Hugging Face's logo

Shresthadev403
/
ner-bert-ingredients

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Metrics Community
Shresthadev403 commited on
Commit
99ea14a
·
1 Parent(s): 0b338d3

End of training

Browse files
Files changed (4) hide show
  1. README.md +5 -5
  2. logs/events.out.tfevents.1704794705.1ec128b7e2b3.26.0 +2 -2
  3. model.safetensors +1 -1
  4. trainer_state.json +17 -3
README.md CHANGED
@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - eval_loss: 1.6165
17
- - eval_runtime: 83.7157
18
- - eval_samples_per_second: 59.726
19
  - eval_steps_per_second: 0.944
20
- - epoch: 20.21
21
- - step: 15000
22
 
23
  ## Model description
24
 
 
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - eval_loss: 1.4814
17
+ - eval_runtime: 83.6915
18
+ - eval_samples_per_second: 59.743
19
  - eval_steps_per_second: 0.944
20
+ - epoch: 21.23
21
+ - step: 15750
22
 
23
  ## Model description
24
 
logs/events.out.tfevents.1704794705.1ec128b7e2b3.26.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db9b2d2e23b405c2a1f9faf31a2cdda4b1ad029412651e4b5c24fd7aac499cd1
3
- size 1717752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e6fce581f69f6b8df26a5ae99b42e4faff7058be92cb7204a0bb7d5adc4e500
3
+ size 1718180
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8aa7a8ea23ee61a82ff7793d70af1591884b53a4218af2de6d18c704093ed320
3
  size 535667604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835d5d712ae076db3d3a830cc933ae82389d194740e0f320d8a5d89088cef4e6
3
  size 535667604
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.3803095817565918,
3
  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-12750",
4
- "epoch": 20.21488716739643,
5
  "eval_steps": 750,
6
- "global_step": 15000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -287,6 +287,20 @@
287
  "eval_samples_per_second": 59.726,
288
  "eval_steps_per_second": 0.944,
289
  "step": 15000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
290
  }
291
  ],
292
  "logging_steps": 750,
@@ -294,7 +308,7 @@
294
  "num_input_tokens_seen": 0,
295
  "num_train_epochs": 100,
296
  "save_steps": 750,
297
- "total_flos": 6.491971115016192e+17,
298
  "train_batch_size": 16,
299
  "trial_name": null,
300
  "trial_params": null
 
1
  {
2
  "best_metric": 1.3803095817565918,
3
  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-12750",
4
+ "epoch": 21.22532839339845,
5
  "eval_steps": 750,
6
+ "global_step": 15750,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
287
  "eval_samples_per_second": 59.726,
288
  "eval_steps_per_second": 0.944,
289
  "step": 15000
290
+ },
291
+ {
292
+ "epoch": 21.23,
293
+ "learning_rate": 4.84845013477089e-05,
294
+ "loss": 1.002,
295
+ "step": 15750
296
+ },
297
+ {
298
+ "epoch": 21.23,
299
+ "eval_loss": 1.481406331062317,
300
+ "eval_runtime": 83.6915,
301
+ "eval_samples_per_second": 59.743,
302
+ "eval_steps_per_second": 0.944,
303
+ "step": 15750
304
  }
305
  ],
306
  "logging_steps": 750,
 
308
  "num_input_tokens_seen": 0,
309
  "num_train_epochs": 100,
310
  "save_steps": 750,
311
+ "total_flos": 6.816569670767002e+17,
312
  "train_batch_size": 16,
313
  "trial_name": null,
314
  "trial_params": null