twscrape-prepared-regression-e5-base-4k-10epochs

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: 0.0003
• Mse: 0.0003
• Target 0 Mse: 0.0010
• Target 0 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f4db4835f90>
• Target 0 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f4d8f3550c0>
• Target 1 Mse: 0.0003
• Target 1 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f4db4c6c0d0>
• Target 1 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f4db498cfa0>
• Target 2 Mse: 0.0001
• Target 2 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f4db4cbc310>
• Target 2 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f4db4967400>
• Target 3 Mse: 0.0000
• Target 3 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f4d9411b490>
• Target 3 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f4da41b1ae0>

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: 2e-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: 10.0

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
0.0007	1.0	943	0.0005	0.0005	0.0013	<wandb.sdk.data_types.image.Image object at 0x7f4d94171540>	<wandb.sdk.data_types.image.Image object at 0x7f4d9415a230>	0.0005	<wandb.sdk.data_types.image.Image object at 0x7f4db49fd840>	<wandb.sdk.data_types.image.Image object at 0x7f4db4aee3b0>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f4d8f337340>	<wandb.sdk.data_types.image.Image object at 0x7f4db4d1b5b0>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f4d8f303310>	<wandb.sdk.data_types.image.Image object at 0x7f4db4c6e020>
0.0006	2.0	1886	0.0004	0.0004	0.0011	<wandb.sdk.data_types.image.Image object at 0x7f4d8f3360e0>	<wandb.sdk.data_types.image.Image object at 0x7f4db4c485b0>	0.0004	<wandb.sdk.data_types.image.Image object at 0x7f4d9b442590>	<wandb.sdk.data_types.image.Image object at 0x7f4d8c272c80>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f4db4bbfd90>	<wandb.sdk.data_types.image.Image object at 0x7f4d9b46fb80>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f4da417b160>	<wandb.sdk.data_types.image.Image object at 0x7f4d9b8f7790>
0.0004	3.0	2829	0.0003	0.0003	0.0010	<wandb.sdk.data_types.image.Image object at 0x7f4da41b1ff0>	<wandb.sdk.data_types.image.Image object at 0x7f4d9b87f160>	0.0003	<wandb.sdk.data_types.image.Image object at 0x7f4d9b717640>	<wandb.sdk.data_types.image.Image object at 0x7f4d9b7135b0>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f4d9b847550>	<wandb.sdk.data_types.image.Image object at 0x7f4d9b7a1c60>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f4d9b5a0940>	<wandb.sdk.data_types.image.Image object at 0x7f4d8c06e890>
0.0004	4.0	3772	0.0003	0.0003	0.0010	<wandb.sdk.data_types.image.Image object at 0x7f4d9b5a3c10>	<wandb.sdk.data_types.image.Image object at 0x7f4d7f7ec070>	0.0003	<wandb.sdk.data_types.image.Image object at 0x7f4d7f6640d0>	<wandb.sdk.data_types.image.Image object at 0x7f4cd43a6740>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f4d7c0a56c0>	<wandb.sdk.data_types.image.Image object at 0x7f4cd431af80>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f4d7f5cedd0>	<wandb.sdk.data_types.image.Image object at 0x7f4d7f5ce8c0>
0.0007	5.0	4715	0.0004	0.0004	0.0010	<wandb.sdk.data_types.image.Image object at 0x7f4cd4701930>	<wandb.sdk.data_types.image.Image object at 0x7f4d7f74ff70>	0.0004	<wandb.sdk.data_types.image.Image object at 0x7f4d8c06cdf0>	<wandb.sdk.data_types.image.Image object at 0x7f4d9b4e8dc0>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f4d7c1c66e0>	<wandb.sdk.data_types.image.Image object at 0x7f4d9b6fa170>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f4da41b1420>	<wandb.sdk.data_types.image.Image object at 0x7f4d9b565e70>
0.0003	6.0	5658	0.0003	0.0003	0.0009	<wandb.sdk.data_types.image.Image object at 0x7f4d9b710040>	<wandb.sdk.data_types.image.Image object at 0x7f4da4103e20>	0.0003	<wandb.sdk.data_types.image.Image object at 0x7f4db4c936a0>	<wandb.sdk.data_types.image.Image object at 0x7f4d8f3735b0>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f4d972ebee0>	<wandb.sdk.data_types.image.Image object at 0x7f4d8f294cd0>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f4d972ea200>	<wandb.sdk.data_types.image.Image object at 0x7f4d941599c0>
0.0003	7.0	6601	0.0003	0.0003	0.0010	<wandb.sdk.data_types.image.Image object at 0x7f4db49fcdf0>	<wandb.sdk.data_types.image.Image object at 0x7f4cd43b4340>	0.0003	<wandb.sdk.data_types.image.Image object at 0x7f4db49aa140>	<wandb.sdk.data_types.image.Image object at 0x7f4d8c08d960>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f4da4156f20>	<wandb.sdk.data_types.image.Image object at 0x7f4d8c2eb100>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f4d8c20a050>	<wandb.sdk.data_types.image.Image object at 0x7f4d9b7c3790>
0.0005	8.0	7544	0.0003	0.0003	0.0010	<wandb.sdk.data_types.image.Image object at 0x7f4d9b7958d0>	<wandb.sdk.data_types.image.Image object at 0x7f4d7c1ec610>	0.0003	<wandb.sdk.data_types.image.Image object at 0x7f4d9b929300>	<wandb.sdk.data_types.image.Image object at 0x7f4d9b44eda0>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f4cd46134c0>	<wandb.sdk.data_types.image.Image object at 0x7f4c1469f4c0>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f4d7c179060>	<wandb.sdk.data_types.image.Image object at 0x7f4c14775d80>
0.0003	9.0	8487	0.0003	0.0003	0.0010	<wandb.sdk.data_types.image.Image object at 0x7f4c147766e0>	<wandb.sdk.data_types.image.Image object at 0x7f4cd423b010>	0.0003	<wandb.sdk.data_types.image.Image object at 0x7f4d9b7952d0>	<wandb.sdk.data_types.image.Image object at 0x7f4d8c2e8c10>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f4d8c08e920>	<wandb.sdk.data_types.image.Image object at 0x7f4d9b9395d0>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f4d9415a3b0>	<wandb.sdk.data_types.image.Image object at 0x7f4d97324e80>
0.0003	10.0	9430	0.0003	0.0003	0.0010	<wandb.sdk.data_types.image.Image object at 0x7f4db4835f90>	<wandb.sdk.data_types.image.Image object at 0x7f4d8f3550c0>	0.0003	<wandb.sdk.data_types.image.Image object at 0x7f4db4c6c0d0>	<wandb.sdk.data_types.image.Image object at 0x7f4db498cfa0>	0.0001	<wandb.sdk.data_types.image.Image object at 0x7f4db4cbc310>	<wandb.sdk.data_types.image.Image object at 0x7f4db4967400>	0.0000	<wandb.sdk.data_types.image.Image object at 0x7f4d9411b490>	<wandb.sdk.data_types.image.Image object at 0x7f4da41b1ae0>

Framework versions

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