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
cb5f048
·
verified ·
1 Parent(s): fd6616b

Training in progress, step 7500, 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 sha256:816f94dc7b94d274001859bde263e04f4a896a53ade67e2995123aff402a7dba
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b42a979265f6b3694cea6a282674c0a71cf402963119b1d07d1aef35906c2b
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:910bf906db23867b28de9ff3400e9d96bd6229d7648305bd0e8f7eec43737b1d
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a84c2231165493973f21239dc562c1fd7e8a9ba34ca95a47de0ebf3630281e71
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a9f9a5b995960bd6f60a802e206be9213a2e7efe51466b4832018c81181c9d4
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:125e492008ff1ed8e235750bb8ed5ff41af9598934d5094b3c067f444f4b94a9
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be40a03f70bb2a35bb567114fb5ceb05ce1222c8df24b1e1100746c617c5be10
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642827d515e7c3d88d20c04224822701abbbc9250deb1d366045f974d08b8258
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b92a571b8baa5cd2064db834c0b66314226372027955024045490e8e27e64eb
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e63359fb448b9dcc7ef1822c884ff56f6d6dbe369428aec0592244db6c4b090
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 7000,
3
- "best_metric": 0.9632054054054054,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-7000",
5
- "epoch": 1.210671970941797,
6
  "eval_steps": 500,
7
- "global_step": 7000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -260,6 +260,24 @@
260
  "eval_steps_per_second": 3.449,
261
  "eval_weighted_f1": 0.9570982563798056,
262
  "step": 7000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
263
  }
264
  ],
265
  "logging_steps": 500,
@@ -279,7 +297,7 @@
279
  "attributes": {}
280
  }
281
  },
282
- "total_flos": 2.9471332779936384e+16,
283
  "train_batch_size": 128,
284
  "trial_name": null,
285
  "trial_params": null
 
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,
 
260
  "eval_steps_per_second": 3.449,
261
  "eval_weighted_f1": 0.9570982563798056,
262
  "step": 7000
263
+ },
264
+ {
265
+ "epoch": 1.297154717633832,
266
+ "grad_norm": 3.8189609050750732,
267
+ "learning_rate": 2.8384065490603024e-05,
268
+ "loss": 0.1208,
269
+ "step": 7500
270
+ },
271
+ {
272
+ "epoch": 1.297154717633832,
273
+ "eval_accuracy": 0.963927027027027,
274
+ "eval_loss": 0.13370193541049957,
275
+ "eval_macro_f1": 0.5746596478621987,
276
+ "eval_runtime": 418.7013,
277
+ "eval_samples_per_second": 883.685,
278
+ "eval_steps_per_second": 3.454,
279
+ "eval_weighted_f1": 0.9576970198616988,
280
+ "step": 7500
281
  }
282
  ],
283
  "logging_steps": 500,
 
297
  "attributes": {}
298
  }
299
  },
300
+ "total_flos": 3.1576655898528384e+16,
301
  "train_batch_size": 128,
302
  "trial_name": null,
303
  "trial_params": null