Token Classification
Safetensors
English
deberta-v2
shawnrushefsky commited on
Commit
e426857
·
verified ·
1 Parent(s): 4c1e1a0

Training in progress, step 11400, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d98df63972fc2e4daaf1bd1e0ab297746f7a42f2ae676738162e55aab2f233e
3
  size 735396724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19feaf516b059174a7559045838c80b23e728963d12ebd98ebd042f85d30ad33
3
  size 735396724
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1976977350f5c06ce05fd495ce5eaf67c2815489ff2ffbbd80f76afdedb9bb1a
3
  size 1470915147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d48bb370823479cf797baa7c6a10c27fc60837d7ac6e6d1d80594d57e5c2f9
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:f9c475e1510f960f87a6874d3ed5ae40a4b21f142d5011bcc012b7d12e77f66e
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c372f7c076b1c50834e1501f00c5f788f7984de6d62a11166ade222fd914c8ea
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 sha256:0d2b56a873b62edf08353311a2201583d72f44f872314034d3be94b7c12f3e4d
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d819f3c2ad802003070d1d634e895d7bcef47d8af5816679be60168bc612206
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 sha256:88f0371238d70128fe141263becf02bdfcbfba1d0e867268958035a7e3bb8475
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e16c00e8b60a67ec266c533d6c8c4aba642004395d7a779e660cde1047c633e7
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:b0688c8441a9e4642075bb058465b7aefcd27cf469f26322931a1567c5d2fb8f
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:780a3c830aaa880addab283cff76df7fdc32362399aa06f77f187171379785a5
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 sha256:784a2938c290d5b3c2d1c5901e3fd434067031b6ab7697365d4278701489564f
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0791ba85315960c66211042a4cdc97593ea0f4a1aea2300b5fc4ddd2740039a2
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 sha256:2f9249a45d30a112fd8cd68af77ed8efdc0969042dc1616fb5742280ead2095a
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24070b7b5aaf0b19cd45a2ea7d0de7bae60117d1135f43858941002abf09caa9
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 sha256:0398926fab265216a618d307e026fbf996d06e83fa3ee6b51d9b15aea231b5bf
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94e8e70bb3314cae1320cf1a756e495a1d99669283be77d1c4493b59b042745
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 sha256:0eeee6408ad97126e72aa43e82b1d5996ea3b49775211b279199c49d1997f1a7
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28dcc79718f618242551bb92fbdec7eecd734f17276ee31ecb83e27d3545b09e
3
  size 16325
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a92e6498d5f72094ee0b67eed3d450cbc8b1d525879162859225a9eaea2d9b41
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965c44b89c096a33bf04ac18d5299e9f65111da8d56850cc0844f723d8f12c5b
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": 2.866649603276171,
6
  "eval_steps": 200,
7
- "global_step": 11200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2192,6 +2192,45 @@
2192
  "eval_samples_per_second": 1674.16,
2193
  "eval_steps_per_second": 26.159,
2194
  "step": 11200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2195
  }
2196
  ],
2197
  "logging_steps": 50,
@@ -2211,7 +2250,7 @@
2211
  "attributes": {}
2212
  }
2213
  },
2214
- "total_flos": 1.416591358310744e+18,
2215
  "train_batch_size": 256,
2216
  "trial_name": null,
2217
  "trial_params": null
 
2
  "best_global_step": 9800,
3
  "best_metric": 0.7528361702207996,
4
  "best_model_checkpoint": "model/checkpoint-9800",
5
+ "epoch": 2.9178397747632454,
6
  "eval_steps": 200,
7
+ "global_step": 11400,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2192
  "eval_samples_per_second": 1674.16,
2193
  "eval_steps_per_second": 26.159,
2194
  "step": 11200
2195
+ },
2196
+ {
2197
+ "epoch": 2.87944714614794,
2198
+ "grad_norm": 0.18220539391040802,
2199
+ "learning_rate": 1.0617040593084437e-07,
2200
+ "loss": 0.0786,
2201
+ "step": 11250
2202
+ },
2203
+ {
2204
+ "epoch": 2.892244689019708,
2205
+ "grad_norm": 0.2002861201763153,
2206
+ "learning_rate": 8.48922300166477e-08,
2207
+ "loss": 0.08,
2208
+ "step": 11300
2209
+ },
2210
+ {
2211
+ "epoch": 2.9050422318914766,
2212
+ "grad_norm": 0.1861000508069992,
2213
+ "learning_rate": 6.59840020429292e-08,
2214
+ "loss": 0.0795,
2215
+ "step": 11350
2216
+ },
2217
+ {
2218
+ "epoch": 2.9178397747632454,
2219
+ "grad_norm": 0.1750432401895523,
2220
+ "learning_rate": 4.944933144399449e-08,
2221
+ "loss": 0.0769,
2222
+ "step": 11400
2223
+ },
2224
+ {
2225
+ "epoch": 2.9178397747632454,
2226
+ "eval_entity_f1": 0.7501227907527926,
2227
+ "eval_entity_precision": 0.6741361926126912,
2228
+ "eval_entity_recall": 0.8839860821211923,
2229
+ "eval_loss": 0.08125095069408417,
2230
+ "eval_runtime": 477.7843,
2231
+ "eval_samples_per_second": 1674.396,
2232
+ "eval_steps_per_second": 26.162,
2233
+ "step": 11400
2234
  }
2235
  ],
2236
  "logging_steps": 50,
 
2250
  "attributes": {}
2251
  }
2252
  },
2253
+ "total_flos": 1.4418667544426578e+18,
2254
  "train_batch_size": 256,
2255
  "trial_name": null,
2256
  "trial_params": null