| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 120.51282051282051, | |
| "eval_steps": 100, | |
| "global_step": 23500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 92.9238510131836, | |
| "learning_rate": 9.9907e-06, | |
| "loss": 2.4016, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "eval_loss": 2.1255013942718506, | |
| "eval_runtime": 34.4318, | |
| "eval_samples_per_second": 11.414, | |
| "eval_steps_per_second": 1.452, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 47.019439697265625, | |
| "learning_rate": 9.980700000000001e-06, | |
| "loss": 2.0696, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "eval_loss": 1.9405728578567505, | |
| "eval_runtime": 34.0713, | |
| "eval_samples_per_second": 11.535, | |
| "eval_steps_per_second": 1.468, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 52.230751037597656, | |
| "learning_rate": 9.970700000000001e-06, | |
| "loss": 1.9983, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "eval_loss": 1.900020718574524, | |
| "eval_runtime": 34.1694, | |
| "eval_samples_per_second": 11.502, | |
| "eval_steps_per_second": 1.463, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 39.62374496459961, | |
| "learning_rate": 9.960800000000001e-06, | |
| "loss": 1.8888, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "eval_loss": 1.8164124488830566, | |
| "eval_runtime": 34.1213, | |
| "eval_samples_per_second": 11.518, | |
| "eval_steps_per_second": 1.465, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 39.697731018066406, | |
| "learning_rate": 9.9508e-06, | |
| "loss": 1.8456, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "eval_loss": 1.7753618955612183, | |
| "eval_runtime": 34.149, | |
| "eval_samples_per_second": 11.508, | |
| "eval_steps_per_second": 1.464, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 52.823184967041016, | |
| "learning_rate": 9.9408e-06, | |
| "loss": 1.7839, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "eval_loss": 1.7344136238098145, | |
| "eval_runtime": 34.121, | |
| "eval_samples_per_second": 11.518, | |
| "eval_steps_per_second": 1.465, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.58974358974359, | |
| "grad_norm": 107.05223083496094, | |
| "learning_rate": 9.9308e-06, | |
| "loss": 1.7544, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.58974358974359, | |
| "eval_loss": 1.6865615844726562, | |
| "eval_runtime": 34.0842, | |
| "eval_samples_per_second": 11.53, | |
| "eval_steps_per_second": 1.467, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.102564102564102, | |
| "grad_norm": 53.641353607177734, | |
| "learning_rate": 9.9208e-06, | |
| "loss": 1.6812, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.102564102564102, | |
| "eval_loss": 1.6568766832351685, | |
| "eval_runtime": 34.432, | |
| "eval_samples_per_second": 11.414, | |
| "eval_steps_per_second": 1.452, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 40.92328643798828, | |
| "learning_rate": 9.9109e-06, | |
| "loss": 1.6501, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "eval_loss": 1.6080188751220703, | |
| "eval_runtime": 34.1751, | |
| "eval_samples_per_second": 11.5, | |
| "eval_steps_per_second": 1.463, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.128205128205128, | |
| "grad_norm": 28.52039909362793, | |
| "learning_rate": 9.9009e-06, | |
| "loss": 1.6579, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.128205128205128, | |
| "eval_loss": 1.6059809923171997, | |
| "eval_runtime": 34.1634, | |
| "eval_samples_per_second": 11.504, | |
| "eval_steps_per_second": 1.464, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.641025641025641, | |
| "grad_norm": 73.21099090576172, | |
| "learning_rate": 9.8909e-06, | |
| "loss": 1.6286, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.641025641025641, | |
| "eval_loss": 1.5779187679290771, | |
| "eval_runtime": 34.1489, | |
| "eval_samples_per_second": 11.508, | |
| "eval_steps_per_second": 1.464, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 36.768428802490234, | |
| "learning_rate": 9.8809e-06, | |
| "loss": 1.5871, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "eval_loss": 1.5641562938690186, | |
| "eval_runtime": 34.1081, | |
| "eval_samples_per_second": 11.522, | |
| "eval_steps_per_second": 1.466, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 28.098352432250977, | |
