jysh1023/tiny-bert-sst2-distilled_original

来源：🤗🏴‍☠️ 救援者：isilicontext-classificationapache-2.04M 参数1.6 GBsafetensors✓ 7 个校验和1,092 天前更新

tiny-bert-sst2-distilled_original

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the glue dataset. It achieves the following results on the evaluation set:

eval_loss: 1.8486
eval_accuracy: 0.7936
eval_runtime: 2.677
eval_samples_per_second: 325.739
eval_steps_per_second: 2.615
epoch: 1.0
step: 527

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.00023791117612513647
train_batch_size: 128
eval_batch_size: 128
seed: 33
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2
mixed_precision_training: Native AMP

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

加载中…

评论分享想法，塑造主权 AI 的未来。

@jysh1023 尚未认领使用同名 Hugging Face 账户或组织成员账户登录，以验证此用户名。认领 @jysh1023

文件与来源

来源可在 🤗 获取

校验和7 个待记录

种子已收录磁力链接

节点群报告 4 个做种者

来源修订版本: b68aecff0ebc…
记录时间: 尚未记录
节点群检查时间: 2026年11月14日 01:01 UTC
权重文件: 7
模型大小: 1.6 GB
下载量 · 上个月: 13
发布者: 未认领

公开校验和记录将在下次同步时生成

权重

原版

F321.5 GB
147 个文件
run-0/checkpoint-1054/optimizer.pt 35 MBrun-0/checkpoint-2635/optimizer.pt 35 MBrun-0/checkpoint-3162/optimizer.pt 35 MBrun-0/checkpoint-527/optimizer.pt 35 MBrun-1/checkpoint-1054/optimizer.pt 35 MBrun-1/checkpoint-2108/optimizer.pt 35 MBrun-1/checkpoint-4743/optimizer.pt 35 MBrun-1/checkpoint-527/optimizer.pt 35 MBrun-2/checkpoint-1054/optimizer.pt 35 MBrun-2/checkpoint-4216/optimizer.pt 35 MBrun-2/checkpoint-4743/optimizer.pt 35 MBrun-2/checkpoint-527/optimizer.pt 35 MBrun-3/checkpoint-1054/optimizer.pt 35 MBrun-3/checkpoint-2635/optimizer.pt 35 MBrun-3/checkpoint-527/optimizer.pt 35 MBrun-4/checkpoint-1054/optimizer.pt 35 MBrun-4/checkpoint-527/optimizer.pt 35 MBrun-5/checkpoint-1054/optimizer.pt 35 MBrun-5/checkpoint-1581/optimizer.pt 35 MBrun-5/checkpoint-4743/optimizer.pt 35 MBrun-5/checkpoint-527/optimizer.pt 35 MBrun-6/checkpoint-1054/optimizer.pt 35 MBrun-6/checkpoint-527/optimizer.pt 35 MBrun-7/checkpoint-1054/optimizer.pt 35 MBrun-7/checkpoint-527/optimizer.pt 35 MBrun-8/checkpoint-1054/optimizer.pt 35 MBrun-8/checkpoint-2635/optimizer.pt 35 MBrun-8/checkpoint-3689/optimizer.pt 35 MBrun-8/checkpoint-527/optimizer.pt 35 MBmodel.safetensors 18 MBrun-0/checkpoint-1054/model.safetensors 18 MBrun-0/checkpoint-2635/model.safetensors 18 MBrun-0/checkpoint-3162/model.safetensors 18 MBrun-0/checkpoint-527/model.safetensors 18 MBrun-1/checkpoint-1054/model.safetensors 18 