| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 200.0, | |
| "global_step": 4800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 7.35e-05, | |
| "loss": 11.2783, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "eval_loss": 4.640867233276367, | |
| "eval_runtime": 5.3814, | |
| "eval_samples_per_second": 26.387, | |
| "eval_steps_per_second": 3.345, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 7.343617021276595e-05, | |
| "loss": 3.5578, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "eval_loss": 3.164858341217041, | |
| "eval_runtime": 5.2371, | |
| "eval_samples_per_second": 27.114, | |
| "eval_steps_per_second": 3.437, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 7.184042553191488e-05, | |
| "loss": 3.1279, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "eval_loss": 3.0335276126861572, | |
| "eval_runtime": 6.7986, | |
| "eval_samples_per_second": 20.887, | |
| "eval_steps_per_second": 2.648, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 7.024468085106383e-05, | |
| "loss": 2.9944, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "eval_loss": 2.952620267868042, | |
| "eval_runtime": 7.0283, | |
| "eval_samples_per_second": 20.204, | |
| "eval_steps_per_second": 2.561, | |
| "eval_wer": 0.998256320836966, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 6.864893617021276e-05, | |
| "loss": 2.9275, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "eval_loss": 2.929126501083374, | |
| "eval_runtime": 6.972, | |
| "eval_samples_per_second": 20.367, | |
| "eval_steps_per_second": 2.582, | |
| "eval_wer": 1.000871839581517, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 6.70531914893617e-05, | |
| "loss": 2.8077, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 2.563281536102295, | |
| "eval_runtime": 7.1264, | |
| "eval_samples_per_second": 19.926, | |
| "eval_steps_per_second": 2.526, | |
| "eval_wer": 0.9895379250217959, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 29.17, | |
| "learning_rate": 6.545744680851063e-05, | |
| "loss": 2.4438, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 29.17, | |
| "eval_loss": 1.904543399810791, | |
| "eval_runtime": 6.7668, | |
| "eval_samples_per_second": 20.985, | |
| "eval_steps_per_second": 2.66, | |
| "eval_wer": 0.95640802092415, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 6.386170212765957e-05, | |
| "loss": 1.9659, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "eval_loss": 1.4114454984664917, | |
| "eval_runtime": 6.9861, | |
| "eval_samples_per_second": 20.326, | |
| "eval_steps_per_second": 2.577, | |
| "eval_wer": 0.7959895379250218, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 6.226595744680851e-05, | |
| "loss": 1.7092, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "eval_loss": 1.2583694458007812, | |
| "eval_runtime": 6.989, | |
| "eval_samples_per_second": 20.318, | |
| "eval_steps_per_second": 2.575, | |
| "eval_wer": 0.7637314734088928, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 6.067021276595744e-05, | |
| "loss": 1.517, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "eval_loss": 1.2040127515792847, | |
| "eval_runtime": 5.4494, | |
| "eval_samples_per_second": 26.058, | |
| "eval_steps_per_second": 3.303, | |
| "eval_wer": 0.7506538796861377, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 45.83, | |
| "learning_rate": 5.907446808510638e-05, | |
| "loss": 1.3966, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 45.83, | |
| "eval_loss": 1.127307415008545, | |
| "eval_runtime": 6.9676, | |
| "eval_samples_per_second": 20.38, | |
| "eval_steps_per_second": 2.583, | |
| "eval_wer": 0.7462946817785527, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 5.747872340425531e-05, | |
| "loss": 1.3197, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 1.10543692111969, | |
| "eval_runtime": 6.7578, | |
| "eval_samples_per_second": 21.013, | |
| "eval_steps_per_second": 2.664, | |
| "eval_wer": 0.6957279860505667, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 54.17, | |
| "learning_rate": 5.588297872340425e-05, | |
| "loss": 1.2476, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 54.17, | |
| "eval_loss": 1.1034547090530396, | |
| "eval_runtime": 6.9962, | |
| "eval_samples_per_second": 20.297, | |
| "eval_steps_per_second": 2.573, | |
| "eval_wer": 0.7000871839581517, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 58.33, | |
