Token Classification
Safetensors
English
deberta-v2
shawnrushefsky commited on
Commit
6e4c269
·
verified ·
1 Parent(s): 3513e89

Training in progress, step 9000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9143105b7a0ae7436a781c2123653e59d0bc5777af0f60a58c6e5974e9e17da
3
  size 735396724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd1d2416880184ab833df5a811703854de5f9951183cac505f4585c69c199897
3
  size 735396724
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e17f79128b8c46fea810a73a0596f0c826ea16768d60fc0029154f29c45cb5a
3
  size 1470915147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c1e77912808125dadcd4116b0b548a4795cc850189200f5aab5f3b4f26f4a51
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:a3dcfe51a302c55f31e9553d92e3297e4cfa0c1aeab5c3ae0f2b9cea4455e2a1
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04715fe6b3719188480603a744ca1968e661b64568d12ca7bcfa04a66d51dda4
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 sha256:1bbe87f56d7657538df7f5b961dbd0cd4ea7be68df32dd2910961a0cec5ed736
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d578e7b8e2ef8417897e0fee8b5a732d8b257bf8e28ee01d307e3040e6bfe643
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 sha256:13d92d7a789f5a6f7063784219e24e0324caef52bfd4282e5e7f0b883768fd13
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07a54660e22add8be892bc97f902233e045918b5949a7f393497f60a4ccd02d8
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 sha256:80d4e88850a75847bad142d32f7c90d97c344d26c24cb30bb810406297fdedbf
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:954882ee6ab46bc24979e0477fac68e21e18e5e1e59d0981138766d32e5a57a3
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:b95894c8265766c8bce6ab907127675946dc54c598e9b6822c796e30da4c41ea
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76f4f0ac2d237da005cfc71348316ed32e740540ede4dc5f312044bbaf2c9dc
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 sha256:2ef85c5173d42b63aea8a1fd8c07be0604b878eebd09ec487489646edf3bcbf0
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda981b0b633bc6514d21246125ad9ab23efa50b61c19b86954925aa32f1183f
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:b4394407f7e5c024d2b81e4054eb912193dcf5838e2888f856dd25a5a9063986
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2f28acb7cc7bdfd581aefdea9dd9858c2e6b2f5b2a37853f74cc64f54386ddd
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 sha256:2e46a2a820de813be1f7d9c5181c505914664d3216706c86e94e5a462108bcd2
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11d434efce32226b940065d93ef3ab9b5d1a52b4dc91048f8fb756515365c17
3
  size 16325
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5f778cac1dbe7aba94e2c0d7e193c86e73795716c113cbc126f6dc89b780319
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f140d69b2e500ee56025bb52538b2aff69eca1ed68a9c35062689a7ec9e7477
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": 2.252367545431277,
6
  "eval_steps": 200,
7
- "global_step": 8800,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1724,6 +1724,45 @@
1724
  "eval_samples_per_second": 1673.125,
1725
  "eval_steps_per_second": 26.143,
1726
  "step": 8800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1727
  }
1728
  ],
1729
  "logging_steps": 50,
@@ -1743,7 +1782,7 @@
1743
  "attributes": {}
1744
  }
1745
  },
1746
- "total_flos": 1.1132399592354611e+18,
1747
  "train_batch_size": 256,
1748
  "trial_name": null,
1749
  "trial_params": null
 
2
  "best_global_step": 8000,
3
  "best_metric": 0.7521935121655035,
4
  "best_model_checkpoint": "model/checkpoint-8000",
5
+ "epoch": 2.303557716918352,
6
  "eval_steps": 200,
7
+ "global_step": 9000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1724
  "eval_samples_per_second": 1673.125,
1725
  "eval_steps_per_second": 26.143,
1726
  "step": 8800
1727
+ },
1728
+ {
1729
+ "epoch": 2.265165088303046,
1730
+ "grad_norm": 0.18763253092765808,
1731
+ "learning_rate": 3.734125462249559e-06,
1732
+ "loss": 0.0811,
1733
+ "step": 8850
1734
+ },
1735
+ {
1736
+ "epoch": 2.2779626311748142,
1737
+ "grad_norm": 0.20808328688144684,
1738
+ "learning_rate": 3.6118446079952557e-06,
1739
+ "loss": 0.0799,
1740
+ "step": 8900
1741
+ },
1742
+ {
1743
+ "epoch": 2.290760174046583,
1744
+ "grad_norm": 0.20532524585723877,
1745
+ "learning_rate": 3.4912604337824106e-06,
1746
+ "loss": 0.0768,
1747
+ "step": 8950
1748
+ },
1749
+ {
1750
+ "epoch": 2.303557716918352,
1751
+ "grad_norm": 0.19934144616127014,
1752
+ "learning_rate": 3.3723959581961686e-06,
1753
+ "loss": 0.0783,
1754
+ "step": 9000
1755
+ },
1756
+ {
1757
+ "epoch": 2.303557716918352,
1758
+ "eval_entity_f1": 0.7505762647056883,
1759
+ "eval_entity_precision": 0.6747397233043843,
1760
+ "eval_entity_recall": 0.8838148604135412,
1761
+ "eval_loss": 0.08156638592481613,
1762
+ "eval_runtime": 478.046,
1763
+ "eval_samples_per_second": 1673.479,
1764
+ "eval_steps_per_second": 26.148,
1765
+ "step": 9000
1766
  }
1767
  ],
1768
  "logging_steps": 50,
 
1782
  "attributes": {}
1783
  }
1784
  },
1785
+ "total_flos": 1.1385167925708063e+18,
1786
  "train_batch_size": 256,
1787
  "trial_name": null,
1788
  "trial_params": null