| "learning_rate": 9.8709e-06, | |
| "loss": 1.6231, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "eval_loss": 1.530659556388855, | |
| "eval_runtime": 34.0717, | |
| "eval_samples_per_second": 11.534, | |
| "eval_steps_per_second": 1.467, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.17948717948718, | |
| "grad_norm": 48.131195068359375, | |
| "learning_rate": 9.8609e-06, | |
| "loss": 1.5178, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.17948717948718, | |
| "eval_loss": 1.5207794904708862, | |
| "eval_runtime": 34.0224, | |
| "eval_samples_per_second": 11.551, | |
| "eval_steps_per_second": 1.47, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "grad_norm": 15.9362211227417, | |
| "learning_rate": 9.8509e-06, | |
| "loss": 1.5434, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "eval_loss": 1.4978805780410767, | |
| "eval_runtime": 34.0269, | |
| "eval_samples_per_second": 11.55, | |
| "eval_steps_per_second": 1.469, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.205128205128204, | |
| "grad_norm": 21.21210479736328, | |
| "learning_rate": 9.840900000000001e-06, | |
| "loss": 1.5368, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.205128205128204, | |
| "eval_loss": 1.4791795015335083, | |
| "eval_runtime": 34.5402, | |
| "eval_samples_per_second": 11.378, | |
| "eval_steps_per_second": 1.448, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.717948717948717, | |
| "grad_norm": 39.53807830810547, | |
| "learning_rate": 9.830900000000001e-06, | |
| "loss": 1.5163, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 8.717948717948717, | |
| "eval_loss": 1.4630368947982788, | |
| "eval_runtime": 34.1482, | |
| "eval_samples_per_second": 11.509, | |
| "eval_steps_per_second": 1.464, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 42.564842224121094, | |
| "learning_rate": 9.820900000000001e-06, | |
| "loss": 1.483, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "eval_loss": 1.4529582262039185, | |
| "eval_runtime": 34.2374, | |
| "eval_samples_per_second": 11.479, | |
| "eval_steps_per_second": 1.46, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.743589743589745, | |
| "grad_norm": 55.969017028808594, | |
| "learning_rate": 9.810900000000001e-06, | |
| "loss": 1.4795, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 9.743589743589745, | |
| "eval_loss": 1.4357120990753174, | |
| "eval_runtime": 34.2522, | |
| "eval_samples_per_second": 11.474, | |
| "eval_steps_per_second": 1.46, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 10.256410256410255, | |
| "grad_norm": 25.308517456054688, | |
| "learning_rate": 9.800900000000001e-06, | |
| "loss": 1.4151, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 10.256410256410255, | |
| "eval_loss": 1.432659387588501, | |
| "eval_runtime": 34.2016, | |
| "eval_samples_per_second": 11.491, | |
| "eval_steps_per_second": 1.462, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 10.76923076923077, | |
| "grad_norm": 54.97860336303711, | |
| "learning_rate": 9.790900000000001e-06, | |
| "loss": 1.4665, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 10.76923076923077, | |
| "eval_loss": 1.4322772026062012, | |
| "eval_runtime": 34.2513, | |
| "eval_samples_per_second": 11.474, | |
| "eval_steps_per_second": 1.46, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 11.282051282051283, | |
| "grad_norm": 26.281103134155273, | |
| "learning_rate": 9.780900000000002e-06, | |
| "loss": 1.4336, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 11.282051282051283, | |
| "eval_loss": 1.41593337059021, | |
| "eval_runtime": 33.815, | |
| "eval_samples_per_second": 11.622, | |
| "eval_steps_per_second": 1.479, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 11.794871794871796, | |
| "grad_norm": 37.469024658203125, | |
| "learning_rate": 9.770900000000002e-06, | |
| "loss": 1.4149, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 11.794871794871796, | |
| "eval_loss": 1.4032217264175415, | |
| "eval_runtime": 33.8113, | |
| "eval_samples_per_second": 11.623, | |
| "eval_steps_per_second": 1.479, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 12.307692307692308, | |
| "grad_norm": 17.248014450073242, | |
| "learning_rate": 9.760900000000002e-06, | |
