Token Classification
Safetensors
English
deberta-v2
shawnrushefsky commited on
Commit
5b04409
·
verified ·
1 Parent(s): 48363ae

Training in progress, step 10400, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8713f587d8c2de0f5d2143c25048db75c3915db2842308fea5376d39a41f4308
3
  size 735396724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4d0459fc32ebdbb4c72d955db6afc8285dba15ec34803aec397b21ebf32c852
3
  size 735396724
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f178e6e3e9cc0892a04a8bf0a1a5a49fb89117226dbce494e8501df1fc95dd95
3
  size 1470915147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f15d2f339383e170cc694bdf753daa9a2fe9b1c02f001d6857210ddd8e1d6ffc
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 sha256:4539ebbd96f2aa7f7df4ece7387a123cc7e62446465a52204550291310cc9673
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f46f170e0b68c5c5b42c56934b129cc052b3411329fdefd73e8d206cd4dafc
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:f2abd277b5c9471b93320941fbc28ed1e0b802dea6507be1a2d1fed167eb2d3a
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8377970c528cb7550e648cacfe81b5f00e170a2d61ff14790d8a2ec531878a3
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:afd70d4d20b2d0f8443eeb250ed5ba2dd766848e4552c631472302a62437057e
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acba1509435e678aea7aaf23acac8f5f447edb4bf590445c90e5f9bb9ef26fb1
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:fb6d7cb46ce79a6aa48d2d9541300f4bcf87ececda0533cc74f370d8de82fdce
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db2de2c8e8cb1a1f0ee86250b057f946700bc697904d0c3135a861dcdb445a38
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:f4aa570420d77f8543e4173c9ad60b9cf8d58781ba858c988b07b6b2ba16e172
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7252e6e58620b1153a4500c8d445bc128378c4c88fb84bc83ab46236ce700c
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:c578e3b57602459b8c3dc95764e9fd946698d00e901c32b0601f7fe16847c044
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ceffc6542e8e6dae00a1caf28daea9154f59bc867717f443acee07d831abd17
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 sha256:944af4f170b65f910ba1fc6cfb4614fa2feb535003323d30840c7fd70e16e85c
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec51171281e541bfc8e9ac1dbcc38f0a51685add507969f1c6c007d6f464584c
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 sha256:5522d39ceff101d1557a26232b5181c9d750a581e0c05ac5a7025e8b6cf9b2c3
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fede174256e6e90b06fdf044f6fefa4d5b3bcf84817de5773de36300f36aa99e
3
  size 16325
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03a202aac98b5e09489a600640b8374ed0c4d649131c9b76a7d50925a164aa1f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cdfb644032da64d9cfbe342107c30f2038a75f8d51490ab65ad8d67a8c8fd7c
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 9800,
3
  "best_metric": 0.7528361702207996,
4
  "best_model_checkpoint": "model/checkpoint-9800",
5
- "epoch": 2.6106987458407986,
6
  "eval_steps": 200,
7
- "global_step": 10200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1997,6 +1997,45 @@
1997
  "eval_samples_per_second": 1666.508,
1998
  "eval_steps_per_second": 26.039,
1999
  "step": 10200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2000
  }
2001
  ],
2002
  "logging_steps": 50,
@@ -2016,7 +2055,7 @@
2016
  "attributes": {}
2017
  }
2018
  },
2019
- "total_flos": 1.2902474370881946e+18,
2020
  "train_batch_size": 256,
2021
  "trial_name": null,
2022
  "trial_params": null
 
2
  "best_global_step": 9800,
3
  "best_metric": 0.7528361702207996,
4
  "best_model_checkpoint": "model/checkpoint-9800",
5
+ "epoch": 2.661888917327873,
6
  "eval_steps": 200,
7
+ "global_step": 10400,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1997
  "eval_samples_per_second": 1666.508,
1998
  "eval_steps_per_second": 26.039,
1999
  "step": 10200
2000
+ },
2001
+ {
2002
+ "epoch": 2.623496288712567,
2003
+ "grad_norm": 0.19847185909748077,
2004
+ "learning_rate": 1.01989316426475e-06,
2005
+ "loss": 0.0803,
2006
+ "step": 10250
2007
+ },
2008
+ {
2009
+ "epoch": 2.636293831584336,
2010
+ "grad_norm": 0.20816150307655334,
2011
+ "learning_rate": 9.526627868819817e-07,
2012
+ "loss": 0.0801,
2013
+ "step": 10300
2014
+ },
2015
+ {
2016
+ "epoch": 2.6490913744561047,
2017
+ "grad_norm": 0.17276419699192047,
2018
+ "learning_rate": 8.876367067597161e-07,
2019
+ "loss": 0.0796,
2020
+ "step": 10350
2021
+ },
2022
+ {
2023
+ "epoch": 2.661888917327873,
2024
+ "grad_norm": 0.18492333590984344,
2025
+ "learning_rate": 8.248273368731366e-07,
2026
+ "loss": 0.0803,
2027
+ "step": 10400
2028
+ },
2029
+ {
2030
+ "epoch": 2.661888917327873,
2031
+ "eval_entity_f1": 0.7501185957279549,
2032
+ "eval_entity_precision": 0.6742695006330793,
2033
+ "eval_entity_recall": 0.8836416003522275,
2034
+ "eval_loss": 0.08124325424432755,
2035
+ "eval_runtime": 479.8592,
2036
+ "eval_samples_per_second": 1667.156,
2037
+ "eval_steps_per_second": 26.049,
2038
+ "step": 10400
2039
  }
2040
  ],
2041
  "logging_steps": 50,
 
2055
  "attributes": {}
2056
  }
2057
  },
2058
+ "total_flos": 1.3154818028606587e+18,
2059
  "train_batch_size": 256,
2060
  "trial_name": null,
2061
  "trial_params": null