Language中文

Theme

Slava/tiny-bert-sst2-distilled · Pirate Face

Weights

Original

F321.9 GB
177 files
run-0/checkpoint-1054/optimizer.pt 35 MBrun-0/checkpoint-1581/optimizer.pt 35 MBrun-0/checkpoint-2108/optimizer.pt 35 MBrun-0/checkpoint-527/optimizer.pt 35 MBrun-1/checkpoint-1054/optimizer.pt 35 MBrun-1/checkpoint-527/optimizer.pt 35 MBrun-11/checkpoint-1054/optimizer.pt 35 MBrun-11/checkpoint-3689/optimizer.pt 35 MBrun-11/checkpoint-527/optimizer.pt 35 MBrun-14/checkpoint-527/optimizer.pt 35 MBrun-16/checkpoint-1581/optimizer.pt 35 MBrun-16/checkpoint-527/optimizer.pt 35 MBrun-18/checkpoint-1054/optimizer.pt 35 MBrun-18/checkpoint-2108/optimizer.pt 35 MBrun-18/checkpoint-2635/optimizer.pt 35 MBrun-18/checkpoint-4743/optimizer.pt 35 MBrun-18/checkpoint-527/optimizer.pt 35 MBrun-19/checkpoint-1581/optimizer.pt 35 MBrun-19/checkpoint-3162/optimizer.pt 35 MBrun-19/checkpoint-527/optimizer.pt 35 MBrun-2/checkpoint-1054/optimizer.pt 35 MBrun-2/checkpoint-2108/optimizer.pt 35 MBrun-2/checkpoint-3689/optimizer.pt 35 MBrun-2/checkpoint-527/optimizer.pt 35 MBrun-20/checkpoint-1054/optimizer.pt 35 MBrun-20/checkpoint-2108/optimizer.pt 35 MBrun-20/checkpoint-527/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-3689/optimizer.pt 35 MBrun-4/checkpoint-4743/optimizer.pt 35 MBrun-4/checkpoint-527/optimizer.pt 35 MBrun-6/checkpoint-527/optimizer.pt 35 MBrun-7/checkpoint-527/optimizer.pt 35 MBmodel.safetensors 18 MBrun-0/checkpoint-1054/model.safetensors 18 MBrun-0/checkpoint-1581/model.safetensors 18 MBrun-0/checkpoint-2108/model.safetensors 18 MBrun-0/checkpoint-527/model.safetensors 18 MBrun-1/checkpoint-1054/model.safetensors 18 MBrun-1/checkpoint-527/model.safetensors 18 MBrun-11/checkpoint-1054/model.safetensors 18 MBrun-11/checkpoint-3689/model.safetensors 18 MBrun-11/checkpoint-527/model.safetensors 18 MBrun-14/checkpoint-527/model.safetensors 18 MBrun-16/checkpoint-1581/model.safetensors 18 MBrun-16/checkpoint-527/model.safetensors 18 MBrun-18/checkpoint-1054/model.safetensors 18 MBrun-18/checkpoint-2108/model.safetensors 18 MBrun-18/checkpoint-2635/model.safetensors 18 MBrun-18/checkpoint-4743/model.safetensors 18 MBrun-18/checkpoint-527/model.safetensors 18 MBrun-19/checkpoint-1581/model.safetensors 18 MBrun-19/checkpoint-3162/model.safetensors 18 MBrun-19/checkpoint-527/model.safetensors 18 MBrun-2/checkpoint-1054/model.safetensors 18 MBrun-2/checkpoint-2108/model.safetensors 18 MBrun-2/checkpoint-3689/model.safetensors 18 MBrun-2/checkpoint-527/model.safetensors 18 MBrun-20/checkpoint-1054/model.safetensors 18 MBrun-20/checkpoint-2108/model.safetensors 18 MBrun-20/checkpoint-527/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-3689/model.safetensors 