| "loss": 1.3918, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 12.307692307692308, | |
| "eval_loss": 1.3832417726516724, | |
| "eval_runtime": 34.1456, | |
| "eval_samples_per_second": 11.51, | |
| "eval_steps_per_second": 1.464, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 12.820512820512821, | |
| "grad_norm": 36.33113479614258, | |
| "learning_rate": 9.7509e-06, | |
| "loss": 1.4319, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 12.820512820512821, | |
| "eval_loss": 1.384070634841919, | |
| "eval_runtime": 33.7658, | |
| "eval_samples_per_second": 11.639, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 28.724761962890625, | |
| "learning_rate": 9.7409e-06, | |
| "loss": 1.3936, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "eval_loss": 1.3891230821609497, | |
| "eval_runtime": 33.7884, | |
| "eval_samples_per_second": 11.631, | |
| "eval_steps_per_second": 1.48, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 13.846153846153847, | |
| "grad_norm": 25.300365447998047, | |
| "learning_rate": 9.7309e-06, | |
| "loss": 1.386, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 13.846153846153847, | |
| "eval_loss": 1.373278260231018, | |
| "eval_runtime": 33.8109, | |
| "eval_samples_per_second": 11.623, | |
| "eval_steps_per_second": 1.479, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 14.35897435897436, | |
| "grad_norm": 165.74114990234375, | |
| "learning_rate": 9.7209e-06, | |
| "loss": 1.3514, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 14.35897435897436, | |
| "eval_loss": 1.376756191253662, | |
| "eval_runtime": 33.8844, | |
| "eval_samples_per_second": 11.598, | |
| "eval_steps_per_second": 1.476, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 14.871794871794872, | |
| "grad_norm": 37.75138854980469, | |
| "learning_rate": 9.7109e-06, | |
| "loss": 1.3542, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 14.871794871794872, | |
| "eval_loss": 1.3550430536270142, | |
| "eval_runtime": 34.0038, | |
| "eval_samples_per_second": 11.558, | |
| "eval_steps_per_second": 1.47, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 15.384615384615385, | |
| "grad_norm": 41.38801956176758, | |
| "learning_rate": 9.7009e-06, | |
| "loss": 1.3653, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 15.384615384615385, | |
| "eval_loss": 1.3493261337280273, | |
| "eval_runtime": 33.7831, | |
| "eval_samples_per_second": 11.633, | |
| "eval_steps_per_second": 1.48, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 15.897435897435898, | |
| "grad_norm": 54.01289749145508, | |
| "learning_rate": 9.6909e-06, | |
| "loss": 1.3451, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 15.897435897435898, | |
| "eval_loss": 1.3563708066940308, | |
| "eval_runtime": 33.7662, | |
| "eval_samples_per_second": 11.639, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 16.41025641025641, | |
| "grad_norm": 47.22911834716797, | |
| "learning_rate": 9.6809e-06, | |
| "loss": 1.323, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 16.41025641025641, | |
| "eval_loss": 1.343112587928772, | |
| "eval_runtime": 34.3174, | |
| "eval_samples_per_second": 11.452, | |
| "eval_steps_per_second": 1.457, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 16.923076923076923, | |
| "grad_norm": 254.61305236816406, | |
| "learning_rate": 9.670900000000001e-06, | |
| "loss": 1.3348, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 16.923076923076923, | |
| "eval_loss": 1.3341063261032104, | |
| "eval_runtime": 33.9905, | |
| "eval_samples_per_second": 11.562, | |
| "eval_steps_per_second": 1.471, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 17.435897435897434, | |
| "grad_norm": 25.823589324951172, | |
| "learning_rate": 9.660900000000001e-06, | |
| "loss": 1.3185, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 17.435897435897434, | |
| "eval_loss": 1.3256839513778687, | |
| "eval_runtime": 33.9185, | |
| "eval_samples_per_second": 11.587, | |
| "eval_steps_per_second": 1.474, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 17.94871794871795, | |
| "grad_norm": 44.86510467529297, | |
| "learning_rate": 9.650900000000001e-06, | |
| "loss": 1.328, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 17.94871794871795, | |
| "eval_loss": 1.3411694765090942, | |
| "eval_runtime": 33.8769, | |