MBrun-1/checkpoint-2108/model.safetensors 18 MBrun-1/checkpoint-4743/model.safetensors 18 MBrun-1/checkpoint-527/model.safetensors 18 MBrun-2/checkpoint-1054/model.safetensors 18 MBrun-2/checkpoint-4216/model.safetensors 18 MBrun-2/checkpoint-4743/model.safetensors 18 MBrun-2/checkpoint-527/model.safetensors 18 MBrun-3/checkpoint-1054/model.safetensors 18 MBrun-3/checkpoint-2635/model.safetensors 18 MBrun-3/checkpoint-527/model.safetensors 18 MBrun-4/checkpoint-1054/model.safetensors 18 MBrun-4/checkpoint-527/model.safetensors 18 MBrun-5/checkpoint-1054/model.safetensors 18 MBrun-5/checkpoint-1581/model.safetensors 18 MBrun-5/checkpoint-4743/model.safetensors 18 MBrun-5/checkpoint-527/model.safetensors 18 MBrun-6/checkpoint-1054/model.safetensors 18 MBrun-6/checkpoint-527/model.safetensors 18 MBrun-7/checkpoint-1054/model.safetensors 18 MBrun-7/checkpoint-527/model.safetensors 18 MBrun-8/checkpoint-1054/model.safetensors 18 MBrun-8/checkpoint-2635/model.safetensors 18 MBrun-8/checkpoint-3689/model.safetensors 18 MBrun-8/checkpoint-527/model.safetensors 18 MBrun-0/checkpoint-1054/rng_state.pth 14.3 kBrun-0/checkpoint-2635/rng_state.pth 14.3 kBrun-0/checkpoint-3162/rng_state.pth 14.3 kBrun-0/checkpoint-527/rng_state.pth 14.3 kBrun-1/checkpoint-1054/rng_state.pth 14.3 kBrun-1/checkpoint-2108/rng_state.pth 14.3 kBrun-1/checkpoint-4743/rng_state.pth 14.3 kBrun-1/checkpoint-527/rng_state.pth 14.3 kBrun-2/checkpoint-1054/rng_state.pth 14.3 kBrun-2/checkpoint-4216/rng_state.pth 14.3 kBrun-2/checkpoint-4743/rng_state.pth 14.3 kBrun-2/checkpoint-527/rng_state.pth 14.3 kBrun-3/checkpoint-1054/rng_state.pth 14.3 kBrun-3/checkpoint-2635/rng_state.pth 14.3 kBrun-3/checkpoint-527/rng_state.pth 14.3 kBrun-4/checkpoint-1054/rng_state.pth 14.3 kBrun-4/checkpoint-527/rng_state.pth 14.3 kBrun-5/checkpoint-1054/rng_state.pth 14.3 kBrun-5/checkpoint-1581/rng_state.pth 14.3 kBrun-5/checkpoint-4743/rng_state.pth 14.3 kBrun-5/checkpoint-527/rng_state.pth 14.3 kBrun-6/checkpoint-1054/rng_state.pth 14.3 kBrun-6/checkpoint-527/rng_state.pth 14.3 kBrun-7/checkpoint-1054/rng_state.pth 14.3 kBrun-7/checkpoint-527/rng_state.pth 14.3 kBrun-8/checkpoint-1054/rng_state.pth 14.3 kBrun-8/checkpoint-2635/rng_state.pth 14.3 kBrun-8/checkpoint-3689/rng_state.pth 14.3 kBrun-8/checkpoint-527/rng_state.pth 14.3 kBrun-0/checkpoint-1054/training_args.bin 4.7 kBrun-0/checkpoint-2635/training_args.bin 4.7 kBrun-0/checkpoint-3162/training_args.bin 