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
bc285f6
·
verified ·
1 Parent(s): 686231a

Training in progress, step 10000, 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 sha256:181b12e25a68f3ff531be3c38c08908d3de3767f51dd9b71ab7236af100114b0
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5e960bcff8746f23fc19600b6597d922c0cc5bb8528a771702e142fca65a65
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6947cb57ef98d2f5a6f25e4c4436ab45e5fbfe8032684285d1d11079742712e1
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef9bdb5e6ca8f10989a76b04250dbc689a634440541d8823c3678e1d97840f6
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14a83d1ca69590c446ff24d17236c152b37e20876b2e60a40575af0a565b5bbb
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7aa0c90399e731c02702c694141aa5d8d82b8c3e659a7592e6e1091f41c110f
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44c509bd3e5fac674b9ba176cbf7752fe31874a5d86b221fb4760c1dc243899a
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 sha256:729dc858ba5180ba4b30a770b18a43487caa76db2369fd0722b26be3ba9a3c3e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5000207fc90f6084755ff97bec8888cb831495da15b51f0644c591ff34cc87
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 9500,
3
- "best_metric": 0.9661621621621621,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-9500",
5
- "epoch": 1.6430857044019718,
6
  "eval_steps": 500,
7
- "global_step": 9500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -350,6 +350,24 @@
350
  "eval_steps_per_second": 3.451,
351
  "eval_weighted_f1": 0.9600300931445321,
352
  "step": 9500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
353
  }
354
  ],
355
  "logging_steps": 500,
@@ -369,7 +387,7 @@
369
  "attributes": {}
370
  }
371
  },
372
- "total_flos": 3.999794837289638e+16,
373
  "train_batch_size": 128,
374
  "trial_name": null,
375
  "trial_params": null
 
1
  {
2
+ "best_global_step": 10000,
3
+ "best_metric": 0.9670945945945946,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-10000",
5
+ "epoch": 1.7295684510940066,
6
  "eval_steps": 500,
7
+ "global_step": 10000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
350
  "eval_steps_per_second": 3.451,
351
  "eval_weighted_f1": 0.9600300931445321,
352
  "step": 9500
353
+ },
354
+ {
355
+ "epoch": 1.7295684510940066,
356
+ "grad_norm": 2.918519973754883,
357
+ "learning_rate": 2.117779315115877e-05,
358
+ "loss": 0.1133,
359
+ "step": 10000
360
+ },
361
+ {
362
+ "epoch": 1.7295684510940066,
363
+ "eval_accuracy": 0.9670945945945946,
364
+ "eval_loss": 0.12201372534036636,
365
+ "eval_macro_f1": 0.5803247802424795,
366
+ "eval_runtime": 418.9179,
367
+ "eval_samples_per_second": 883.228,
368
+ "eval_steps_per_second": 3.452,
369
+ "eval_weighted_f1": 0.9608891715468071,
370
+ "step": 10000
371
  }
372
  ],
373
  "logging_steps": 500,
 
387
  "attributes": {}
388
  }
389
  },
390
+ "total_flos": 4.210327149148838e+16,
391
  "train_batch_size": 128,
392
  "trial_name": null,
393
  "trial_params": null