| "eval_samples_per_second": 11.601, | |
| "eval_steps_per_second": 1.476, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "grad_norm": 20.39423942565918, | |
| "learning_rate": 9.640900000000001e-06, | |
| "loss": 1.3306, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "eval_loss": 1.318002462387085, | |
| "eval_runtime": 33.7275, | |
| "eval_samples_per_second": 11.652, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 18.974358974358974, | |
| "grad_norm": 42.16006088256836, | |
| "learning_rate": 9.630900000000001e-06, | |
| "loss": 1.301, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 18.974358974358974, | |
| "eval_loss": 1.3143377304077148, | |
| "eval_runtime": 33.8038, | |
| "eval_samples_per_second": 11.626, | |
| "eval_steps_per_second": 1.479, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 19.487179487179485, | |
| "grad_norm": 36.292999267578125, | |
| "learning_rate": 9.620900000000001e-06, | |
| "loss": 1.3036, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 19.487179487179485, | |
| "eval_loss": 1.3157984018325806, | |
| "eval_runtime": 33.7447, | |
| "eval_samples_per_second": 11.646, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 64.44886016845703, | |
| "learning_rate": 9.610900000000001e-06, | |
| "loss": 1.3077, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.31955885887146, | |
| "eval_runtime": 33.8296, | |
| "eval_samples_per_second": 11.617, | |
| "eval_steps_per_second": 1.478, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 20.51282051282051, | |
| "grad_norm": 37.88364028930664, | |
| "learning_rate": 9.600900000000002e-06, | |
| "loss": 1.3092, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 20.51282051282051, | |
| "eval_loss": 1.3180863857269287, | |
| "eval_runtime": 34.1642, | |
| "eval_samples_per_second": 11.503, | |
| "eval_steps_per_second": 1.464, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 21.025641025641026, | |
| "grad_norm": 27.300247192382812, | |
| "learning_rate": 9.5909e-06, | |
| "loss": 1.27, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 21.025641025641026, | |
| "eval_loss": 1.3031089305877686, | |
| "eval_runtime": 34.0151, | |
| "eval_samples_per_second": 11.554, | |
| "eval_steps_per_second": 1.47, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 21.53846153846154, | |
| "grad_norm": 27.94341278076172, | |
| "learning_rate": 9.5809e-06, | |
| "loss": 1.2983, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 21.53846153846154, | |
| "eval_loss": 1.3018323183059692, | |
| "eval_runtime": 34.1294, | |
| "eval_samples_per_second": 11.515, | |
| "eval_steps_per_second": 1.465, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 22.05128205128205, | |
| "grad_norm": 35.468135833740234, | |
| "learning_rate": 9.5709e-06, | |
| "loss": 1.2568, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 22.05128205128205, | |
| "eval_loss": 1.3130985498428345, | |
| "eval_runtime": 33.9979, | |
| "eval_samples_per_second": 11.56, | |
| "eval_steps_per_second": 1.471, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 22.564102564102566, | |
| "grad_norm": 21.431076049804688, | |
| "learning_rate": 9.5609e-06, | |
| "loss": 1.2812, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 22.564102564102566, | |
| "eval_loss": 1.293820858001709, | |
| "eval_runtime": 33.9036, | |
| "eval_samples_per_second": 11.592, | |
| "eval_steps_per_second": 1.475, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 23.076923076923077, | |
| "grad_norm": 59.38164520263672, | |
| "learning_rate": 9.5509e-06, | |
| "loss": 1.2776, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 23.076923076923077, | |
| "eval_loss": 1.2872756719589233, | |
| "eval_runtime": 33.8513, | |
| "eval_samples_per_second": 11.61, | |
| "eval_steps_per_second": 1.477, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 23.58974358974359, | |
| "grad_norm": 48.05171585083008, | |
| "learning_rate": 9.5409e-06, | |
| "loss": 1.2488, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 23.58974358974359, | |
| "eval_loss": 1.2994896173477173, | |
| "eval_runtime": 33.9738, | |
| "eval_samples_per_second": 11.568, | |
| "eval_steps_per_second": 1.472, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 24.102564102564102, | |
| "grad_norm": 32.86454391479492, | |
