java_and_text_pythia_410m

This model is a fine-tuned version of EleutherAI/pythia-410m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.6663
• Accuracy: 0.1806
• Num Input Tokens Seen: 1990656

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 8
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Input Tokens Seen
No log	0	0	2.6310	0.25	0
1.9603	0.6173	50	1.8225	0.1944	409600
1.7774	1.2346	100	1.7544	0.1806	819200
1.6193	1.8519	150	1.6663	0.1806	1228800
1.7311	2.4691	200	1.7399	0.1944	1638400

Framework versions

• Transformers 4.43.2
• Pytorch 2.4.0
• Datasets 2.20.0
• Tokenizers 0.19.1