Token Classification
Safetensors
English
deberta-v2
shawnrushefsky commited on
Commit
022d120
·
verified ·
1 Parent(s): 3f9e4c6

Training in progress, step 11600, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19feaf516b059174a7559045838c80b23e728963d12ebd98ebd042f85d30ad33
3
  size 735396724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd050329dfe4f3d34fd3d8146820eccab83580a9419868542e3e694818350a7
3
  size 735396724
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56d48bb370823479cf797baa7c6a10c27fc60837d7ac6e6d1d80594d57e5c2f9
3
  size 1470915147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257531cd2b8a983cdc8963fb3b73a1ea95b2711fac274b5b07d92dcbd1bc7a7c
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:c372f7c076b1c50834e1501f00c5f788f7984de6d62a11166ade222fd914c8ea
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8d2e68812d0da06b4571de7a1e628ee6cd6951efcbe132b6f22cf1f7646bccf
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 sha256:6d819f3c2ad802003070d1d634e895d7bcef47d8af5816679be60168bc612206
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b37b02b37d8c8b6a97c3e70768708ece4856f6becc3bec7fa2c61ef8a63692db
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:e16c00e8b60a67ec266c533d6c8c4aba642004395d7a779e660cde1047c633e7
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44812d3395d40e70c9f32c21033a75eb598058b15c17c86f7fa9d4ff8ca1aa4
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 sha256:780a3c830aaa880addab283cff76df7fdc32362399aa06f77f187171379785a5
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5dcb4ab9d8cab2ede679bfb12d8611e8d4d10b7dd4878c544f081cd19c8f61b
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 sha256:0791ba85315960c66211042a4cdc97593ea0f4a1aea2300b5fc4ddd2740039a2
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd81846c05c79fc4f44d4ed8a3afc2d598a3a8f13c95b910ef96283a7fd810e
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 sha256:24070b7b5aaf0b19cd45a2ea7d0de7bae60117d1135f43858941002abf09caa9
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7a832c79f26ee6415fb94adc8f6ec27fe836740a788ac8b18b53cca8403119
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:b94e8e70bb3314cae1320cf1a756e495a1d99669283be77d1c4493b59b042745
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487c825fd31296d943b237024440c251557053f31f3640f17813497ab9afdf9f
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 sha256:28dcc79718f618242551bb92fbdec7eecd734f17276ee31ecb83e27d3545b09e
3
  size 16325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af4fdbe897f6a9e4d589ccf20ceae33b17d6677e1f22d3a55dfa590b6304624
3
  size 16325
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:965c44b89c096a33bf04ac18d5299e9f65111da8d56850cc0844f723d8f12c5b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3685a20f48a7bea1d8ac9f36223299325cf9a37163c4f18ef985397282a6b4
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": 2.9178397747632454,
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,
@@ -2231,6 +2231,45 @@
2231
  "eval_samples_per_second": 1674.396,
2232
  "eval_steps_per_second": 26.162,
2233
  "step": 11400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2234
  }
2235
  ],
2236
  "logging_steps": 50,
@@ -2250,7 +2289,7 @@
2250
  "attributes": {}
2251
  }
2252
  },
2253
- "total_flos": 1.4418667544426578e+18,
2254
  "train_batch_size": 256,
2255
  "trial_name": null,
2256
  "trial_params": null
 
2
  "best_global_step": 9800,
3
  "best_metric": 0.7528361702207996,
4
  "best_model_checkpoint": "model/checkpoint-9800",
5
+ "epoch": 2.96902994625032,
6
  "eval_steps": 200,
7
+ "global_step": 11600,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2231
  "eval_samples_per_second": 1674.396,
2232
  "eval_steps_per_second": 26.162,
2233
  "step": 11400
2234
+ },
2235
+ {
2236
+ "epoch": 2.9306373176350142,
2237
+ "grad_norm": 0.23810507357120514,
2238
+ "learning_rate": 3.529137456043247e-08,
2239
+ "loss": 0.0808,
2240
+ "step": 11450
2241
+ },
2242
+ {
2243
+ "epoch": 2.9434348605067826,
2244
+ "grad_norm": 0.17240500450134277,
2245
+ "learning_rate": 2.3512834036583386e-08,
2246
+ "loss": 0.0785,
2247
+ "step": 11500
2248
+ },
2249
+ {
2250
+ "epoch": 2.9562324033785514,
2251
+ "grad_norm": 0.15246008336544037,
2252
+ "learning_rate": 1.4115958304629361e-08,
2253
+ "loss": 0.0795,
2254
+ "step": 11550
2255
+ },
2256
+ {
2257
+ "epoch": 2.96902994625032,
2258
+ "grad_norm": 0.21297241747379303,
2259
+ "learning_rate": 7.10254115538489e-09,
2260
+ "loss": 0.0789,
2261
+ "step": 11600
2262
+ },
2263
+ {
2264
+ "epoch": 2.96902994625032,
2265
+ "eval_entity_f1": 0.7501707038653356,
2266
+ "eval_entity_precision": 0.6742491385967203,
2267
+ "eval_entity_recall": 0.883897413736873,
2268
+ "eval_loss": 0.08122596889734268,
2269
+ "eval_runtime": 476.3572,
2270
+ "eval_samples_per_second": 1679.412,
2271
+ "eval_steps_per_second": 26.241,
2272
+ "step": 11600
2273
  }
2274
  ],
2275
  "logging_steps": 50,
 
2289
  "attributes": {}
2290
  }
2291
  },
2292
+ "total_flos": 1.4671988591752643e+18,
2293
  "train_batch_size": 256,
2294
  "trial_name": null,
2295
  "trial_params": null