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
72ea6fd
·
verified ·
1 Parent(s): 0865405

Training in progress, step 3500, 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:fd2e265c793d5d97135c35fda96708ac8d0a12e4428a42ac61b29a23301ad916
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36acdec4693682eb88e951ead0c08aa7be70ad418cd9b1569781a1abd4dfc40d
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8f7fef778553d645b4eb1349e7d8eb755f0341568762587b35f7728c68f27f4
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32098f6d74ba0af75d2d05609e46614ccf82ec9ceab57a5bb3ebfd9e2e9aa47a
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e8ba250a1ab8923f95945e479ace2a792132acdf18e15ed69045fbbe37db523
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d50362465415ab3167a1ac50baf48c7d5198fdd653474083449b2996827fc0
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1b9358ab1cb9acff90f4d1d692ac08bbdb1986a66544aed9f6fe9b801b17b3
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:103bd8c7f892070840bf85274593feba516ca2e00f4f3e47c97c1b892fc9bcc0
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad531672d19de892560bca92120faf6da41489b53fd48e49ce152724282fe6c
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 3000,
3
- "best_metric": 0.947972972972973,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-3000",
5
- "epoch": 0.5188964801522097,
6
  "eval_steps": 500,
7
- "global_step": 3000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -116,6 +116,24 @@
116
  "eval_steps_per_second": 3.455,
117
  "eval_weighted_f1": 0.9417715175152749,
118
  "step": 3000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
119
  }
120
  ],
121
  "logging_steps": 500,
@@ -135,7 +153,7 @@
135
  "attributes": {}
136
  }
137
  },
138
- "total_flos": 1.2631938711552e+16,
139
  "train_batch_size": 128,
140
  "trial_name": null,
141
  "trial_params": null
 
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,
 
116
  "eval_steps_per_second": 3.455,
117
  "eval_weighted_f1": 0.9417715175152749,
118
  "step": 3000
119
+ },
120
+ {
121
+ "epoch": 0.6053792268442446,
122
+ "grad_norm": 3.640698194503784,
123
+ "learning_rate": 3.9914101233713826e-05,
124
+ "loss": 0.1955,
125
+ "step": 3500
126
+ },
127
+ {
128
+ "epoch": 0.6053792268442446,
129
+ "eval_accuracy": 0.9518621621621621,
130
+ "eval_loss": 0.17032282054424286,
131
+ "eval_macro_f1": 0.5375603114820035,
132
+ "eval_runtime": 418.6948,
133
+ "eval_samples_per_second": 883.699,
134
+ "eval_steps_per_second": 3.454,
135
+ "eval_weighted_f1": 0.9454971013709563,
136
+ "step": 3500
137
  }
138
  ],
139
  "logging_steps": 500,
 
153
  "attributes": {}
154
  }
155
  },
156
+ "total_flos": 1.4737261830144e+16,
157
  "train_batch_size": 128,
158
  "trial_name": null,
159
  "trial_params": null