|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 30.0, |
|
"eval_steps": 100, |
|
"global_step": 7020, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.43, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 60.2276, |
|
"eval_samples_per_second": 12.42, |
|
"eval_steps_per_second": 1.561, |
|
"eval_wer": 1.258039732191856, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 58.2497, |
|
"eval_samples_per_second": 12.841, |
|
"eval_steps_per_second": 1.614, |
|
"eval_wer": 1.0, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 58.0059, |
|
"eval_samples_per_second": 12.895, |
|
"eval_steps_per_second": 1.621, |
|
"eval_wer": 1.0, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 57.8536, |
|
"eval_samples_per_second": 12.929, |
|
"eval_steps_per_second": 1.625, |
|
"eval_wer": 1.0, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 7.807999999999999e-06, |
|
"loss": 12.36, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 59.1436, |
|
"eval_samples_per_second": 12.647, |
|
"eval_steps_per_second": 1.589, |
|
"eval_wer": 1.0, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 57.8973, |
|
"eval_samples_per_second": 12.919, |
|
"eval_steps_per_second": 1.624, |
|
"eval_wer": 1.0, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 57.5316, |
|
"eval_samples_per_second": 13.002, |
|
"eval_steps_per_second": 1.634, |
|
"eval_wer": 1.0, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 3.42, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 58.6719, |
|
"eval_samples_per_second": 12.749, |
|
"eval_steps_per_second": 1.602, |
|
"eval_wer": 1.0, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 58.8307, |
|
"eval_samples_per_second": 12.714, |
|
"eval_steps_per_second": 1.598, |
|
"eval_wer": 1.0, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 7.414723926380368e-06, |
|
"loss": 8.4674, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 58.475, |
|
"eval_samples_per_second": 12.792, |
|
"eval_steps_per_second": 1.608, |
|
"eval_wer": 1.0, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 4.7, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.8849, |
|
"eval_samples_per_second": 13.629, |
|
"eval_steps_per_second": 1.713, |
|
"eval_wer": 1.0, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 5.13, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 55.2282, |
|
"eval_samples_per_second": 13.544, |
|
"eval_steps_per_second": 1.702, |
|
"eval_wer": 1.0, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 5.56, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 56.5087, |
|
"eval_samples_per_second": 13.237, |
|
"eval_steps_per_second": 1.663, |
|
"eval_wer": 1.0, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 5.98, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.6135, |
|
"eval_samples_per_second": 13.696, |
|
"eval_steps_per_second": 1.721, |
|
"eval_wer": 1.0, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 6.41, |
|
"learning_rate": 6.813496932515337e-06, |
|
"loss": 6.9866, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 6.41, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.3306, |
|
"eval_samples_per_second": 13.768, |
|
"eval_steps_per_second": 1.73, |
|
"eval_wer": 1.0, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 6.84, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.6515, |
|
"eval_samples_per_second": 13.687, |
|
"eval_steps_per_second": 1.72, |
|
"eval_wer": 1.0, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 7.26, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.747, |
|
"eval_samples_per_second": 13.663, |
|
"eval_steps_per_second": 1.717, |
|
"eval_wer": 1.0, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 7.69, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.4355, |
|
"eval_samples_per_second": 13.741, |
|
"eval_steps_per_second": 1.727, |
|
"eval_wer": 1.0, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 8.12, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.7161, |
|
"eval_samples_per_second": 13.671, |
|
"eval_steps_per_second": 1.718, |
|
"eval_wer": 1.0, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 8.55, |
|
"learning_rate": 6.213496932515337e-06, |
|
"loss": 6.8089, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 8.55, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.3228, |
|
"eval_samples_per_second": 13.77, |
|
"eval_steps_per_second": 1.73, |
|
"eval_wer": 1.0, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 8.97, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.3156, |
|
"eval_samples_per_second": 13.771, |
|
"eval_steps_per_second": 1.731, |
|
"eval_wer": 1.0, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 9.4, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.9347, |
|
"eval_samples_per_second": 13.869, |
|
"eval_steps_per_second": 1.743, |
|
"eval_wer": 1.0, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 9.83, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.9961, |
|
"eval_samples_per_second": 13.853, |
|
"eval_steps_per_second": 1.741, |
|
"eval_wer": 1.0, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 10.26, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.7565, |
|
"eval_samples_per_second": 13.66, |
|
"eval_steps_per_second": 1.717, |
|
"eval_wer": 1.0, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 10.68, |
|
"learning_rate": 5.613496932515337e-06, |
|
"loss": 6.7847, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 10.68, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 55.3504, |
|
"eval_samples_per_second": 13.514, |
|
"eval_steps_per_second": 1.698, |
|
