anthonymeo/full-train

predict

This model is a fine-tuned version of internlm/internlm2_5-1_8b-chat on the expanded dataset. It achieves the following results on the evaluation set:

• Loss: 0.3829

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: 4
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.3932	0.5398	100	0.3729
0.235	1.0796	200	0.3673
0.2243	1.6194	300	0.3492
0.1416	2.1592	400	0.3768
0.1247	2.6991	500	0.3841

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1