Hugging Face's logo

T0KII
/
MASRIBERTv3

Fill-Mask
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
T0KII commited on
Commit
562815b
·
verified ·
1 Parent(s): daf110f

Training in progress, step 10000

Browse files
Files changed (8) 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 +6 -42
  7. last-checkpoint/training_args.bin +1 -1
  8. model.safetensors +1 -1
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94866cc75aec33c09133a0fb4fa4dfd49fb0b254b4b6ede67f1805569573438d
3
  size 775678032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e506b28af94c9f67ed9877547aca9647b078ad697e757ce9d0fd58f033848a2
3
  size 775678032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9296cbf34201bcdb073c905679753552821e4613b2a1709034cff62a6edb2bd8
3
  size 1551478091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd807cd6d5226dc57760c3eb773655ceee8cf46f2e27dadacc31cbcf814fd8cf
3
  size 1551478091
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45b7666e8a6f09360daf8a47228bb57f19d338bbc0f88e8d91aa3858a27c844d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5ee8ed6de8ebff1f4e53f6af005a75173401b22aced8e149a6ca7d20e5d75d
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00b4eb0c27b559cfd649f7c80a6d3394a55880d92b3ee2ca98f71b67e7b2333a
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:022915fa8ac65fae0f13853519b8aa7ee79efd632a399c1f64c6b87bab0b057a
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:151c5e22bfc2a771646595fb1b1d684f2565cfc37c097b2585cef37a029984c7
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97cf90b08eb246acaa107a6f5e6030cf607ba438f27aa86bb0197faea0282107
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 9000,
3
- "best_metric": 4.669365406036377,
4
- "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-9000",
5
- "epoch": 1.352812958021722,
6
  "eval_steps": 1000,
7
- "global_step": 9000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -296,42 +296,6 @@
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
  "logging_steps": 250,
@@ -360,7 +324,7 @@
360
  "attributes": {}
361
  }
362
  },
363
- "total_flos": 1.517862734247767e+17,
364
  "train_batch_size": 32,
365
  "trial_name": null,
366
  "trial_params": null
 
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
  "eval_samples_per_second": 72.134,
297
  "eval_steps_per_second": 1.128,
298
  "step": 8000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
299
  }
300
  ],
301
  "logging_steps": 250,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 1.349195872843607e+17,
328
  "train_batch_size": 32,
329
  "trial_name": null,
330
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d8537015b69c60e2c29af27ee6860531dfc4207cede0d753719b984b2c5e39a
3
  size 5201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e81ef68ecf6d54adfcba782e86ddd0804ab77ba8d53704fbef9e1dfb6174a6bf
3
  size 5201
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94866cc75aec33c09133a0fb4fa4dfd49fb0b254b4b6ede67f1805569573438d
3
  size 775678032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd7a22be120abec7cae4d835d4800211fd1c582dac90b575825986a3f3babf2b
3
  size 775678032