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
736fd7a
·
verified ·
1 Parent(s): 3a0ce4e

Training in progress, step 12500, 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 sha256:1480d9f4a630f6362b6c9b9468cf771d2a85b6a789312d734a4392acf6401523
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700bbbe8d2682ffa17c7c5ca3b69ade80a806017bca61fd1a7295a3fd61c1ce1
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2281b994c226e57b66b8d419588cdcb42cbd3535018df591d44d76344dea3b7
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f1f225a4056e0225f60466f5dafd5eebc5d474220af5ec449756f5b07b75b2
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:f3e8edef986f4bbf76f2de5f38080bedbaeda32f953eac6bedda8cf73cae1fd6
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606e55a840b88e7e35194e4c71ed6a1b24c298ca2694b6847c343ddacfcaacca
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae029a8e6af9f014c9ef8b713fcd28cef1f184648ddde977ce75efc89ca9a242
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec660d412b1d1fb9bca206aff549abab2519999210979dad75078f21bca5feb
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d447d717c68fd522f6372d2b3ebbc9666da3ac61bf609597ba0f72b0cdaf7a6
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b67bb6cece76a3f1907ad1a07c15a075bb6ae116b0ef419943601eefd565b0
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 12000,
3
- "best_metric": 0.9689324324324324,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-12000",
5
- "epoch": 2.0754129551154543,
6
  "eval_steps": 500,
7
- "global_step": 12000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -440,6 +440,24 @@
440
  "eval_steps_per_second": 3.449,
441
  "eval_weighted_f1": 0.9632448268921581,
442
  "step": 12000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
443
  }
444
  ],
445
  "logging_steps": 500,
@@ -459,7 +477,7 @@
459
  "attributes": {}
460
  }
461
  },
462
- "total_flos": 5.052137308550477e+16,
463
  "train_batch_size": 128,
464
  "trial_name": null,
465
  "trial_params": null
 
1
  {
2
+ "best_global_step": 12500,
3
+ "best_metric": 0.9692378378378378,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-12500",
5
+ "epoch": 2.1618957018074894,
6
  "eval_steps": 500,
7
+ "global_step": 12500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
440
  "eval_steps_per_second": 3.449,
441
  "eval_weighted_f1": 0.9632448268921581,
442
  "step": 12000
443
+ },
444
+ {
445
+ "epoch": 2.1618957018074894,
446
+ "grad_norm": 2.067152738571167,
447
+ "learning_rate": 1.3971520811714517e-05,
448
+ "loss": 0.0851,
449
+ "step": 12500
450
+ },
451
+ {
452
+ "epoch": 2.1618957018074894,
453
+ "eval_accuracy": 0.9692378378378378,
454
+ "eval_loss": 0.11705382913351059,
455
+ "eval_macro_f1": 0.5857631212432319,
456
+ "eval_runtime": 419.6262,
457
+ "eval_samples_per_second": 881.737,
458
+ "eval_steps_per_second": 3.446,
459
+ "eval_weighted_f1": 0.9632093509253533,
460
+ "step": 12500
461
  }
462
  ],
463
  "logging_steps": 500,
 
477
  "attributes": {}
478
  }
479
  },
480
+ "total_flos": 5.262669620409677e+16,
481
  "train_batch_size": 128,
482
  "trial_name": null,
483
  "trial_params": null