| "learning_rate": 5.428723404255319e-05, | |
| "loss": 1.1796, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 58.33, | |
| "eval_loss": 1.0890159606933594, | |
| "eval_runtime": 6.8836, | |
| "eval_samples_per_second": 20.629, | |
| "eval_steps_per_second": 2.615, | |
| "eval_wer": 0.7096774193548387, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "learning_rate": 5.269148936170212e-05, | |
| "loss": 1.1237, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "eval_loss": 1.0882998704910278, | |
| "eval_runtime": 7.0292, | |
| "eval_samples_per_second": 20.202, | |
| "eval_steps_per_second": 2.561, | |
| "eval_wer": 0.7166521360069747, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 5.109574468085105e-05, | |
| "loss": 1.0777, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "eval_loss": 1.106709599494934, | |
| "eval_runtime": 6.9652, | |
| "eval_samples_per_second": 20.387, | |
| "eval_steps_per_second": 2.584, | |
| "eval_wer": 0.7218831734960767, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 70.83, | |
| "learning_rate": 4.95e-05, | |
| "loss": 1.0051, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 70.83, | |
| "eval_loss": 1.111539363861084, | |
| "eval_runtime": 5.3056, | |
| "eval_samples_per_second": 26.764, | |
| "eval_steps_per_second": 3.393, | |
| "eval_wer": 0.7236268526591108, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 4.7904255319148935e-05, | |
| "loss": 0.9521, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_loss": 1.0866659879684448, | |
| "eval_runtime": 7.6166, | |
| "eval_samples_per_second": 18.644, | |
| "eval_steps_per_second": 2.363, | |
| "eval_wer": 0.7131647776809067, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 79.17, | |
| "learning_rate": 4.6308510638297865e-05, | |
| "loss": 0.9147, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 79.17, | |
| "eval_loss": 1.0851967334747314, | |
| "eval_runtime": 6.7698, | |
| "eval_samples_per_second": 20.975, | |
| "eval_steps_per_second": 2.659, | |
| "eval_wer": 0.7210113339145597, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 83.33, | |
| "learning_rate": 4.471276595744681e-05, | |
| "loss": 0.8798, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 83.33, | |
| "eval_loss": 1.1411497592926025, | |
| "eval_runtime": 6.711, | |
| "eval_samples_per_second": 21.159, | |
| "eval_steps_per_second": 2.682, | |
| "eval_wer": 0.7096774193548387, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 87.5, | |
| "learning_rate": 4.311702127659574e-05, | |
| "loss": 0.8317, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 87.5, | |
| "eval_loss": 1.1634019613265991, | |
| "eval_runtime": 6.8272, | |
| "eval_samples_per_second": 20.799, | |
| "eval_steps_per_second": 2.637, | |
| "eval_wer": 0.7018308631211857, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 91.67, | |
| "learning_rate": 4.152127659574468e-05, | |
| "loss": 0.7946, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 91.67, | |
| "eval_loss": 1.1620630025863647, | |
| "eval_runtime": 7.1289, | |
| "eval_samples_per_second": 19.919, | |
| "eval_steps_per_second": 2.525, | |
| "eval_wer": 0.7201394943330427, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 95.83, | |
| "learning_rate": 3.992553191489361e-05, | |
| "loss": 0.7594, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 95.83, | |
| "eval_loss": 1.1481679677963257, | |
| "eval_runtime": 7.0324, | |
| "eval_samples_per_second": 20.192, | |
| "eval_steps_per_second": 2.56, | |
| "eval_wer": 0.7035745422842197, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 3.834574468085106e-05, | |
| "loss": 0.729, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 1.1493021249771118, | |
| "eval_runtime": 6.9652, | |
| "eval_samples_per_second": 20.387, | |
| "eval_steps_per_second": 2.584, | |
| "eval_wer": 0.7061900610287707, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 104.17, | |
| "learning_rate": 3.675e-05, | |
| "loss": 0.7055, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 104.17, | |
| "eval_loss": 1.1725823879241943, | |
| "eval_runtime": 7.0084, | |
| "eval_samples_per_second": 20.261, | |
| "eval_steps_per_second": 2.568, | |
| "eval_wer": 0.6931124673060157, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 108.33, | |
| "learning_rate": 3.5154255319148936e-05, | |
| "loss": 0.6622, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 108.33, | |