4.7 kBrun-0/checkpoint-527/training_args.bin 4.7 kBrun-1/checkpoint-1054/training_args.bin 4.7 kBrun-1/checkpoint-2108/training_args.bin 4.7 kBrun-1/checkpoint-4743/training_args.bin 4.7 kBrun-1/checkpoint-527/training_args.bin 4.7 kBrun-2/checkpoint-1054/training_args.bin 4.7 kBrun-2/checkpoint-4216/training_args.bin 4.7 kBrun-2/checkpoint-4743/training_args.bin 4.7 kBrun-2/checkpoint-527/training_args.bin 4.7 kBrun-3/checkpoint-1054/training_args.bin 4.7 kBrun-3/checkpoint-2635/training_args.bin 4.7 kBrun-3/checkpoint-527/training_args.bin 4.7 kBrun-4/checkpoint-1054/training_args.bin 4.7 kBrun-4/checkpoint-527/training_args.bin 4.7 kBrun-5/checkpoint-1054/training_args.bin 4.7 kBrun-5/checkpoint-1581/training_args.bin 4.7 kBrun-5/checkpoint-4743/training_args.bin 4.7 kBrun-5/checkpoint-527/training_args.bin 4.7 kBrun-6/checkpoint-1054/training_args.bin 4.7 kBrun-6/checkpoint-527/training_args.bin 4.7 kBrun-7/checkpoint-1054/training_args.bin 4.7 kBrun-7/checkpoint-527/training_args.bin 4.7 kBrun-8/checkpoint-1054/training_args.bin 4.7 kBrun-8/checkpoint-2635/training_args.bin 4.7 kBrun-8/checkpoint-3689/training_args.bin 4.7 kBrun-8/checkpoint-527/training_args.bin 4.7 kBtraining_args.bin 4.7 kBrun-0/checkpoint-1054/scheduler.pt 1.1 kBrun-0/checkpoint-2635/scheduler.pt 1.1 kBrun-0/checkpoint-3162/scheduler.pt 1.1 kBrun-0/checkpoint-527/scheduler.pt 1.1 kBrun-1/checkpoint-1054/scheduler.pt 1.1 kBrun-1/checkpoint-2108/scheduler.pt 1.1 kBrun-1/checkpoint-4743/scheduler.pt 1.1 kBrun-1/checkpoint-527/scheduler.pt 1.1 kBrun-2/checkpoint-1054/scheduler.pt 1.1 kBrun-2/checkpoint-4216/scheduler.pt 1.1 kBrun-2/checkpoint-4743/scheduler.pt 1.1 kBrun-2/checkpoint-527/scheduler.pt 1.1 kBrun-3/checkpoint-1054/scheduler.pt 1.1 kBrun-3/checkpoint-2635/scheduler.pt 1.1 kBrun-3/checkpoint-527/scheduler.pt 1.1 kBrun-4/checkpoint-1054/scheduler.pt 1.1 kBrun-4/checkpoint-527/scheduler.pt 1.1 kBrun-5/checkpoint-1054/scheduler.pt 1.1 kBrun-5/checkpoint-1581/scheduler.pt 1.1 kBrun-5/checkpoint-4743/scheduler.pt 1.1 kBrun-5/checkpoint-527/scheduler.pt 1.1 kBrun-6/checkpoint-1054/scheduler.pt 1.1 kBrun-6/checkpoint-527/scheduler.pt 1.1 kBrun-7/checkpoint-1054/scheduler.pt 1.1 kBrun-7/checkpoint-527/scheduler.pt 1.1 kBrun-8/checkpoint-1054/scheduler.pt 1.1 kBrun-8/checkpoint-2635/scheduler.pt 1.1 kBrun-8/checkpoint-3689/scheduler.pt 1.1 kBrun-8/checkpoint-527/scheduler.pt 1.1 kB

