| { | |
| "batch_size": 12, | |
| "block_num": 16, | |
| "embed_dims": 1024, | |
| "head_size": 64, | |
| "iterations": 40000, | |
| "lr": 0.0003, | |
| "num_heads": 16, | |
| "seq_len": 2048, | |
| "vocab_size": 49152 | |
| } |
| { | |
| "batch_size": 12, | |
| "block_num": 16, | |
| "embed_dims": 1024, | |
| "head_size": 64, | |
| "iterations": 40000, | |
| "lr": 0.0003, | |
| "num_heads": 16, | |
| "seq_len": 2048, | |
| "vocab_size": 49152 | |
| } |