| "learning_rate": 9.5309e-06, | |
| "loss": 1.3085, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 24.102564102564102, | |
| "eval_loss": 1.2995264530181885, | |
| "eval_runtime": 33.8598, | |
| "eval_samples_per_second": 11.607, | |
| "eval_steps_per_second": 1.477, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 24.615384615384617, | |
| "grad_norm": 36.235042572021484, | |
| "learning_rate": 9.5209e-06, | |
| "loss": 1.2439, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 24.615384615384617, | |
| "eval_loss": 1.285250186920166, | |
| "eval_runtime": 34.2054, | |
| "eval_samples_per_second": 11.489, | |
| "eval_steps_per_second": 1.462, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 25.128205128205128, | |
| "grad_norm": 17.993911743164062, | |
| "learning_rate": 9.5109e-06, | |
| "loss": 1.2427, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 25.128205128205128, | |
| "eval_loss": 1.2752227783203125, | |
| "eval_runtime": 33.8959, | |
| "eval_samples_per_second": 11.594, | |
| "eval_steps_per_second": 1.475, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 25.641025641025642, | |
| "grad_norm": 55.71548080444336, | |
| "learning_rate": 9.501000000000001e-06, | |
| "loss": 1.2774, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 25.641025641025642, | |
| "eval_loss": 1.28258216381073, | |
| "eval_runtime": 33.7988, | |
| "eval_samples_per_second": 11.628, | |
| "eval_steps_per_second": 1.479, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 26.153846153846153, | |
| "grad_norm": 30.139249801635742, | |
| "learning_rate": 9.491000000000001e-06, | |
| "loss": 1.2224, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 26.153846153846153, | |
| "eval_loss": 1.2681365013122559, | |
| "eval_runtime": 33.759, | |
| "eval_samples_per_second": 11.641, | |
| "eval_steps_per_second": 1.481, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 39.02808380126953, | |
| "learning_rate": 9.481000000000001e-06, | |
| "loss": 1.2226, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "eval_loss": 1.2783496379852295, | |
| "eval_runtime": 33.8934, | |
| "eval_samples_per_second": 11.595, | |
| "eval_steps_per_second": 1.475, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 27.17948717948718, | |
| "grad_norm": 27.232601165771484, | |
| "learning_rate": 9.471000000000001e-06, | |
| "loss": 1.2542, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 27.17948717948718, | |
| "eval_loss": 1.2665411233901978, | |
| "eval_runtime": 33.8407, | |
| "eval_samples_per_second": 11.613, | |
| "eval_steps_per_second": 1.478, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 27.692307692307693, | |
| "grad_norm": 25.21843719482422, | |
| "learning_rate": 9.461000000000001e-06, | |
| "loss": 1.2193, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 27.692307692307693, | |
| "eval_loss": 1.2602121829986572, | |
| "eval_runtime": 33.8192, | |
| "eval_samples_per_second": 11.621, | |
| "eval_steps_per_second": 1.478, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 28.205128205128204, | |
| "grad_norm": 27.98350715637207, | |
| "learning_rate": 9.451000000000002e-06, | |
| "loss": 1.2602, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 28.205128205128204, | |
| "eval_loss": 1.257614016532898, | |
| "eval_runtime": 33.8642, | |
| "eval_samples_per_second": 11.605, | |
| "eval_steps_per_second": 1.476, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 28.71794871794872, | |
| "grad_norm": 80.89112854003906, | |
| "learning_rate": 9.441000000000002e-06, | |
| "loss": 1.2233, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 28.71794871794872, | |
| "eval_loss": 1.2567039728164673, | |
| "eval_runtime": 33.9431, | |
| "eval_samples_per_second": 11.578, | |
| "eval_steps_per_second": 1.473, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 29.23076923076923, | |
| "grad_norm": 89.17146301269531, | |
| "learning_rate": 9.431000000000002e-06, | |
| "loss": 1.2349, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 29.23076923076923, | |
| "eval_loss": 1.2528877258300781, | |
| "eval_runtime": 33.691, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 29.743589743589745, | |
| "grad_norm": 27.014436721801758, | |
| "learning_rate": 9.421000000000002e-06, | |
