{"loss": 2.8604686737060545, "grad_norm": 2.879204750061035, "learning_rate": 0.00019710144927536234, "entropy": 0.9759442292153835, "mean_token_accuracy": 0.5975040771067143, "num_tokens": 24284.0, "epoch": 0.12987012987012986, "step": 10}
{"eval_loss": 0.3304476737976074, "eval_runtime": 35.1127, "eval_samples_per_second": 7.86, "eval_steps_per_second": 1.965, "eval_entropy": 0.2818886768882689, "eval_mean_token_accuracy": 0.8783024968444437, "eval_num_tokens": 24284.0, "epoch": 0.12987012987012986, "step": 10}
{"loss": 0.2881659984588623, "grad_norm": 2.773315668106079, "learning_rate": 0.0001681159420289855, "entropy": 0.2522051867097616, "mean_token_accuracy": 0.8995958730578423, "num_tokens": 49006.0, "epoch": 0.2597402597402597, "step": 20}
{"eval_loss": 0.2693280279636383, "eval_runtime": 35.0653, "eval_samples_per_second": 7.871, "eval_steps_per_second": 1.968, "eval_entropy": 0.2848691619608713, "eval_mean_token_accuracy": 0.9030525883038839, "eval_num_tokens": 49006.0, "epoch": 0.2597402597402597, "step": 20}
{"loss": 0.21758480072021485, "grad_norm": 1.946448564529419, "learning_rate": 0.0001391304347826087, "entropy": 0.25360131561756133, "mean_token_accuracy": 0.9238064631819725, "num_tokens": 72913.0, "epoch": 0.38961038961038963, "step": 30}
{"eval_loss": 0.26951390504837036, "eval_runtime": 34.8665, "eval_samples_per_second": 7.916, "eval_steps_per_second": 1.979, "eval_entropy": 0.14841289556099344, "eval_mean_token_accuracy": 0.9170999691106271, "eval_num_tokens": 72913.0, "epoch": 0.38961038961038963, "step": 30}
{"loss": 0.1358746886253357, "grad_norm": 2.2474899291992188, "learning_rate": 0.00011014492753623188, "entropy": 0.12105789233464748, "mean_token_accuracy": 0.9425255253911018, "num_tokens": 97047.0, "epoch": 0.5194805194805194, "step": 40}
{"eval_loss": 0.14637623727321625, "eval_runtime": 34.8272, "eval_samples_per_second": 7.925, "eval_steps_per_second": 1.981, "eval_entropy": 0.11433988535250335, "eval_mean_token_accuracy": 0.9459391443625741, "eval_num_tokens": 97047.0, "epoch": 0.5194805194805194, "step": 40}
{"loss": 0.148651647567749, "grad_norm": 0.9377484321594238, "learning_rate": 8.115942028985508e-05, "entropy": 0.11090484634041786, "mean_token_accuracy": 0.945919668674469, "num_tokens": 121400.0, "epoch": 0.6493506493506493, "step": 50}
{"eval_loss": 0.11833041906356812, "eval_runtime": 22.6416, "eval_samples_per_second": 12.19, "eval_steps_per_second": 3.047, "eval_entropy": 0.10311543951283439, "eval_mean_token_accuracy": 0.9562725018763888, "eval_num_tokens": 121400.0, "epoch": 0.6493506493506493, "step": 50}
{"loss": 0.10815563201904296, "grad_norm": 1.8924756050109863, "learning_rate": 5.217391304347826e-05, "entropy": 0.10382378250360488, "mean_token_accuracy": 0.9667990371584892, "num_tokens": 146373.0, "epoch": 0.7792207792207793, "step": 60}
{"eval_loss": 0.09682893007993698, "eval_runtime": 22.5497, "eval_samples_per_second": 12.24, "eval_steps_per_second": 3.06, "eval_entropy": 0.0982072375735025, "eval_mean_token_accuracy": 0.9668227788330852, "eval_num_tokens": 146373.0, "epoch": 0.7792207792207793, "step": 60}
{"loss": 0.07531189322471618, "grad_norm": 0.47692957520484924, "learning_rate": 2.318840579710145e-05, "entropy": 0.08715626804623752, "mean_token_accuracy": 0.9735257163643837, "num_tokens": 170780.0, "epoch": 0.9090909090909091, "step": 70}
{"eval_loss": 0.07184422016143799, "eval_runtime": 22.5042, "eval_samples_per_second": 12.264, "eval_steps_per_second": 3.066, "eval_entropy": 0.09423687292492368, "eval_mean_token_accuracy": 0.9780449374862339, "eval_num_tokens": 170780.0, "epoch": 0.9090909090909091, "step": 70}
{"eval_loss": 0.06722576916217804, "eval_runtime": 22.5255, "eval_samples_per_second": 12.253, "eval_steps_per_second": 3.063, "eval_entropy": 0.08899597958762846, "eval_mean_token_accuracy": 0.9784566630487856, "eval_num_tokens": 187530.0, "epoch": 1.0, "step": 77}
{"train_runtime": 828.1966, "train_samples_per_second": 1.485, "train_steps_per_second": 0.093, "total_flos": 1.0844998691180544e+16, "train_loss": 0.5039860044980978, "epoch": 1.0, "step": 77}