| { | |
| "step": 650, | |
| "val_loss": 1.0146265029907227, | |
| "mmlu_acc": 0.3037109375, | |
| "arc_easy_acc": 0.33203125, | |
| "model_config": { | |
| "sequence_len": 2048, | |
| "vocab_size": 65536, | |
| "n_layer": 20, | |
| "n_head": 10, | |
| "n_kv_head": 10, | |
| "n_embd": 1280 | |
| } | |
| } |
| { | |
| "step": 650, | |
| "val_loss": 1.0146265029907227, | |
| "mmlu_acc": 0.3037109375, | |
| "arc_easy_acc": 0.33203125, | |
| "model_config": { | |
| "sequence_len": 2048, | |
| "vocab_size": 65536, | |
| "n_layer": 20, | |
| "n_head": 10, | |
| "n_kv_head": 10, | |
| "n_embd": 1280 | |
| } | |
| } |