Upload Minisun Trained using model.fit on NeelNanda/pile-10k[0-5000],lr 1e-4,cw 128,2 epoch,batch size 8,cosine with restart
2418aff
verified
| { | |
| "vocab_size": 50272, | |
| "max_position_embeddings": 2048, | |
| "hidden_size": 768, | |
| "num_attention_heads": 12, | |
| "intermediate_size": 3072, | |
| "num_hidden_layers": 12, | |
| "dropout_rate": 0.1, | |
| "weight_decay": 0.01, | |
| "learning_rate": 0.0001, | |
| "restart_period": 208, | |
| "total_steps": 625, | |
| "warmup_ratio": 0.2 | |
| } |