Hugging Face's logo

T0KII
/
MASRIBERTv3

Fill-Mask
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
T0KII commited on
Commit
351c944
·
verified ·
1 Parent(s): 562815b

Training in progress, step 10000, checkpoint

Browse files
Files changed (7) 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 +78 -6
  7. last-checkpoint/training_args.bin +1 -1
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e506b28af94c9f67ed9877547aca9647b078ad697e757ce9d0fd58f033848a2
3
  size 775678032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd7a22be120abec7cae4d835d4800211fd1c582dac90b575825986a3f3babf2b
3
  size 775678032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd807cd6d5226dc57760c3eb773655ceee8cf46f2e27dadacc31cbcf814fd8cf
3
  size 1551478091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfa545be0c9d7b43d6549f4f1bf0f2071ca9d4210a9de6d823275e4c73628332
3
  size 1551478091
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b5ee8ed6de8ebff1f4e53f6af005a75173401b22aced8e149a6ca7d20e5d75d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f4b97af2f4a85a98fa4869b40f7b4371fe0109d9dcd77c19217a58c88e458e
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 sha256:1e6fd97f105f8edb4cfe7d5753c1c5716920ac3feb07414e58ddd6a461f2d28f
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97cf90b08eb246acaa107a6f5e6030cf607ba438f27aa86bb0197faea0282107
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9807d918a10d1f4568a93321ac8a3b95086950e9354315755af2e5e74af21105
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 8000,
3
- "best_metric": 4.758424758911133,
4
- "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-8000",
5
- "epoch": 1.2024878800405878,
6
  "eval_steps": 1000,
7
- "global_step": 8000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -296,6 +296,78 @@
296
  "eval_samples_per_second": 72.134,
297
  "eval_steps_per_second": 1.128,
298
  "step": 8000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
299
  }
300
  ],
301
  "logging_steps": 250,
@@ -324,7 +396,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.349195872843607e+17,
328
  "train_batch_size": 32,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
+ "best_global_step": 10000,
3
+ "best_metric": 4.5992112159729,
4
+ "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-10000",
5
+ "epoch": 1.5031380360028561,
6
  "eval_steps": 1000,
7
+ "global_step": 10000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
296
  "eval_samples_per_second": 72.134,
297
  "eval_steps_per_second": 1.128,
298
  "step": 8000
299
+ },
300
+ {
301
+ "epoch": 1.2400691495358713,
302
+ "grad_norm": 94.54589080810547,
303
+ "learning_rate": 3.905384188481714e-05,
304
+ "loss": 39.47437890625,
305
+ "step": 8250
306
+ },
307
+ {
308
+ "epoch": 1.2776504190311548,
309
+ "grad_norm": 84.85308837890625,
310
+ "learning_rate": 3.843760628720439e-05,
311
+ "loss": 39.3814765625,
312
+ "step": 8500
313
+ },
314
+ {
315
+ "epoch": 1.3152316885264383,
316
+ "grad_norm": 80.48727416992188,
317
+ "learning_rate": 3.7809667206761164e-05,
318
+ "loss": 39.18900390625,
319
+ "step": 8750
320
+ },
321
+ {
322
+ "epoch": 1.352812958021722,
323
+ "grad_norm": 79.16352844238281,
324
+ "learning_rate": 3.717057154701251e-05,
325
+ "loss": 39.15230859375,
326
+ "step": 9000
327
+ },
328
+ {
329
+ "epoch": 1.352812958021722,
330
+ "eval_loss": 4.669365406036377,
331
+ "eval_runtime": 240.8713,
332
+ "eval_samples_per_second": 71.416,
333
+ "eval_steps_per_second": 1.117,
334
+ "step": 9000
335
+ },
336
+ {
337
+ "epoch": 1.3903942275170056,
338
+ "grad_norm": 81.47567749023438,
339
+ "learning_rate": 3.6520875928305904e-05,
340
+ "loss": 38.7915625,
341
+ "step": 9250
342
+ },
343
+ {
344
+ "epoch": 1.427975497012289,
345
+ "grad_norm": 79.67969512939453,
346
+ "learning_rate": 3.58611462030228e-05,
347
+ "loss": 38.70076953125,
348
+ "step": 9500
349
+ },
350
+ {
351
+ "epoch": 1.4655567665075726,
352
+ "grad_norm": 78.06887817382812,
353
+ "learning_rate": 3.5191956962749483e-05,
354
+ "loss": 38.5454296875,
355
+ "step": 9750
356
+ },
357
+ {
358
+ "epoch": 1.5031380360028561,
359
+ "grad_norm": 81.57176971435547,
360
+ "learning_rate": 3.4513891037836586e-05,
361
+ "loss": 38.56761328125,
362
+ "step": 10000
363
+ },
364
+ {
365
+ "epoch": 1.5031380360028561,
366
+ "eval_loss": 4.5992112159729,
367
+ "eval_runtime": 240.6841,
368
+ "eval_samples_per_second": 71.471,
369
+ "eval_steps_per_second": 1.118,
370
+ "step": 10000
371
  }
372
  ],
373
  "logging_steps": 250,
 
396
  "attributes": {}
397
  }
398
  },
399
+ "total_flos": 1.686529595651927e+17,
400
  "train_batch_size": 32,
401
  "trial_name": null,
402
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e81ef68ecf6d54adfcba782e86ddd0804ab77ba8d53704fbef9e1dfb6174a6bf
3
  size 5201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8537015b69c60e2c29af27ee6860531dfc4207cede0d753719b984b2c5e39a
3
  size 5201