| "eval_loss": 1.1937670707702637, | |
| "eval_runtime": 7.4493, | |
| "eval_samples_per_second": 19.062, | |
| "eval_steps_per_second": 2.416, | |
| "eval_wer": 0.7000871839581517, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 112.5, | |
| "learning_rate": 3.355851063829787e-05, | |
| "loss": 0.6583, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 112.5, | |
| "eval_loss": 1.1832083463668823, | |
| "eval_runtime": 6.9743, | |
| "eval_samples_per_second": 20.361, | |
| "eval_steps_per_second": 2.581, | |
| "eval_wer": 0.7149084568439407, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 116.67, | |
| "learning_rate": 3.1962765957446805e-05, | |
| "loss": 0.6299, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 116.67, | |
| "eval_loss": 1.1996266841888428, | |
| "eval_runtime": 7.2192, | |
| "eval_samples_per_second": 19.67, | |
| "eval_steps_per_second": 2.493, | |
| "eval_wer": 0.7175239755884917, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 120.83, | |
| "learning_rate": 3.036702127659574e-05, | |
| "loss": 0.5903, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 120.83, | |
| "eval_loss": 1.1986336708068848, | |
| "eval_runtime": 7.2606, | |
| "eval_samples_per_second": 19.558, | |
| "eval_steps_per_second": 2.479, | |
| "eval_wer": 0.7131647776809067, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "learning_rate": 2.877127659574468e-05, | |
| "loss": 0.5816, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_loss": 1.1909323930740356, | |
| "eval_runtime": 6.9272, | |
| "eval_samples_per_second": 20.499, | |
| "eval_steps_per_second": 2.598, | |
| "eval_wer": 0.7009590235396687, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 129.17, | |
| "learning_rate": 2.7175531914893614e-05, | |
| "loss": 0.5583, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 129.17, | |
| "eval_loss": 1.207918405532837, | |
| "eval_runtime": 6.9368, | |
| "eval_samples_per_second": 20.471, | |
| "eval_steps_per_second": 2.595, | |
| "eval_wer": 0.6870095902353966, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 133.33, | |
| "learning_rate": 2.5579787234042552e-05, | |
| "loss": 0.5392, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 133.33, | |
| "eval_loss": 1.2108745574951172, | |
| "eval_runtime": 5.9814, | |
| "eval_samples_per_second": 23.74, | |
| "eval_steps_per_second": 3.009, | |
| "eval_wer": 0.7227550130775937, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 137.5, | |
| "learning_rate": 2.398404255319149e-05, | |
| "loss": 0.5412, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 137.5, | |
| "eval_loss": 1.235259771347046, | |
| "eval_runtime": 6.7958, | |
| "eval_samples_per_second": 20.895, | |
| "eval_steps_per_second": 2.649, | |
| "eval_wer": 0.7244986922406277, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 141.67, | |
| "learning_rate": 2.2388297872340424e-05, | |
| "loss": 0.5136, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 141.67, | |
| "eval_loss": 1.2390460968017578, | |
| "eval_runtime": 6.7486, | |
| "eval_samples_per_second": 21.042, | |
| "eval_steps_per_second": 2.667, | |
| "eval_wer": 0.7253705318221447, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 145.83, | |
| "learning_rate": 2.079255319148936e-05, | |
| "loss": 0.5007, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 145.83, | |
| "eval_loss": 1.227264165878296, | |
| "eval_runtime": 6.7331, | |
| "eval_samples_per_second": 21.09, | |
| "eval_steps_per_second": 2.673, | |
| "eval_wer": 0.7122929380993898, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "learning_rate": 1.9196808510638296e-05, | |
| "loss": 0.4883, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "eval_loss": 1.2772815227508545, | |
| "eval_runtime": 6.6223, | |
| "eval_samples_per_second": 21.443, | |
| "eval_steps_per_second": 2.718, | |
| "eval_wer": 0.7288578901482128, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 154.17, | |
| "learning_rate": 1.7601063829787233e-05, | |
| "loss": 0.4835, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 154.17, | |
| "eval_loss": 1.2677749395370483, | |
| "eval_runtime": 6.8418, | |
| "eval_samples_per_second": 20.755, | |
| "eval_steps_per_second": 2.631, | |
| "eval_wer": 0.7288578901482128, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 158.33, | |
| "learning_rate": 1.600531914893617e-05, | |