模型家族

↑ 微调自 google/bert_uncased_L-2_H-128_A-2

权重

原版

F321.5 GB
147 个文件
run-0/checkpoint-1054/optimizer.pt 35 MBrun-0/checkpoint-2635/optimizer.pt 35 MBrun-0/checkpoint-3162/optimizer.pt 35 MBrun-0/checkpoint-527/optimizer.pt 35 MBrun-1/checkpoint-1054/optimizer.pt 35 MBrun-1/checkpoint-2108/optimizer.pt 35 MBrun-1/checkpoint-4743/optimizer.pt 35 MBrun-1/checkpoint-527/optimizer.pt 35 MBrun-2/checkpoint-1054/optimizer.pt 35 MBrun-2/checkpoint-4216/optimizer.pt 35 MBrun-2/checkpoint-4743/optimizer.pt 35 MBrun-2/checkpoint-527/optimizer.pt 35 MBrun-3/checkpoint-1054/optimizer.pt 35 MBrun-3/checkpoint-2635/optimizer.pt 35 MBrun-3/checkpoint-527/optimizer.pt 35 MBrun-4/checkpoint-1054/optimizer.pt 35 MBrun-4/checkpoint-527/optimizer.pt 35 MBrun-5/checkpoint-1054/optimizer.pt 35 MBrun-5/checkpoint-1581/optimizer.pt 35 MBrun-5/checkpoint-4743/optimizer.pt 35 MBrun-5/checkpoint-527/optimizer.pt 35 MBrun-6/checkpoint-1054/optimizer.pt 35 MBrun-6/checkpoint-527/optimizer.pt 35 MBrun-7/checkpoint-1054/optimizer.pt 35 MBrun-7/checkpoint-527/optimizer.pt 35 MBrun-8/checkpoint-1054/optimizer.pt 35 MBrun-8/checkpoint-2635/optimizer.pt 35 MBrun-8/checkpoint-3689/optimizer.pt 35 MBrun-8/checkpoint-527/optimizer.pt 35 MBmodel.safetensors 18 MBrun-0/checkpoint-1054/model.safetensors 18 MBrun-0/checkpoint-2635/model.safetensors 18 MBrun-0/checkpoint-3162/model.safetensors 18 MBrun-0/checkpoint-527/model.safetensors 18 MBrun-1/checkpoint-1054/model.safetensors 18 MBrun-1/checkpoint-2108/model.safetensors 18 MBrun-1/checkpoint-4743/model.safetensors 18 MBrun-1/checkpoint-527/model.safetensors 18 MBrun-2/checkpoint-1054/model.safetensors 18 MBrun-2/checkpoint-4216/model.safetensors 18 MBrun-2/checkpoint-4743/model.safetensors 18 MBrun-2/checkpoint-527/model.safetensors 18 MBrun-3/checkpoint-1054/model.safetensors 18 MBrun-3/checkpoint-2635/model.safetensors 18 MBrun-3/checkpoint-527/model.safetensors 18 MBrun-4/checkpoint-1054/model.safetensors 18 MBrun-4/checkpoint-527/model.safetensors 18 MBrun-5/checkpoint-1054/model.safetensors 18 MBrun-5/checkpoint-1581/model.safetensors 18 MBrun-5/checkpoint-4743/model.safetensors 18 MBrun-5/checkpoint-527/model.safetensors 18 MBrun-6/checkpoint-1054/model.safetensors 18 MBrun-6/checkpoint-527/model.safetensors 18 MBrun-7/checkpoint-1054/model.safetensors 18 MBrun-7/checkpoint-527/model.safetensors 18 MBrun-8/checkpoint-1054/model.safetensors 18 MBrun-8/checkpoint-2635/model.safetensors 18 MBrun-8/checkpoint-3689/model.safetensors 18 MBrun-8/checkpoint-527/model.safetensors 18 MBrun-0/checkpoint-1054/rng_state.pth 14.3 kBrun-0/checkpoint-2635/rng_state.pth 14.3 kBrun-0/checkpoint-3162/rng_state.pth 14.3 kBrun-0/checkpoint-527/rng_state.pth 14.3 kBrun-1/checkpoint-1054/rng_state.pth 14.3 kBrun-1/checkpoint-2108/rng_state.pth 14.3 kBrun-1/checkpoint-4743/rng_state.pth 14.3 kBrun-1/checkpoint-527/rng_state.pth 14.3 kBrun-2/checkpoint-1054/rng_state.pth 14.3 kBrun-2/checkpoint-4216/rng_state.pth 14.3 kBrun-2/checkpoint-4743/rng_state.pth 14.3 kBrun-2/checkpoint-527/rng_state.pth 14.3 kBrun-3/checkpoint-1054/rng_state.pth 14.3 kBrun-3/checkpoint-2635/rng_state.pth 14.3 