| "loss": 1.1977, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 29.743589743589745, | |
| "eval_loss": 1.2418824434280396, | |
| "eval_runtime": 33.786, | |
| "eval_samples_per_second": 11.632, | |
| "eval_steps_per_second": 1.48, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 30.256410256410255, | |
| "grad_norm": 34.459503173828125, | |
| "learning_rate": 9.411000000000002e-06, | |
| "loss": 1.2017, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 30.256410256410255, | |
| "eval_loss": 1.2447059154510498, | |
| "eval_runtime": 33.7138, | |
| "eval_samples_per_second": 11.657, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 30.76923076923077, | |
| "grad_norm": 33.78609848022461, | |
| "learning_rate": 9.401000000000002e-06, | |
| "loss": 1.1899, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 30.76923076923077, | |
| "eval_loss": 1.2605268955230713, | |
| "eval_runtime": 34.1716, | |
| "eval_samples_per_second": 11.501, | |
| "eval_steps_per_second": 1.463, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 31.28205128205128, | |
| "grad_norm": 15.015114784240723, | |
| "learning_rate": 9.391e-06, | |
| "loss": 1.2086, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 31.28205128205128, | |
| "eval_loss": 1.2350114583969116, | |
| "eval_runtime": 33.8206, | |
| "eval_samples_per_second": 11.62, | |
| "eval_steps_per_second": 1.478, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 31.794871794871796, | |
| "grad_norm": 34.10783386230469, | |
| "learning_rate": 9.381e-06, | |
| "loss": 1.1763, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 31.794871794871796, | |
| "eval_loss": 1.2277166843414307, | |
| "eval_runtime": 33.7042, | |
| "eval_samples_per_second": 11.66, | |
| "eval_steps_per_second": 1.483, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 32.30769230769231, | |
| "grad_norm": 42.146934509277344, | |
| "learning_rate": 9.371e-06, | |
| "loss": 1.1821, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 32.30769230769231, | |
| "eval_loss": 1.2275365591049194, | |
| "eval_runtime": 33.8943, | |
| "eval_samples_per_second": 11.595, | |
| "eval_steps_per_second": 1.475, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 32.82051282051282, | |
| "grad_norm": 27.311311721801758, | |
| "learning_rate": 9.361e-06, | |
| "loss": 1.1891, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 32.82051282051282, | |
| "eval_loss": 1.2212082147598267, | |
| "eval_runtime": 34.1213, | |
| "eval_samples_per_second": 11.518, | |
| "eval_steps_per_second": 1.465, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 33.333333333333336, | |
| "grad_norm": 25.96141242980957, | |
| "learning_rate": 9.351e-06, | |
| "loss": 1.1981, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 33.333333333333336, | |
| "eval_loss": 1.234484076499939, | |
| "eval_runtime": 33.8881, | |
| "eval_samples_per_second": 11.597, | |
| "eval_steps_per_second": 1.475, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 33.84615384615385, | |
| "grad_norm": 43.51643753051758, | |
| "learning_rate": 9.341000000000001e-06, | |
| "loss": 1.1933, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 33.84615384615385, | |
| "eval_loss": 1.2187552452087402, | |
| "eval_runtime": 33.7579, | |
| "eval_samples_per_second": 11.642, | |
| "eval_steps_per_second": 1.481, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 34.35897435897436, | |
| "grad_norm": 28.205900192260742, | |
| "learning_rate": 9.331000000000001e-06, | |
| "loss": 1.1809, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 34.35897435897436, | |
| "eval_loss": 1.227611780166626, | |
| "eval_runtime": 33.8658, | |
| "eval_samples_per_second": 11.605, | |
| "eval_steps_per_second": 1.476, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 34.87179487179487, | |
| "grad_norm": 39.5003662109375, | |
| "learning_rate": 9.321000000000001e-06, | |
| "loss": 1.191, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 34.87179487179487, | |
| "eval_loss": 1.21685791015625, | |
| "eval_runtime": 33.9275, | |
| "eval_samples_per_second": 11.584, | |
| "eval_steps_per_second": 1.474, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 35.38461538461539, | |
| "grad_norm": 49.183170318603516, | |
| "learning_rate": 9.311000000000001e-06, | |
| "loss": 1.1955, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 35.38461538461539, | |
