| { | |
| "d_model": 128, | |
| "nhead": 4, | |
| "num_layers": 4, | |
| "vocab_size": 257, | |
| "avg_loss": 0.04414808150714841, | |
| "avg_bpb": 0.06369221825512475 | |
| } |
| { | |
| "d_model": 128, | |
| "nhead": 4, | |
| "num_layers": 4, | |
| "vocab_size": 257, | |
| "avg_loss": 0.04414808150714841, | |
| "avg_bpb": 0.06369221825512475 | |
| } |