kBrun-3/checkpoint-527/rng_state.pth 14.3 kBrun-4/checkpoint-1054/rng_state.pth 14.3 kBrun-4/checkpoint-527/rng_state.pth 14.3 kBrun-5/checkpoint-1054/rng_state.pth 14.3 kBrun-5/checkpoint-1581/rng_state.pth 14.3 kBrun-5/checkpoint-4743/rng_state.pth 14.3 kBrun-5/checkpoint-527/rng_state.pth 14.3 kBrun-6/checkpoint-1054/rng_state.pth 14.3 kBrun-6/checkpoint-527/rng_state.pth 14.3 kBrun-7/checkpoint-1054/rng_state.pth 14.3 kBrun-7/checkpoint-527/rng_state.pth 14.3 kBrun-8/checkpoint-1054/rng_state.pth 14.3 kBrun-8/checkpoint-2635/rng_state.pth 14.3 kBrun-8/checkpoint-3689/rng_state.pth 14.3 kBrun-8/checkpoint-527/rng_state.pth 14.3 kBrun-0/checkpoint-1054/training_args.bin 4.7 kBrun-0/checkpoint-2635/training_args.bin 4.7 kBrun-0/checkpoint-3162/training_args.bin 4.7 kBrun-0/checkpoint-527/training_args.bin 4.7 kBrun-1/checkpoint-1054/training_args.bin 4.7 kBrun-1/checkpoint-2108/training_args.bin 4.7 kBrun-1/checkpoint-4743/training_args.bin 4.7 kBrun-1/checkpoint-527/training_args.bin 4.7 kBrun-2/checkpoint-1054/training_args.bin 4.7 kBrun-2/checkpoint-4216/training_args.bin 4.7 kBrun-2/checkpoint-4743/training_args.bin 4.7 kBrun-2/checkpoint-527/training_args.bin 4.7 kBrun-3/checkpoint-1054/training_args.bin 4.7 kBrun-3/checkpoint-2635/training_args.bin 4.7 kBrun-3/checkpoint-527/training_args.bin 4.7 kBrun-4/checkpoint-1054/training_args.bin 4.7 kBrun-4/checkpoint-527/training_args.bin 4.7 kBrun-5/checkpoint-1054/training_args.bin 4.7 kBrun-5/checkpoint-1581/training_args.bin 4.7 kBrun-5/checkpoint-4743/training_args.bin 4.7 kBrun-5/checkpoint-527/training_args.bin 4.7 kBrun-6/checkpoint-1054/training_args.bin 4.7 kBrun-6/checkpoint-527/training_args.bin 4.7 kBrun-7/checkpoint-1054/training_args.bin 4.7 kBrun-7/checkpoint-527/training_args.bin 4.7 kBrun-8/checkpoint-1054/training_args.bin 4.7 kBrun-8/checkpoint-2635/training_args.bin 4.7 kBrun-8/checkpoint-3689/training_args.bin 4.7 kBrun-8/checkpoint-527/training_args.bin 4.7 kBtraining_args.bin 4.7 kBrun-0/checkpoint-1054/scheduler.pt 1.1 kBrun-0/checkpoint-2635/scheduler.pt 1.1 kBrun-0/checkpoint-3162/scheduler.pt 1.1 kBrun-0/checkpoint-527/scheduler.pt 1.1 kBrun-1/checkpoint-1054/scheduler.pt 1.1 kBrun-1/checkpoint-2108/scheduler.pt 1.1 kBrun-1/checkpoint-4743/scheduler.pt 1.1 kBrun-1/checkpoint-527/scheduler.pt 1.1 kBrun-2/checkpoint-1054/scheduler.pt 1.1 kBrun-2/checkpoint-4216/scheduler.pt 1.1 kBrun-2/checkpoint-4743/scheduler.pt 1.1 kBrun-2/checkpoint-527/scheduler.pt 1.1 kBrun-3/checkpoint-1054/scheduler.pt 1.1 kBrun-3/checkpoint-2635/scheduler.pt 1.1 kBrun-3/checkpoint-527/scheduler.pt 1.1 kBrun-4/checkpoint-1054/scheduler.pt 1.1 kBrun-4/checkpoint-527/scheduler.pt 1.1 kBrun-5/checkpoint-1054/scheduler.pt 1.1 kBrun-5/checkpoint-1581/scheduler.pt 1.1 kBrun-5/checkpoint-4743/scheduler.pt 1.1 kBrun-5/checkpoint-527/scheduler.pt 1.1 kBrun-6/checkpoint-1054/scheduler.pt 1.1 kBrun-6/checkpoint-527/scheduler.pt 1.1 kBrun-7/checkpoint-1054/scheduler.pt 1.1 kBrun-7/checkpoint-527/scheduler.pt 1.1 kBrun-8/checkpoint-1054/scheduler.pt 1.1 kBrun-8/checkpoint-2635/scheduler.pt 1.1 kBrun-8/checkpoint-3689/scheduler.pt 1.1 kBrun-8/checkpoint-527/scheduler.pt 1.1 kB