ruadapt_solar_10.7_part1_proj_init_rsg_lora

This model is a fine-tuned version of RefalMachine/ruadapt_solar_10.7_part1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0771

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: 0.00025
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 30
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.1107	0.45	100	0.0784
0.0853	0.9	200	0.0900
0.0565	1.35	300	0.0818
0.0475	1.8	400	0.0688
0.0203	2.24	500	0.0788
0.0291	2.69	600	0.0771

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.2
• Datasets 2.14.4
• Tokenizers 0.14.1