santacoder-finetuned-robot

This model is a fine-tuned version of bigcode/santacoder on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6328

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1
• training_steps: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.05	1	1.7303
No log	0.1	2	2.2496
No log	0.15	3	1.4159
No log	0.2	4	1.8682
No log	0.25	5	1.1694
No log	0.3	6	1.0727
No log	0.35	7	1.0604
No log	0.4	8	1.0381
No log	0.45	9	1.0675
1.4199	0.5	10	0.7489
1.4199	0.55	11	0.7854
1.4199	0.6	12	0.7172
1.4199	0.65	13	0.6637
1.4199	0.7	14	0.6807
1.4199	0.75	15	0.6512
1.4199	0.8	16	0.6214
1.4199	0.85	17	0.6348
1.4199	0.9	18	0.6343
1.4199	0.95	19	0.6325
0.4492	1.0	20	0.6328

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3