {}
1432
  }
1433
  },
1434
+ "total_flos": 9.108260291556147e+17,
1435
  "train_batch_size": 256,
1436
  "trial_name": null,
1437
  "trial_params": null