| "eval_loss": 1.2113089561462402, | |
| "eval_runtime": 33.874, | |
| "eval_samples_per_second": 11.602, | |
| "eval_steps_per_second": 1.476, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 35.8974358974359, | |
| "grad_norm": 24.414306640625, | |
| "learning_rate": 9.301000000000001e-06, | |
| "loss": 1.1529, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 35.8974358974359, | |
| "eval_loss": 1.204311728477478, | |
| "eval_runtime": 33.8158, | |
| "eval_samples_per_second": 11.622, | |
| "eval_steps_per_second": 1.479, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 36.41025641025641, | |
| "grad_norm": 41.432579040527344, | |
| "learning_rate": 9.291000000000001e-06, | |
| "loss": 1.1701, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 36.41025641025641, | |
| "eval_loss": 1.203251600265503, | |
| "eval_runtime": 33.9027, | |
| "eval_samples_per_second": 11.592, | |
| "eval_steps_per_second": 1.475, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 36.92307692307692, | |
| "grad_norm": 33.03053665161133, | |
| "learning_rate": 9.281000000000001e-06, | |
| "loss": 1.1413, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 36.92307692307692, | |
| "eval_loss": 1.1928728818893433, | |
| "eval_runtime": 34.3378, | |
| "eval_samples_per_second": 11.445, | |
| "eval_steps_per_second": 1.456, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 37.43589743589744, | |
| "grad_norm": 18.388671875, | |
| "learning_rate": 9.271000000000002e-06, | |
| "loss": 1.1929, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 37.43589743589744, | |
| "eval_loss": 1.2051817178726196, | |
| "eval_runtime": 33.7433, | |
| "eval_samples_per_second": 11.647, | |
| "eval_steps_per_second": 1.482, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 37.94871794871795, | |
| "grad_norm": 36.36753463745117, | |
| "learning_rate": 9.261000000000002e-06, | |
| "loss": 1.1365, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 37.94871794871795, | |
| "eval_loss": 1.1993858814239502, | |
| "eval_runtime": 33.7824, | |
| "eval_samples_per_second": 11.633, | |
| "eval_steps_per_second": 1.48, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 38.46153846153846, | |
| "grad_norm": 31.875085830688477, | |
| "learning_rate": 9.251000000000002e-06, | |
| "loss": 1.1455, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 38.46153846153846, | |
| "eval_loss": 1.209811806678772, | |
| "eval_runtime": 33.938, | |
| "eval_samples_per_second": 11.58, | |
| "eval_steps_per_second": 1.473, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 38.97435897435897, | |
| "grad_norm": 30.268564224243164, | |
| "learning_rate": 9.241000000000002e-06, | |
| "loss": 1.1583, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 38.97435897435897, | |
| "eval_loss": 1.1939027309417725, | |
| "eval_runtime": 33.8431, | |
| "eval_samples_per_second": 11.612, | |
| "eval_steps_per_second": 1.477, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 39.48717948717949, | |
| "grad_norm": 126.68383026123047, | |
| "learning_rate": 9.231000000000002e-06, | |
| "loss": 1.1443, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 39.48717948717949, | |
| "eval_loss": 1.2021498680114746, | |
| "eval_runtime": 33.8224, | |
| "eval_samples_per_second": 11.62, | |
| "eval_steps_per_second": 1.478, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 30.38014793395996, | |
| "learning_rate": 9.221e-06, | |
| "loss": 1.1509, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 1.2058591842651367, | |
| "eval_runtime": 33.7036, | |
| "eval_samples_per_second": 11.66, | |
| "eval_steps_per_second": 1.484, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 40.51282051282051, | |
| "grad_norm": 42.52033996582031, | |
| "learning_rate": 9.211e-06, | |
| "loss": 1.1635, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 40.51282051282051, | |
| "eval_loss": 1.2037510871887207, | |
| "eval_runtime": 33.7516, | |
| "eval_samples_per_second": 11.644, | |
| "eval_steps_per_second": 1.481, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 41.02564102564103, | |
| "grad_norm": 32.66926193237305, | |
| "learning_rate": 9.201e-06, | |
| "loss": 1.132, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 41.02564102564103, | |
