| { | |
| "d_model": 128, | |
| "nhead": 4, | |
| "num_layers": 4, | |
| "vocab_size": 257, | |
| "avg_loss": 0.015984146152301267, | |
| "avg_bpb": 0.023060248386769445 | |
| } |
| { | |
| "d_model": 128, | |
| "nhead": 4, | |
| "num_layers": 4, | |
| "vocab_size": 257, | |
| "avg_loss": 0.015984146152301267, | |
| "avg_bpb": 0.023060248386769445 | |
| } |