| "loss": 0.4568, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 158.33, | |
| "eval_loss": 1.2592484951019287, | |
| "eval_runtime": 6.8949, | |
| "eval_samples_per_second": 20.595, | |
| "eval_steps_per_second": 2.611, | |
| "eval_wer": 0.7349607672188317, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 162.5, | |
| "learning_rate": 1.4409574468085105e-05, | |
| "loss": 0.4525, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 162.5, | |
| "eval_loss": 1.270469069480896, | |
| "eval_runtime": 5.5893, | |
| "eval_samples_per_second": 25.406, | |
| "eval_steps_per_second": 3.22, | |
| "eval_wer": 0.7253705318221447, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 166.67, | |
| "learning_rate": 1.2813829787234041e-05, | |
| "loss": 0.4379, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 166.67, | |
| "eval_loss": 1.2717314958572388, | |
| "eval_runtime": 6.6834, | |
| "eval_samples_per_second": 21.247, | |
| "eval_steps_per_second": 2.693, | |
| "eval_wer": 0.7306015693112468, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 170.83, | |
| "learning_rate": 1.1218085106382979e-05, | |
| "loss": 0.4198, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 170.83, | |
| "eval_loss": 1.2617682218551636, | |
| "eval_runtime": 7.1514, | |
| "eval_samples_per_second": 19.856, | |
| "eval_steps_per_second": 2.517, | |
| "eval_wer": 0.7218831734960767, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 175.0, | |
| "learning_rate": 9.622340425531914e-06, | |
| "loss": 0.4216, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 175.0, | |
| "eval_loss": 1.2908614873886108, | |
| "eval_runtime": 7.5161, | |
| "eval_samples_per_second": 18.893, | |
| "eval_steps_per_second": 2.395, | |
| "eval_wer": 0.7157802964254577, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 179.17, | |
| "learning_rate": 8.02659574468085e-06, | |
| "loss": 0.4305, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 179.17, | |
| "eval_loss": 1.2808016538619995, | |
| "eval_runtime": 7.0468, | |
| "eval_samples_per_second": 20.151, | |
| "eval_steps_per_second": 2.554, | |
| "eval_wer": 0.7166521360069747, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 183.33, | |
| "learning_rate": 6.446808510638297e-06, | |
| "loss": 0.399, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 183.33, | |
| "eval_loss": 1.2750086784362793, | |
| "eval_runtime": 6.8372, | |
| "eval_samples_per_second": 20.769, | |
| "eval_steps_per_second": 2.633, | |
| "eval_wer": 0.7192676547515258, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 187.5, | |
| "learning_rate": 4.851063829787233e-06, | |
| "loss": 0.3937, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 187.5, | |
| "eval_loss": 1.271910309791565, | |
| "eval_runtime": 7.0869, | |
| "eval_samples_per_second": 20.037, | |
| "eval_steps_per_second": 2.54, | |
| "eval_wer": 0.7149084568439407, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 191.67, | |
| "learning_rate": 3.25531914893617e-06, | |
| "loss": 0.3905, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 191.67, | |
| "eval_loss": 1.2815755605697632, | |
| "eval_runtime": 5.4594, | |
| "eval_samples_per_second": 26.01, | |
| "eval_steps_per_second": 3.297, | |
| "eval_wer": 0.7157802964254577, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 195.83, | |
| "learning_rate": 1.6595744680851062e-06, | |
| "loss": 0.3892, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 195.83, | |
| "eval_loss": 1.295116901397705, | |
| "eval_runtime": 7.0588, | |
| "eval_samples_per_second": 20.117, | |
| "eval_steps_per_second": 2.55, | |
| "eval_wer": 0.7210113339145597, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "learning_rate": 6.382978723404255e-08, | |
| "loss": 0.3932, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "eval_loss": 1.2923693656921387, | |
| "eval_runtime": 7.179, | |
| "eval_samples_per_second": 19.78, | |
| "eval_steps_per_second": 2.507, | |
| "eval_wer": 0.7201394943330427, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "step": 4800, | |
| "total_flos": 1.0000910465788367e+19, | |
| "train_loss": 1.2620406293869018, | |
| "train_runtime": 6643.3653, | |
| "train_samples_per_second": 11.38, | |
| "train_steps_per_second": 0.723 | |
| } | |
| ], | |
| "max_steps": 4800, | |
| "num_train_epochs": 200, | |
| "total_flos": 1.0000910465788367e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |