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
fc2ef10
·
verified ·
1 Parent(s): 55b2b65

Training in progress, step 4000, 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 sha256:36acdec4693682eb88e951ead0c08aa7be70ad418cd9b1569781a1abd4dfc40d
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5b5677d9891aa45d89fc955cb9243c4c892a2a17a6073e436d3ef472af3c90
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32098f6d74ba0af75d2d05609e46614ccf82ec9ceab57a5bb3ebfd9e2e9aa47a
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0020a391ae538dd0d03ce6a8dc6d4f64e2b76592736b7fbcb7e2e3720d50be8
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36d50362465415ab3167a1ac50baf48c7d5198fdd653474083449b2996827fc0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5623710a9876a4527c86696e9da486d40af7f8bddb58e1bce4e588a31c362f74
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac1b9358ab1cb9acff90f4d1d692ac08bbdb1986a66544aed9f6fe9b801b17b3
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ad531672d19de892560bca92120faf6da41489b53fd48e49ce152724282fe6c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a240a74c36b0a3848e3b90a2aab92160a9fd1865c484f7158ef535a987fb39
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 3500,
3
- "best_metric": 0.9518621621621621,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-3500",
5
- "epoch": 0.6053792268442446,
6
  "eval_steps": 500,
7
- "global_step": 3500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -134,6 +134,24 @@
134
  "eval_steps_per_second": 3.454,
135
  "eval_weighted_f1": 0.9454971013709563,
136
  "step": 3500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
137
  }
138
  ],
139
  "logging_steps": 500,
@@ -153,7 +171,7 @@
153
  "attributes": {}
154
  }
155
  },
156
- "total_flos": 1.4737261830144e+16,
157
  "train_batch_size": 128,
158
  "trial_name": null,
159
  "trial_params": null
 
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,
 
134
  "eval_steps_per_second": 3.454,
135
  "eval_weighted_f1": 0.9454971013709563,
136
  "step": 3500
137
+ },
138
+ {
139
+ "epoch": 0.6918619735362795,
140
+ "grad_norm": 5.204596996307373,
141
+ "learning_rate": 3.847284676582498e-05,
142
+ "loss": 0.1782,
143
+ "step": 4000
144
+ },
145
+ {
146
+ "epoch": 0.6918619735362795,
147
+ "eval_accuracy": 0.9557081081081081,
148
+ "eval_loss": 0.15780550241470337,
149
+ "eval_macro_f1": 0.5498663380782979,
150
+ "eval_runtime": 418.4036,
151
+ "eval_samples_per_second": 884.314,
152
+ "eval_steps_per_second": 3.456,
153
+ "eval_weighted_f1": 0.9495774047836557,
154
+ "step": 4000
155
  }
156
  ],
157
  "logging_steps": 500,
 
171
  "attributes": {}
172
  }
173
  },
174
+ "total_flos": 1.6842584948736e+16,
175
  "train_batch_size": 128,
176
  "trial_name": null,
177
  "trial_params": null