18 MBrun-4/checkpoint-4743/model.safetensors 18 MBrun-4/checkpoint-527/model.safetensors 18 MBrun-6/checkpoint-527/model.safetensors 18 MBrun-7/checkpoint-527/model.safetensors 18 MBrun-0/checkpoint-1054/rng_state.pth 13.6 kBrun-0/checkpoint-1581/rng_state.pth 13.6 kBrun-0/checkpoint-2108/rng_state.pth 13.6 kBrun-0/checkpoint-527/rng_state.pth 13.6 kBrun-1/checkpoint-1054/rng_state.pth 13.6 kBrun-1/checkpoint-527/rng_state.pth 13.6 kBrun-11/checkpoint-1054/rng_state.pth 13.6 kBrun-11/checkpoint-3689/rng_state.pth 13.6 kBrun-11/checkpoint-527/rng_state.pth 13.6 kBrun-14/checkpoint-527/rng_state.pth 13.6 kBrun-16/checkpoint-1581/rng_state.pth 13.6 kBrun-16/checkpoint-527/rng_state.pth 13.6 kBrun-18/checkpoint-1054/rng_state.pth 13.6 kBrun-18/checkpoint-2108/rng_state.pth 13.6 kBrun-18/checkpoint-2635/rng_state.pth 13.6 kBrun-18/checkpoint-4743/rng_state.pth 13.6 kBrun-18/checkpoint-527/rng_state.pth 13.6 kBrun-19/checkpoint-1581/rng_state.pth 13.6 kBrun-19/checkpoint-3162/rng_state.pth 13.6 kBrun-19/checkpoint-527/rng_state.pth 13.6 kBrun-2/checkpoint-1054/rng_state.pth 13.6 kBrun-2/checkpoint-2108/rng_state.pth 13.6 kBrun-2/checkpoint-3689/rng_state.pth 13.6 kBrun-2/checkpoint-527/rng_state.pth 13.6 kBrun-20/checkpoint-1054/rng_state.pth 13.6 kBrun-20/checkpoint-2108/rng_state.pth 13.6 kBrun-20/checkpoint-527/rng_state.pth 13.6 kBrun-3/checkpoint-2635/rng_state.pth 13.6 kBrun-3/checkpoint-527/rng_state.pth 13.6 kBrun-4/checkpoint-1054/rng_state.pth 13.6 kBrun-4/checkpoint-3689/rng_state.pth 13.6 kBrun-4/checkpoint-4743/rng_state.pth 13.6 kBrun-4/checkpoint-527/rng_state.pth 13.6 kBrun-6/checkpoint-527/rng_state.pth 13.6 kBrun-7/checkpoint-527/rng_state.pth 13.6 kBrun-0/checkpoint-1054/training_args.bin 4.3 kBrun-0/checkpoint-1581/training_args.bin 4.3 kBrun-0/checkpoint-2108/training_args.bin 4.3 kBrun-0/checkpoint-527/training_args.bin 4.3 kBrun-1/checkpoint-1054/training_args.bin 4.3 kBrun-1/checkpoint-527/training_args.bin 4.3 kBrun-11/checkpoint-1054/training_args.bin 4.3 kBrun-11/checkpoint-3689/training_args.bin 4.3 kBrun-11/checkpoint-527/training_args.bin 4.3 kBrun-14/checkpoint-527/training_args.bin 4.3 kBrun-16/checkpoint-1581/training_args.bin 4.3 kBrun-16/checkpoint-527/training_args.bin 4.3 kBrun-18/checkpoint-1054/training_args.bin 4.3 kBrun-18/checkpoint-2108/training_args.bin 4.3 kBrun-18/checkpoint-2635/training_args.bin 4.3 kBrun-18/checkpoint-4743/training_args.bin 4.3 kBrun-18/checkpoint-527/training_args.bin 4.3 kBrun-19/checkpoint-1581/training_args.bin 4.3 kBrun-19/checkpoint-3162/training_args.bin 4.3 kBrun-19/checkpoint-527/training_args.bin 4.3 kBrun-2/checkpoint-1054/training_args.bin 4.3 