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
f073048
·
verified ·
1 Parent(s): 0d051d0

Training in progress, step 4500, 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 sha256:1c5b5677d9891aa45d89fc955cb9243c4c892a2a17a6073e436d3ef472af3c90
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759c7c3dc8b8a977f96c54dc6091e6b8d76952d45a68af63bfd9cc20855a2cc8
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0020a391ae538dd0d03ce6a8dc6d4f64e2b76592736b7fbcb7e2e3720d50be8
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96dfc714953d1a8ff52a7a455f377370390dc1a138c1e24bdce92adaea47d2e
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5623710a9876a4527c86696e9da486d40af7f8bddb58e1bce4e588a31c362f74
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbe3959441c1e1942eefadc50f29de4fc080c3ca8c311c2ebeeda1537571efdc
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b62db0ba9861d9ab63380744e79a287faa461a1bf55700140a411fe1e976f1cd
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4a240a74c36b0a3848e3b90a2aab92160a9fd1865c484f7158ef535a987fb39
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414e55f58b5266553da3c3fe877f96c896218d59ea6b776dd34481a4e5d7964e
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 4000,
3
- "best_metric": 0.9557081081081081,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-4000",
5
- "epoch": 0.6918619735362795,
6
  "eval_steps": 500,
7
- "global_step": 4000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -152,6 +152,24 @@
152
  "eval_steps_per_second": 3.456,
153
  "eval_weighted_f1": 0.9495774047836557,
154
  "step": 4000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
155
  }
156
  ],
157
  "logging_steps": 500,
@@ -171,7 +189,7 @@
171
  "attributes": {}
172
  }
173
  },
174
- "total_flos": 1.6842584948736e+16,
175
  "train_batch_size": 128,
176
  "trial_name": null,
177
  "trial_params": null
 
1
  {
2
+ "best_global_step": 4500,
3
+ "best_metric": 0.9571459459459459,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-4500",
5
+ "epoch": 0.7783447202283145,
6
  "eval_steps": 500,
7
+ "global_step": 4500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
152
  "eval_steps_per_second": 3.456,
153
  "eval_weighted_f1": 0.9495774047836557,
154
  "step": 4000
155
+ },
156
+ {
157
+ "epoch": 0.7783447202283145,
158
+ "grad_norm": 2.9452965259552,
159
+ "learning_rate": 3.7031592297936126e-05,
160
+ "loss": 0.1699,
161
+ "step": 4500
162
+ },
163
+ {
164
+ "epoch": 0.7783447202283145,
165
+ "eval_accuracy": 0.9571459459459459,
166
+ "eval_loss": 0.15344275534152985,
167
+ "eval_macro_f1": 0.5465995200000592,
168
+ "eval_runtime": 418.0876,
169
+ "eval_samples_per_second": 884.982,
170
+ "eval_steps_per_second": 3.459,
171
+ "eval_weighted_f1": 0.9507761247869798,
172
+ "step": 4500
173
  }
174
  ],
175
  "logging_steps": 500,
 
189
  "attributes": {}
190
  }
191
  },
192
+ "total_flos": 1.8947908067328e+16,
193
  "train_batch_size": 128,
194
  "trial_name": null,
195
  "trial_params": null