"eval_wer": 1.0, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 11.11, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.5118, |
|
"eval_samples_per_second": 13.722, |
|
"eval_steps_per_second": 1.724, |
|
"eval_wer": 1.0, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 11.54, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 55.1125, |
|
"eval_samples_per_second": 13.572, |
|
"eval_steps_per_second": 1.706, |
|
"eval_wer": 1.0, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 11.97, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.9713, |
|
"eval_samples_per_second": 13.859, |
|
"eval_steps_per_second": 1.742, |
|
"eval_wer": 1.0, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 12.39, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.933, |
|
"eval_samples_per_second": 13.869, |
|
"eval_steps_per_second": 1.743, |
|
"eval_wer": 1.0, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 12.82, |
|
"learning_rate": 5.0122699386503064e-06, |
|
"loss": 6.7941, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 12.82, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.7915, |
|
"eval_samples_per_second": 13.906, |
|
"eval_steps_per_second": 1.747, |
|
"eval_wer": 1.0, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 13.25, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.0722, |
|
"eval_samples_per_second": 13.833, |
|
"eval_steps_per_second": 1.738, |
|
"eval_wer": 1.0, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 13.68, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.6653, |
|
"eval_samples_per_second": 13.938, |
|
"eval_steps_per_second": 1.752, |
|
"eval_wer": 1.0, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 14.1, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.481, |
|
"eval_samples_per_second": 13.986, |
|
"eval_steps_per_second": 1.758, |
|
"eval_wer": 1.0, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 14.53, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.2383, |
|
"eval_samples_per_second": 13.791, |
|
"eval_steps_per_second": 1.733, |
|
"eval_wer": 1.0, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 14.96, |
|
"learning_rate": 4.412269938650307e-06, |
|
"loss": 6.7956, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 14.96, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.7211, |
|
"eval_samples_per_second": 13.669, |
|
"eval_steps_per_second": 1.718, |
|
"eval_wer": 1.0, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 15.38, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.1823, |
|
"eval_samples_per_second": 13.805, |
|
"eval_steps_per_second": 1.735, |
|
"eval_wer": 1.0, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 15.81, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.1656, |
|
"eval_samples_per_second": 13.81, |
|
"eval_steps_per_second": 1.735, |
|
"eval_wer": 1.0, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 16.24, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.5557, |
|
"eval_samples_per_second": 13.711, |
|
"eval_steps_per_second": 1.723, |
|
"eval_wer": 1.0, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 16.67, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.9313, |
|
"eval_samples_per_second": 13.617, |
|
"eval_steps_per_second": 1.711, |
|
"eval_wer": 1.0, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 17.09, |
|
"learning_rate": 3.811042944785276e-06, |
|
"loss": 6.8102, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 17.09, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.5372, |
|
"eval_samples_per_second": 13.972, |
|
"eval_steps_per_second": 1.756, |
|
"eval_wer": 1.0, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 17.52, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.8907, |
|
"eval_samples_per_second": 13.88, |
|
"eval_steps_per_second": 1.744, |
|
"eval_wer": 1.0, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 17.95, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.237, |
|
"eval_samples_per_second": 13.791, |
|
"eval_steps_per_second": 1.733, |
|
"eval_wer": 1.0, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 18.38, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 55.2609, |
|
"eval_samples_per_second": 13.536, |
|
"eval_steps_per_second": 1.701, |
|
"eval_wer": 1.0, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 18.8, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.5797, |
|
"eval_samples_per_second": 13.705, |
|
"eval_steps_per_second": 1.722, |
|
"eval_wer": 1.0, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 19.23, |
|
"learning_rate": 3.211042944785276e-06, |
|
"loss": 6.7761, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 19.23, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.9682, |
|
"eval_samples_per_second": 13.608, |
|
"eval_steps_per_second": 1.71, |
|
"eval_wer": 1.0, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 19.66, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.7806, |
|
"eval_samples_per_second": 13.654, |
|
"eval_steps_per_second": 1.716, |
|
"eval_wer": 1.0, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 20.09, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.3191, |
|
"eval_samples_per_second": 14.029, |
|
"eval_steps_per_second": 1.763, |
|
"eval_wer": 1.0, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 20.51, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.1748, |
|
"eval_samples_per_second": 13.807, |
|
"eval_steps_per_second": 1.735, |
|
"eval_wer": 1.0, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 20.94, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.7395, |
|
"eval_samples_per_second": 13.919, |
