Hugging Face's logo

Shaer-AI
/
ARBERT-base-submeter-classifier

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
NourFakih commited on
Commit
968ab8f
·
verified ·
1 Parent(s): 52c6eed

Training in progress, step 8500, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +24 -6
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1729ade4a3b27dcd5054a3dbd9159e2fdd261f96af28691317d91e1b969f919b
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a69da797b91f150e7fcd691c5ef84ea08d8bb1bb96b57b022954521a2834331
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b91c4aa51808a21774863a308dfe5a96613a0cc00e12b509773113228d3c154
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee61b09be180b57917ebcd2abdec50c65ee7386897f52f6099a8a201900363dd
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dab905411ef3135d4cd3876442f0ded4fb6f75e082af92eeebd93053a6153f2
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e14abb68a69b1d3b6d7aa43acf2e900d6d4bf6e4c47d7389f68b812c5983af2c
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:022915fa8ac65fae0f13853519b8aa7ee79efd632a399c1f64c6b87bab0b057a
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793190053d1293f4ec72cd72bea61df6e622ffbc2a94ef18fbadb35cfca4423b
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fcfd5ff5ecd302e9792a65b2975f4ea0f2cce1094a1020251dbc681c29a4d57
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7e830af27401c6dbafa250f1dbae41b4878f5981f0bf0a06f9a0fd838e21b57
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 8000,
3
- "best_metric": 0.964472972972973,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-8000",
5
- "epoch": 1.3836374643258669,
6
  "eval_steps": 500,
7
- "global_step": 8000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -296,6 +296,24 @@
296
  "eval_steps_per_second": 3.453,
297
  "eval_weighted_f1": 0.9581300625445718,
298
  "step": 8000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
299
  }
300
  ],
301
  "logging_steps": 500,
@@ -315,7 +333,7 @@
315
  "attributes": {}
316
  }
317
  },
318
- "total_flos": 3.3681979017120384e+16,
319
  "train_batch_size": 128,
320
  "trial_name": null,
321
  "trial_params": null
 
1
  {
2
+ "best_global_step": 8500,
3
+ "best_metric": 0.9651378378378378,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-8500",
5
+ "epoch": 1.470120211017902,
6
  "eval_steps": 500,
7
+ "global_step": 8500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
296
  "eval_steps_per_second": 3.453,
297
  "eval_weighted_f1": 0.9581300625445718,
298
  "step": 8000
299
+ },
300
+ {
301
+ "epoch": 1.470120211017902,
302
+ "grad_norm": 3.3662569522857666,
303
+ "learning_rate": 2.5501556554825323e-05,
304
+ "loss": 0.1201,
305
+ "step": 8500
306
+ },
307
+ {
308
+ "epoch": 1.470120211017902,
309
+ "eval_accuracy": 0.9651378378378378,
310
+ "eval_loss": 0.12952136993408203,
311
+ "eval_macro_f1": 0.5705480082509794,
312
+ "eval_runtime": 418.5068,
313
+ "eval_samples_per_second": 884.095,
314
+ "eval_steps_per_second": 3.455,
315
+ "eval_weighted_f1": 0.9587555599089429,
316
+ "step": 8500
317
  }
318
  ],
319
  "logging_steps": 500,
 
333
  "attributes": {}
334
  }
335
  },
336
+ "total_flos": 3.5787302135712384e+16,
337
  "train_batch_size": 128,
338
  "trial_name": null,
339
  "trial_params": null