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
51ccf19
·
verified ·
1 Parent(s): 378df40

Training in progress, step 6500, 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 sha256:12c470a17dbe8250eb3711663def054fcab3331f5be99c6d57850d196072ad91
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd8eb51586015b96114ad3bed48811e3850551bc992d6d49d45c89b103988465
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:611153bb3285a35559d860f0b889c64689ef347e95d437692cf8ad6e448d64d5
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d589184aeb5f2363d6ace789239adcdf45f4f20cc33c3a408f232bfc21d169bf
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:713e5f70ab7746d0848664abe6562e461cee0e4046be3c44eb3fe5523e67aedd
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8304aef9c8e25daa597b118c0cc771e2d04b30d8876daf7c6ea3f6587df11e04
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72ec040f7dbfafb8a0d9c346b901cc53a9760e25574232230ec90bf3c4a5f84d
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7534cacc10bd8d4b4219398d58514a47b600e17e3bb81aff93725ab2ed7b02a5
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:968db3e7ebf342cf531002d612ad1567d0cdb68cf93b976366564e3b71aa041c
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 5500,
3
- "best_metric": 0.9602459459459459,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-5500",
5
- "epoch": 1.0377064775577272,
6
  "eval_steps": 500,
7
- "global_step": 6000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -224,6 +224,24 @@
224
  "eval_steps_per_second": 3.442,
225
  "eval_weighted_f1": 0.9533441467822756,
226
  "step": 6000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
227
  }
228
  ],
229
  "logging_steps": 500,
@@ -243,7 +261,7 @@
243
  "attributes": {}
244
  }
245
  },
246
- "total_flos": 2.5260686542752384e+16,
247
  "train_batch_size": 128,
248
  "trial_name": null,
249
  "trial_params": null
 
1
  {
2
+ "best_global_step": 6500,
3
+ "best_metric": 0.9628189189189189,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-6500",
5
+ "epoch": 1.1241892242497622,
6
  "eval_steps": 500,
7
+ "global_step": 6500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
224
  "eval_steps_per_second": 3.442,
225
  "eval_weighted_f1": 0.9533441467822756,
226
  "step": 6000
227
+ },
228
+ {
229
+ "epoch": 1.1241892242497622,
230
+ "grad_norm": 3.167544364929199,
231
+ "learning_rate": 3.1266574426380724e-05,
232
+ "loss": 0.1251,
233
+ "step": 6500
234
+ },
235
+ {
236
+ "epoch": 1.1241892242497622,
237
+ "eval_accuracy": 0.9628189189189189,
238
+ "eval_loss": 0.13693760335445404,
239
+ "eval_macro_f1": 0.5800974551510764,
240
+ "eval_runtime": 420.0357,
241
+ "eval_samples_per_second": 880.877,
242
+ "eval_steps_per_second": 3.443,
243
+ "eval_weighted_f1": 0.9568010100001315,
244
+ "step": 6500
245
  }
246
  ],
247
  "logging_steps": 500,
 
261
  "attributes": {}
262
  }
263
  },
264
+ "total_flos": 2.7366009661344384e+16,
265
  "train_batch_size": 128,
266
  "trial_name": null,
267
  "trial_params": null