|
"eval_steps_per_second": 1.749, |
|
"eval_wer": 1.0, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 21.37, |
|
"learning_rate": 2.6085889570552147e-06, |
|
"loss": 6.8063, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 21.37, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.3884, |
|
"eval_samples_per_second": 13.753, |
|
"eval_steps_per_second": 1.728, |
|
"eval_wer": 1.0, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 21.79, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.0413, |
|
"eval_samples_per_second": 13.841, |
|
"eval_steps_per_second": 1.739, |
|
"eval_wer": 1.0, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 22.22, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.5209, |
|
"eval_samples_per_second": 13.976, |
|
"eval_steps_per_second": 1.756, |
|
"eval_wer": 1.0, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 22.65, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.6053, |
|
"eval_samples_per_second": 13.954, |
|
"eval_steps_per_second": 1.754, |
|
"eval_wer": 1.0, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 23.08, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.6011, |
|
"eval_samples_per_second": 13.955, |
|
"eval_steps_per_second": 1.754, |
|
"eval_wer": 1.0, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 23.5, |
|
"learning_rate": 2.0085889570552145e-06, |
|
"loss": 6.7934, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 23.5, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.8555, |
|
"eval_samples_per_second": 13.889, |
|
"eval_steps_per_second": 1.745, |
|
"eval_wer": 1.0, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 23.93, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.8589, |
|
"eval_samples_per_second": 13.888, |
|
"eval_steps_per_second": 1.745, |
|
"eval_wer": 1.0, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 24.36, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.7804, |
|
"eval_samples_per_second": 13.908, |
|
"eval_steps_per_second": 1.748, |
|
"eval_wer": 1.0, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 24.79, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.7894, |
|
"eval_samples_per_second": 13.906, |
|
"eval_steps_per_second": 1.748, |
|
"eval_wer": 1.0, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 25.21, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.0321, |
|
"eval_samples_per_second": 13.844, |
|
"eval_steps_per_second": 1.74, |
|
"eval_wer": 1.0, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 25.64, |
|
"learning_rate": 1.4085889570552147e-06, |
|
"loss": 6.7819, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 25.64, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 53.8026, |
|
"eval_samples_per_second": 13.903, |
|
"eval_steps_per_second": 1.747, |
|
"eval_wer": 1.0, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 26.07, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 57.7929, |
|
"eval_samples_per_second": 12.943, |
|
"eval_steps_per_second": 1.626, |
|
"eval_wer": 1.0, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 26.5, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 55.4788, |
|
"eval_samples_per_second": 13.483, |
|
"eval_steps_per_second": 1.694, |
|
"eval_wer": 1.0, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 26.92, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 55.3669, |
|
"eval_samples_per_second": 13.51, |
|
"eval_steps_per_second": 1.698, |
|
"eval_wer": 1.0, |
|
"step": 6300 |
|
}, |
|
{ |
|
"epoch": 27.35, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.9557, |
|
"eval_samples_per_second": 13.611, |
|
"eval_steps_per_second": 1.71, |
|
"eval_wer": 1.0, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 27.78, |
|
"learning_rate": 8.07361963190184e-07, |
|
"loss": 6.8278, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 27.78, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.648, |
|
"eval_samples_per_second": 13.688, |
|
"eval_steps_per_second": 1.72, |
|
"eval_wer": 1.0, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 28.21, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.7948, |
|
"eval_samples_per_second": 13.651, |
|
"eval_steps_per_second": 1.715, |
|
"eval_wer": 1.0, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 28.63, |
|
"eval_loss": Infinity, |
|
"eval_runtime": 54.9921, |
|
"eval_samples_per_second": 13.602, |
|
"eval_steps_per_second": 1.709, |
|
"eval_wer": 1.0, |
|
"step": 6700 |
|
}, |
|
{ |
|
"epoch": 29.06, |
|
"eval_loss": NaN, |
|
"eval_runtime": 54.8536, |
|
"eval_samples_per_second": 13.636, |
|
"eval_steps_per_second": 1.714, |
|
"eval_wer": 1.0, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 29.49, |
|
"eval_loss": NaN, |
|
"eval_runtime": 54.728, |
|
"eval_samples_per_second": 13.668, |
|
"eval_steps_per_second": 1.718, |
|
"eval_wer": 1.0, |
|
"step": 6900 |
|
}, |
|
{ |
|
"epoch": 29.91, |
|
"learning_rate": 2.282208588957055e-07, |
|
"loss": 6.7427, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 29.91, |
|
"eval_loss": NaN, |
|
"eval_runtime": 54.4734, |
|
"eval_samples_per_second": 13.731, |
|
"eval_steps_per_second": 1.726, |
|
"eval_wer": 1.0, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"step": 7020, |
|
"total_flos": 8.526629534148013e+18, |
|
"train_loss": 7.303107645844462, |
|
"train_runtime": 22559.2753, |
|
"train_samples_per_second": 9.943, |
|
"train_steps_per_second": 0.311 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 7020, |
|
"num_train_epochs": 30, |
|
"save_steps": 500, |
|
"total_flos": 8.526629534148013e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|