Token Classification
Safetensors
English
deberta-v2
shawnrushefsky commited on
Commit
da36749
·
verified ·
1 Parent(s): 98aabab

Training in progress, step 10200, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23e0dd1d46a47384406ae5a72bfe3ab3ba6e99bfe98ea609fffa57fa98a4e38d
3
  size 735396724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8713f587d8c2de0f5d2143c25048db75c3915db2842308fea5376d39a41f4308
3
  size 735396724
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2f79cdb81b3fd1ec7ff307c00eb73498c1a231ceaeb2db78ea584b637d9ec98
3
  size 1470915147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f178e6e3e9cc0892a04a8bf0a1a5a49fb89117226dbce494e8501df1fc95dd95
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:d2b05943add517814c436fa6361081d163823e7a55a4ef9e3212fb73da299b7e
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4539ebbd96f2aa7f7df4ece7387a123cc7e62446465a52204550291310cc9673
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:e61730fadae7f56a564062b442edf74ed2372f26d9196e3835831f574e5df201
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2abd277b5c9471b93320941fbc28ed1e0b802dea6507be1a2d1fed167eb2d3a
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 sha256:1983536013c7a3223de0fc3f2f4e450bf680fb5eacfb8a06148e798107b8488f
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afd70d4d20b2d0f8443eeb250ed5ba2dd766848e4552c631472302a62437057e
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:ae00fbf9a337446081d2410c93cd878d4ade42334323d1c72b5cc6cd67220355
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb6d7cb46ce79a6aa48d2d9541300f4bcf87ececda0533cc74f370d8de82fdce
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:d0f9495d62346a50abca2fe8481c6cfa869178659f5842f86623fa9e7305f8ca
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4aa570420d77f8543e4173c9ad60b9cf8d58781ba858c988b07b6b2ba16e172
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 sha256:34f635ab023e169509272e47aac723d4d85c1796814f5312880b38b6b8f01184
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c578e3b57602459b8c3dc95764e9fd946698d00e901c32b0601f7fe16847c044
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 sha256:6983e6ccfcf55f4dbba47b561193e5fccc9d7d3908ec878b09d99375fc88a8be
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944af4f170b65f910ba1fc6cfb4614fa2feb535003323d30840c7fd70e16e85c
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:dda7660a32754567d67eada126e70cccf77f094f58b5845ab27201fd82039445
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5522d39ceff101d1557a26232b5181c9d750a581e0c05ac5a7025e8b6cf9b2c3
3
  size 16325
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:758bb68ccd339a1b793c16faba9699654df4b43549411a47d631c04b4bfa1fff
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03a202aac98b5e09489a600640b8374ed0c4d649131c9b76a7d50925a164aa1f
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": 2.559508574353724,
6
  "eval_steps": 200,
7
- "global_step": 10000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1958,6 +1958,45 @@
1958
  "eval_samples_per_second": 1674.4,
1959
  "eval_steps_per_second": 26.162,
1960
  "step": 10000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1961
  }
1962
  ],
1963
  "logging_steps": 50,
@@ -1977,7 +2016,7 @@
1977
  "attributes": {}
1978
  }
1979
  },
1980
- "total_flos": 1.2648850168658002e+18,
1981
  "train_batch_size": 256,
1982
  "trial_name": null,
1983
  "trial_params": null
 
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,
 
1958
  "eval_samples_per_second": 1674.4,
1959
  "eval_steps_per_second": 26.162,
1960
  "step": 10000
1961
+ },
1962
+ {
1963
+ "epoch": 2.5723061172254926,
1964
+ "grad_norm": 0.18073636293411255,
1965
+ "learning_rate": 1.310594711488078e-06,
1966
+ "loss": 0.0755,
1967
+ "step": 10050
1968
+ },
1969
+ {
1970
+ "epoch": 2.5851036600972614,
1971
+ "grad_norm": 0.2599385976791382,
1972
+ "learning_rate": 1.234679653254088e-06,
1973
+ "loss": 0.0799,
1974
+ "step": 10100
1975
+ },
1976
+ {
1977
+ "epoch": 2.59790120296903,
1978
+ "grad_norm": 0.17557959258556366,
1979
+ "learning_rate": 1.1609150574445255e-06,
1980
+ "loss": 0.0809,
1981
+ "step": 10150
1982
+ },
1983
+ {
1984
+ "epoch": 2.6106987458407986,
1985
+ "grad_norm": 0.17557652294635773,
1986
+ "learning_rate": 1.0893150051495562e-06,
1987
+ "loss": 0.0814,
1988
+ "step": 10200
1989
+ },
1990
+ {
1991
+ "epoch": 2.6106987458407986,
1992
+ "eval_entity_f1": 0.7500700322882474,
1993
+ "eval_entity_precision": 0.6743530583815431,
1994
+ "eval_entity_recall": 0.8843906953232014,
1995
+ "eval_loss": 0.08134948462247849,
1996
+ "eval_runtime": 480.0458,
1997
+ "eval_samples_per_second": 1666.508,
1998
+ "eval_steps_per_second": 26.039,
1999
+ "step": 10200
2000
  }
2001
  ],
2002
  "logging_steps": 50,
 
2016
  "attributes": {}
2017
  }
2018
  },
2019
+ "total_flos": 1.2902474370881946e+18,
2020
  "train_batch_size": 256,
2021
  "trial_name": null,
2022
  "trial_params": null