Token Classification
Safetensors
English
deberta-v2
shawnrushefsky commited on
Commit
6810aea
·
verified ·
1 Parent(s): 7af5095

Training in progress, step 10000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ade3a987bda6b550c43dc13485050e50f44bad5a2c59f156a6c24f534e2b131d
3
  size 735396724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23e0dd1d46a47384406ae5a72bfe3ab3ba6e99bfe98ea609fffa57fa98a4e38d
3
  size 735396724
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f928f7e80b595e28fe7b098eecef521b75fd1dbda5cc27f08970bb3ea5eb2f9
3
  size 1470915147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f79cdb81b3fd1ec7ff307c00eb73498c1a231ceaeb2db78ea584b637d9ec98
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 sha256:7826acfda3eb57f9ecc0eeacd8917a453b70ee075254e9164fd20537d7cd6194
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2b05943add517814c436fa6361081d163823e7a55a4ef9e3212fb73da299b7e
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 sha256:9923e9700d500e4bd9d4a487dd6201eafe196397f2376d3ba9040cb68c586b7b
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61730fadae7f56a564062b442edf74ed2372f26d9196e3835831f574e5df201
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:ee229b5a56fd3a0599ac9a7cf41c74be670af6c72d7e2cca9ea76da9da2e2c62
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1983536013c7a3223de0fc3f2f4e450bf680fb5eacfb8a06148e798107b8488f
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 sha256:4e73456bcae806330fbb6d1111265be5df05d67119803b7fc1c123712da05449
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae00fbf9a337446081d2410c93cd878d4ade42334323d1c72b5cc6cd67220355
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 sha256:1d65d476e018dbafbf8f10e590a8a5d35bad81fbc34a8877873996304c546ea8
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f9495d62346a50abca2fe8481c6cfa869178659f5842f86623fa9e7305f8ca
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 sha256:2ee1c2152dd6c533fca21bd06f6b341e4b4c2fee774b95445e7be0561edb6f75
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34f635ab023e169509272e47aac723d4d85c1796814f5312880b38b6b8f01184
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 sha256:0229a02d02340d8ddfcb2c2c7f52e7a4ef08d3dbb5f58de055824c0f442ddb33
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6983e6ccfcf55f4dbba47b561193e5fccc9d7d3908ec878b09d99375fc88a8be
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 sha256:831226e343c7371254425c3f224e8aa5806593fca5f8c75851e4021e9dc0bdeb
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda7660a32754567d67eada126e70cccf77f094f58b5845ab27201fd82039445
3
  size 16325
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:670acb7d7917fc04cd7835096d2552ff2ece1482bcb1d01c0bfb3fd19b79af68
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:758bb68ccd339a1b793c16faba9699654df4b43549411a47d631c04b4bfa1fff
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": 2.5083184028666494,
6
  "eval_steps": 200,
7
- "global_step": 9800,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1919,6 +1919,45 @@
1919
  "eval_samples_per_second": 1672.301,
1920
  "eval_steps_per_second": 26.13,
1921
  "step": 9800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1922
  }
1923
  ],
1924
  "logging_steps": 50,
@@ -1938,7 +1977,7 @@
1938
  "attributes": {}
1939
  }
1940
  },
1941
- "total_flos": 1.2395854475842028e+18,
1942
  "train_batch_size": 256,
1943
  "trial_name": null,
1944
  "trial_params": null
 
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,
 
1919
  "eval_samples_per_second": 1672.301,
1920
  "eval_steps_per_second": 26.13,
1921
  "step": 9800
1922
+ },
1923
+ {
1924
+ "epoch": 2.5211159457384182,
1925
+ "grad_norm": 0.21187463402748108,
1926
+ "learning_rate": 1.635463637770432e-06,
1927
+ "loss": 0.0815,
1928
+ "step": 9850
1929
+ },
1930
+ {
1931
+ "epoch": 2.533913488610187,
1932
+ "grad_norm": 0.17519764602184296,
1933
+ "learning_rate": 1.5510957089114195e-06,
1934
+ "loss": 0.078,
1935
+ "step": 9900
1936
+ },
1937
+ {
1938
+ "epoch": 2.5467110314819554,
1939
+ "grad_norm": 0.19588303565979004,
1940
+ "learning_rate": 1.4688178411018869e-06,
1941
+ "loss": 0.0785,
1942
+ "step": 9950
1943
+ },
1944
+ {
1945
+ "epoch": 2.559508574353724,
1946
+ "grad_norm": 0.28233495354652405,
1947
+ "learning_rate": 1.3886457405497058e-06,
1948
+ "loss": 0.0796,
1949
+ "step": 10000
1950
+ },
1951
+ {
1952
+ "epoch": 2.559508574353724,
1953
+ "eval_entity_f1": 0.748310894114638,
1954
+ "eval_entity_precision": 0.6711821127565412,
1955
+ "eval_entity_recall": 0.8848024427630291,
1956
+ "eval_loss": 0.08149130642414093,
1957
+ "eval_runtime": 477.7832,
1958
+ "eval_samples_per_second": 1674.4,
1959
+ "eval_steps_per_second": 26.162,
1960
+ "step": 10000
1961
  }
1962
  ],
1963
  "logging_steps": 50,
 
1977
  "attributes": {}
1978
  }
1979
  },
1980
+ "total_flos": 1.2648850168658002e+18,
1981
  "train_batch_size": 256,
1982
  "trial_name": null,
1983
  "trial_params": null