Ctrl+K
- 1.52 kB initial commit
- 369 Bytes upload checkpoint step=95600 best_val_loss=3.987103
- 1.72 kB upload checkpoint step=95600 best_val_loss=3.987103
- 487 Bytes upload checkpoint step=95600 best_val_loss=3.987103
- 164 Bytes upload checkpoint step=19999 best_val_loss=4.810709
- 107 MB xetUpload mija_bench_with_gpt4o_mini_text.parquet
- model_state.pt761 MB
Detected Pickle imports (442)
- "collections.OrderedDict",
- "torch.ByteStorage",
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling",
- "torch.storage._load_from_bytes",
- "transformer_engine.common.recipe._FormatHelper",
- "collections.OrderedDict",
- "transformer_engine.common.recipe.Format",
- "torch._utils._rebuild_tensor_v2",
- "transformer_engine.common.recipe.DelayedScaling"
xetupload checkpoint step=95600 best_val_loss=3.987103 - 113 MB xetUpload resultado_final_completo.parquet
- 131 Bytes upload checkpoint step=19999 best_val_loss=4.810709
- 225 Bytes upload checkpoint step=95600 best_val_loss=3.987103
- 193 Bytes upload checkpoint step=19999 best_val_loss=4.810709