anthonymeo/full-train-expanded

predict2

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: 0.2200

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
0.2062	0.5984	100	0.2123
0.1256	1.1967	200	0.2036
0.1296	1.7951	300	0.1937
0.0592	2.3934	400	0.2185
0.0646	2.9918	500	0.2199

Framework versions

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