kBrun-2/checkpoint-2108/training_args.bin 4.3 kBrun-2/checkpoint-3689/training_args.bin 4.3 kBrun-2/checkpoint-527/training_args.bin 4.3 kBrun-20/checkpoint-1054/training_args.bin 4.3 kBrun-20/checkpoint-2108/training_args.bin 4.3 kBrun-20/checkpoint-527/training_args.bin 4.3 kBrun-3/checkpoint-2635/training_args.bin 4.3 kBrun-3/checkpoint-527/training_args.bin 4.3 kBrun-4/checkpoint-1054/training_args.bin 4.3 kBrun-4/checkpoint-3689/training_args.bin 4.3 kBrun-4/checkpoint-4743/training_args.bin 4.3 kBrun-4/checkpoint-527/training_args.bin 4.3 kBrun-6/checkpoint-527/training_args.bin 4.3 kBrun-7/checkpoint-527/training_args.bin 4.3 kBtraining_args.bin 4.3 kBrun-0/checkpoint-1054/scheduler.pt 0.6 kBrun-0/checkpoint-1581/scheduler.pt 0.6 kBrun-0/checkpoint-2108/scheduler.pt 0.6 kBrun-0/checkpoint-527/scheduler.pt 0.6 kBrun-1/checkpoint-1054/scheduler.pt 0.6 kBrun-1/checkpoint-527/scheduler.pt 0.6 kBrun-11/checkpoint-1054/scheduler.pt 0.6 kBrun-11/checkpoint-3689/scheduler.pt 0.6 kBrun-11/checkpoint-527/scheduler.pt 0.6 kBrun-14/checkpoint-527/scheduler.pt 0.6 kBrun-16/checkpoint-1581/scheduler.pt 0.6 kBrun-16/checkpoint-527/scheduler.pt 0.6 kBrun-18/checkpoint-1054/scheduler.pt 0.6 kBrun-18/checkpoint-2108/scheduler.pt 0.6 kBrun-18/checkpoint-2635/scheduler.pt 0.6 kBrun-18/checkpoint-4743/scheduler.pt 0.6 kBrun-18/checkpoint-527/scheduler.pt 0.6 kBrun-19/checkpoint-1581/scheduler.pt 0.6 kBrun-19/checkpoint-3162/scheduler.pt 0.6 kBrun-19/checkpoint-527/scheduler.pt 0.6 kBrun-2/checkpoint-1054/scheduler.pt 0.6 kBrun-2/checkpoint-2108/scheduler.pt 0.6 kBrun-2/checkpoint-3689/scheduler.pt 0.6 kBrun-2/checkpoint-527/scheduler.pt 0.6 kBrun-20/checkpoint-1054/scheduler.pt 0.6 kBrun-20/checkpoint-2108/scheduler.pt 0.6 kBrun-20/checkpoint-527/scheduler.pt 0.6 kBrun-3/checkpoint-2635/scheduler.pt 0.6 kBrun-3/checkpoint-527/scheduler.pt 0.6 kBrun-4/checkpoint-1054/scheduler.pt 0.6 kBrun-4/checkpoint-3689/scheduler.pt 0.6 kBrun-4/checkpoint-4743/scheduler.pt 0.6 kBrun-4/checkpoint-527/scheduler.pt 0.6 kBrun-6/checkpoint-527/scheduler.pt 0.6 kBrun-7/checkpoint-527/scheduler.pt 0.6 kB

tiny-bert-sst2-distilled

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

Loss: 1.9648
Accuracy: 0.8245

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: 0.0002628217875157273
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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.5717	1.0	527	2.0086	0.8073
1.2017	2.0	1054	1.8121	0.8222
0.9081	3.0	1581	1.8837	0.8177
0.7559	4.0	2108	1.9089	0.8234
0.6694	5.0	2635	1.9749	0.8177
0.6147	6.0	3162	1.9445	0.8257
0.5729	7.0	3689	1.9648	0.8245

Framework versions

Transformers 4.37.1
Pytorch 2.0.1
Datasets 2.16.1
Tokenizers 0.15.1