twscrape-prepared-regression-qwen-3b-full-1epochs

• Loss: 1.3087
• Mse: 0.0003
• Target 0 Mse: 0.0008
• Target 0 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f8816507ac0>
• Target 0 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f8815712fe0>
• Target 1 Mse: 0.0003
• Target 1 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f8b78b175e0>
• Target 1 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f8815ff4d90>
• Target 2 Mse: 0.0000
• Target 2 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f881603e680>
• Target 2 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f88158d2c80>
• Target 3 Mse: 0.0000
• Target 3 Distributions: <wandb.sdk.data_types.image.Image object at 0x7f8815d6c8b0>
• Target 3 Error Distribution: <wandb.sdk.data_types.image.Image object at 0x7f8815db5c60>

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 256
• total_eval_batch_size: 128
• 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: 1.0

Training results

Framework versions

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