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
dc85e00
·
verified ·
1 Parent(s): 880aea1

Training in progress, step 6000, 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 +21 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c063be5646bdd548ecf3b4ab7f9c2b91e45c71b9c9604cc7739ae2ce57156601
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12c470a17dbe8250eb3711663def054fcab3331f5be99c6d57850d196072ad91
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc51b9293489ca30d6dbff10b4294572048e3eb175e5855b611474ffe8eaa441
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:611153bb3285a35559d860f0b889c64689ef347e95d437692cf8ad6e448d64d5
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b983edfe88b8213df49573de3b0a2e9dd491e6543bf5f5bd102232be36fc39e
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713e5f70ab7746d0848664abe6562e461cee0e4046be3c44eb3fe5523e67aedd
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bb8c4f79563cb7c9027a7d8be443142caa0e3f4a88491ec812af28bc90af134
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78c40077907b8f0920b0693d5918e0226f1b7b772e68b0f126acf47e6adc0ab9
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7534cacc10bd8d4b4219398d58514a47b600e17e3bb81aff93725ab2ed7b02a5
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 5500,
3
  "best_metric": 0.9602459459459459,
4
  "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-5500",
5
- "epoch": 0.9513102136123843,
6
  "eval_steps": 500,
7
- "global_step": 5500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -206,6 +206,24 @@
206
  "eval_steps_per_second": 3.451,
207
  "eval_weighted_f1": 0.9536733224654437,
208
  "step": 5500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
209
  }
210
  ],
211
  "logging_steps": 500,
@@ -225,7 +243,7 @@
225
  "attributes": {}
226
  }
227
  },
228
- "total_flos": 2.3158554304512e+16,
229
  "train_batch_size": 128,
230
  "trial_name": null,
231
  "trial_params": null
 
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,
 
206
  "eval_steps_per_second": 3.451,
207
  "eval_weighted_f1": 0.9536733224654437,
208
  "step": 5500
209
+ },
210
+ {
211
+ "epoch": 1.0377064775577272,
212
+ "grad_norm": 4.706158638000488,
213
+ "learning_rate": 3.270782889426958e-05,
214
+ "loss": 0.1422,
215
+ "step": 6000
216
+ },
217
+ {
218
+ "epoch": 1.0377064775577272,
219
+ "eval_accuracy": 0.9593081081081081,
220
+ "eval_loss": 0.1468845158815384,
221
+ "eval_macro_f1": 0.5689795604124087,
222
+ "eval_runtime": 420.1108,
223
+ "eval_samples_per_second": 880.72,
224
+ "eval_steps_per_second": 3.442,
225
+ "eval_weighted_f1": 0.9533441467822756,
226
+ "step": 6000
227
  }
228
  ],
229
  "logging_steps": 500,
 
243
  "attributes": {}
244
  }
245
  },
246
+ "total_flos": 2.5260686542752384e+16,
247
  "train_batch_size": 128,
248
  "trial_name": null,
249
  "trial_params": null