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
45b3a47
·
verified ·
1 Parent(s): 64639db

Training in progress, step 3000, 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 sha256:43aa2f7b6fd4cd88e09989bcafeaf2d9fc9b1b32cba4ebafaa9fcd8b6031b2a8
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd2e265c793d5d97135c35fda96708ac8d0a12e4428a42ac61b29a23301ad916
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3660b5c419b045a3c9b9c05d65cec8e85dfe06f001d13f70be41e2e0eec32ea
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f7fef778553d645b4eb1349e7d8eb755f0341568762587b35f7728c68f27f4
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:fd15b5cee9fa85066017a2a27480699f51fd3ab7ff41b7dc00da9c5468231fc0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8ba250a1ab8923f95945e479ace2a792132acdf18e15ed69045fbbe37db523
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:861ce13e6ca091acee9a68ebfc5ca38479baf4b537c37b3949f071f77b81e9f0
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dd7ac36cf214dcb59edbbd2c30318c75c25f5cb8880daeaf1168686f9108e2a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:103bd8c7f892070840bf85274593feba516ca2e00f4f3e47c97c1b892fc9bcc0
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 2500,
3
- "best_metric": 0.9421918918918919,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-2500",
5
- "epoch": 0.4324137334601747,
6
  "eval_steps": 500,
7
- "global_step": 2500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -98,6 +98,24 @@
98
  "eval_steps_per_second": 3.451,
99
  "eval_weighted_f1": 0.9356836777939385,
100
  "step": 2500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
101
  }
102
  ],
103
  "logging_steps": 500,
@@ -117,7 +135,7 @@
117
  "attributes": {}
118
  }
119
  },
120
- "total_flos": 1.052661559296e+16,
121
  "train_batch_size": 128,
122
  "trial_name": null,
123
  "trial_params": null
 
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,
 
98
  "eval_steps_per_second": 3.451,
99
  "eval_weighted_f1": 0.9356836777939385,
100
  "step": 2500
101
+ },
102
+ {
103
+ "epoch": 0.5188964801522097,
104
+ "grad_norm": 7.528863906860352,
105
+ "learning_rate": 4.135535570160268e-05,
106
+ "loss": 0.2168,
107
+ "step": 3000
108
+ },
109
+ {
110
+ "epoch": 0.5188964801522097,
111
+ "eval_accuracy": 0.947972972972973,
112
+ "eval_loss": 0.1820368617773056,
113
+ "eval_macro_f1": 0.5299222018041627,
114
+ "eval_runtime": 418.5666,
115
+ "eval_samples_per_second": 883.969,
116
+ "eval_steps_per_second": 3.455,
117
+ "eval_weighted_f1": 0.9417715175152749,
118
+ "step": 3000
119
  }
120
  ],
121
  "logging_steps": 500,
 
135
  "attributes": {}
136
  }
137
  },
138
+ "total_flos": 1.2631938711552e+16,
139
  "train_batch_size": 128,
140
  "trial_name": null,
141
  "trial_params": null