| { | |
| "d_model": 128, | |
| "nhead": 4, | |
| "num_layers": 4, | |
| "vocab_size": 257, | |
| "avg_loss": 0.04948290410004556, | |
| "avg_bpb": 0.07138874035391997 | |
| } |
| { | |
| "d_model": 128, | |
| "nhead": 4, | |
| "num_layers": 4, | |
| "vocab_size": 257, | |
| "avg_loss": 0.04948290410004556, | |
| "avg_bpb": 0.07138874035391997 | |
| } |