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
82e0c97
·
verified ·
1 Parent(s): 732509b

Training in progress, step 1500, 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:c3d45943f1fb69425779b3a5e92c015cab639e5b856f858eb4c692e6b5016add
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647fed4e04ad26ebb3c784d1a356a784a9637958334db3eb5d0316be84f6d5e8
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62fab10da5336115608576a8c401e758b6abcdb54e32af763173f335ed96fc8f
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:757e6258c732d8be296ea401a064e7d047e5fe243b906b0fe02527d2b65887e0
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:080c1850d2033951b5683c6c7ec3bd66f5fcefe03d61fee224ef4ae6ad3f7f85
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce76db4209fed0144afb633123692a9504a05f46b5db395d330022dd387107c
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca372268f4fa9335030c0cb7aedb6cdba75f457da50e7a4034abb1a2d0843689
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c5e8f1a0db66947ed8e10cf85c39e1340e677a1cf02a1eff444d7b852d484f4
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d83883040b01510c2a7a674131a901f107e1b441c0ea6574a16489cefbc3e2d
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 1000,
3
- "best_metric": 0.8766405405405405,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-1000",
5
- "epoch": 0.17296549338406988,
6
  "eval_steps": 500,
7
- "global_step": 1000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -44,6 +44,24 @@
44
  "eval_steps_per_second": 3.458,
45
  "eval_weighted_f1": 0.8676584583901654,
46
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 500,
@@ -63,7 +81,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 4210646237184000.0,
67
  "train_batch_size": 128,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
+ "best_global_step": 1500,
3
+ "best_metric": 0.9137351351351352,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-1500",
5
+ "epoch": 0.25944824007610484,
6
  "eval_steps": 500,
7
+ "global_step": 1500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
44
  "eval_steps_per_second": 3.458,
45
  "eval_weighted_f1": 0.8676584583901654,
46
  "step": 1000
47
+ },
48
+ {
49
+ "epoch": 0.25944824007610484,
50
+ "grad_norm": 6.3231658935546875,
51
+ "learning_rate": 4.567911910526923e-05,
52
+ "loss": 0.3789,
53
+ "step": 1500
54
+ },
55
+ {
56
+ "epoch": 0.25944824007610484,
57
+ "eval_accuracy": 0.9137351351351352,
58
+ "eval_loss": 0.2946445643901825,
59
+ "eval_macro_f1": 0.47816321808462303,
60
+ "eval_runtime": 418.8729,
61
+ "eval_samples_per_second": 883.323,
62
+ "eval_steps_per_second": 3.452,
63
+ "eval_weighted_f1": 0.9066607985127312,
64
+ "step": 1500
65
  }
66
  ],
67
  "logging_steps": 500,
 
81
  "attributes": {}
82
  }
83
  },
84
+ "total_flos": 6315969355776000.0,
85
  "train_batch_size": 128,
86
  "trial_name": null,
87
  "trial_params": null