the gears to ascension comments on Transfer learning and generalization-qua-capability in Babbage and Davinci (or, why division is better than Spanish)

[the gears to ascension]

Attempting to label the chart, please correct me:

X (bottom label): small fine tuning. Y (left label): large fine tuning.

Process to produce each cell in the plots:

bigmodel = finetuned(
    finetuned(orig_model,
        data=datasets[y_label][:200]),
    data=datasets[x_label][:10])
smallmodel = finetuned(
    orig_model,
    data=datasets[x_label][:10])
plot_1_scores[(x_label, y_label)] = test(bigmodel, datasets[x_label][10:])
plot_2_scores[(x_label, y_label)] = plot_1_scores[(x_label, y_label)] - test(smallmodel, datasets[x_label][10:])

Pretty sure I got something wrong, your descriptions are pretty ambitious.