twscrape-prepared-regression-e5-base-4k-3epochs

This model is a fine-tuned version of dwzhu/e5-base-4k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4350
• Mse: 0.0003
• Target 0 Mse: 0.0009
• Target 0 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f5b2a1ac610>
• Target 0 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f5c314b43a0>
• Target 1 Mse: 0.0003
• Target 1 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f5c3131fdf0>
• Target 1 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f5c180ffaf0>
• Target 2 Mse: 0.0001
• Target 2 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f5c1809f5e0>
• Target 2 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f5c3015e920>
• Target 3 Mse: 0.0000
• Target 3 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f5c312b04f0>
• Target 3 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f5c312b3340>

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 256
• total_eval_batch_size: 256
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Target 0 Mse	Target 0 Distributions	Target 0 Error Distribution	Target 1 Mse	Target 1 Distributions	Target 1 Error Distribution	Target 2 Mse	Target 2 Distributions	Target 2 Error Distribution	Target 3 Mse	Target 3 Distributions	Target 3 Error Distribution
1.4561	1.0	1589	1.4744	0.0003	0.0010	<wandb.sdk.data_types.image.Image object at 0x7f5c32c2e530>	<wandb.sdk.data_types.image.Image object at 0x7f5c32c2e620>	0.0003	<wandb.sdk.data_types.image.Image object at 0x7f5c4414f610>	<wandb.sdk.data_types.image.Image object at 0x7f5c473e3340>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f5c47230ac0>	<wandb.sdk.data_types.image.Image object at 0x7f5c4711f820>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f5c440fb250>	<wandb.sdk.data_types.image.Image object at 0x7f5c474deb60>
1.4648	2.0	3178	1.4401	0.0003	0.0009	<wandb.sdk.data_types.image.Image object at 0x7f5c47483f40>	<wandb.sdk.data_types.image.Image object at 0x7f5c442efa30>	0.0003	<wandb.sdk.data_types.image.Image object at 0x7f5c3639dfc0>	<wandb.sdk.data_types.image.Image object at 0x7f5c1839de40>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f5c1843d9c0>	<wandb.sdk.data_types.image.Image object at 0x7f5c182ce5f0>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f5c3627e980>	<wandb.sdk.data_types.image.Image object at 0x7f5c36151f00>
1.1685	3.0	4767	1.4350	0.0003	0.0009	<wandb.sdk.data_types.image.Image object at 0x7f5c32e8c2b0>	<wandb.sdk.data_types.image.Image object at 0x7f5c3610c1c0>	0.0003	<wandb.sdk.data_types.image.Image object at 0x7f5a8ea24640>	<wandb.sdk.data_types.image.Image object at 0x7f5c32defee0>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f5c315609a0>	<wandb.sdk.data_types.image.Image object at 0x7f5a8ea248b0>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f5b2a27d900>	<wandb.sdk.data_types.image.Image object at 0x7f5c316b6710>

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.0.1
• Tokenizers 0.21.0