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
9146faf
·
verified ·
1 Parent(s): 7295f5e

Training in progress, step 8000, 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:f8b42a979265f6b3694cea6a282674c0a71cf402963119b1d07d1aef35906c2b
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1729ade4a3b27dcd5054a3dbd9159e2fdd261f96af28691317d91e1b969f919b
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a84c2231165493973f21239dc562c1fd7e8a9ba34ca95a47de0ebf3630281e71
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b91c4aa51808a21774863a308dfe5a96613a0cc00e12b509773113228d3c154
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:125e492008ff1ed8e235750bb8ed5ff41af9598934d5094b3c067f444f4b94a9
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dab905411ef3135d4cd3876442f0ded4fb6f75e082af92eeebd93053a6153f2
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:642827d515e7c3d88d20c04224822701abbbc9250deb1d366045f974d08b8258
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 sha256:7e63359fb448b9dcc7ef1822c884ff56f6d6dbe369428aec0592244db6c4b090
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fcfd5ff5ecd302e9792a65b2975f4ea0f2cce1094a1020251dbc681c29a4d57
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 7500,
3
- "best_metric": 0.963927027027027,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-7500",
5
- "epoch": 1.297154717633832,
6
  "eval_steps": 500,
7
- "global_step": 7500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -278,6 +278,24 @@
278
  "eval_steps_per_second": 3.454,
279
  "eval_weighted_f1": 0.9576970198616988,
280
  "step": 7500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
281
  }
282
  ],
283
  "logging_steps": 500,
@@ -297,7 +315,7 @@
297
  "attributes": {}
298
  }
299
  },
300
- "total_flos": 3.1576655898528384e+16,
301
  "train_batch_size": 128,
302
  "trial_name": null,
303
  "trial_params": null
 
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,
 
278
  "eval_steps_per_second": 3.454,
279
  "eval_weighted_f1": 0.9576970198616988,
280
  "step": 7500
281
+ },
282
+ {
283
+ "epoch": 1.3836374643258669,
284
+ "grad_norm": 4.8342461585998535,
285
+ "learning_rate": 2.694281102271417e-05,
286
+ "loss": 0.1188,
287
+ "step": 8000
288
+ },
289
+ {
290
+ "epoch": 1.3836374643258669,
291
+ "eval_accuracy": 0.964472972972973,
292
+ "eval_loss": 0.13066376745700836,
293
+ "eval_macro_f1": 0.5725448949887878,
294
+ "eval_runtime": 418.7971,
295
+ "eval_samples_per_second": 883.483,
296
+ "eval_steps_per_second": 3.453,
297
+ "eval_weighted_f1": 0.9581300625445718,
298
+ "step": 8000
299
  }
300
  ],
301
  "logging_steps": 500,
 
315
  "attributes": {}
316
  }
317
  },
318
+ "total_flos": 3.3681979017120384e+16,
319
  "train_batch_size": 128,
320
  "trial_name": null,
321
  "trial_params": null