| "eval_loss": 1.2147732973098755, | |
| "eval_runtime": 33.9388, | |
| "eval_samples_per_second": 11.58, | |
| "eval_steps_per_second": 1.473, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 41.53846153846154, | |
| "grad_norm": 42.2666130065918, | |
| "learning_rate": 9.191e-06, | |
| "loss": 1.1688, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 41.53846153846154, | |
| "eval_loss": 1.214206337928772, | |
| "eval_runtime": 33.8017, | |
| "eval_samples_per_second": 11.627, | |
| "eval_steps_per_second": 1.479, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 42.05128205128205, | |
| "grad_norm": 61.25041198730469, | |
| "learning_rate": 9.181e-06, | |
| "loss": 1.1035, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 42.05128205128205, | |
| "eval_loss": 1.1902282238006592, | |
| "eval_runtime": 33.7773, | |
| "eval_samples_per_second": 11.635, | |
| "eval_steps_per_second": 1.48, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 42.56410256410256, | |
| "grad_norm": 42.63145065307617, | |
| "learning_rate": 9.171e-06, | |
| "loss": 1.1429, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 42.56410256410256, | |
| "eval_loss": 1.2035140991210938, | |
| "eval_runtime": 33.7617, | |
| "eval_samples_per_second": 11.64, | |
| "eval_steps_per_second": 1.481, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 43.07692307692308, | |
| "grad_norm": 20.476646423339844, | |
| "learning_rate": 9.161000000000001e-06, | |
| "loss": 1.1663, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 43.07692307692308, | |
| "eval_loss": 1.1914900541305542, | |
| "eval_runtime": 33.9898, | |
| "eval_samples_per_second": 11.562, | |
| "eval_steps_per_second": 1.471, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 43.58974358974359, | |
| "grad_norm": 36.54648971557617, | |
| "learning_rate": 9.151000000000001e-06, | |
| "loss": 1.1096, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 43.58974358974359, | |
| "eval_loss": 1.183597207069397, | |
| "eval_runtime": 33.897, | |
| "eval_samples_per_second": 11.594, | |
| "eval_steps_per_second": 1.475, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 44.1025641025641, | |
| "grad_norm": 44.22875213623047, | |
| "learning_rate": 9.141000000000001e-06, | |
| "loss": 1.1497, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 44.1025641025641, | |
| "eval_loss": 1.1925466060638428, | |
| "eval_runtime": 33.8189, | |
| "eval_samples_per_second": 11.621, | |
| "eval_steps_per_second": 1.478, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 44.61538461538461, | |
| "grad_norm": 42.943180084228516, | |
| "learning_rate": 9.131000000000001e-06, | |
| "loss": 1.104, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 44.61538461538461, | |
| "eval_loss": 1.1945114135742188, | |
| "eval_runtime": 33.8565, | |
| "eval_samples_per_second": 11.608, | |
| "eval_steps_per_second": 1.477, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 45.12820512820513, | |
| "grad_norm": 21.709800720214844, | |
| "learning_rate": 9.121000000000001e-06, | |
| "loss": 1.1303, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 45.12820512820513, | |
| "eval_loss": 1.1883279085159302, | |
| "eval_runtime": 33.8145, | |
| "eval_samples_per_second": 11.622, | |
| "eval_steps_per_second": 1.479, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 45.64102564102564, | |
| "grad_norm": 34.65962219238281, | |
| "learning_rate": 9.1111e-06, | |
| "loss": 1.1347, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 45.64102564102564, | |
| "eval_loss": 1.1927034854888916, | |
| "eval_runtime": 34.2072, | |
| "eval_samples_per_second": 11.489, | |
| "eval_steps_per_second": 1.462, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "grad_norm": 31.94856071472168, | |
| "learning_rate": 9.1011e-06, | |
| "loss": 1.1077, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 46.15384615384615, | |
| "eval_loss": 1.185064673423767, | |
| "eval_runtime": 33.9549, | |
| "eval_samples_per_second": 11.574, | |
| "eval_steps_per_second": 1.473, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 46.666666666666664, | |
| "grad_norm": 42.5874137878418, | |
| "learning_rate": 9.0911e-06, | |
| "loss": 1.124, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 46.666666666666664, | |
| "eval_loss": 1.186991572380066, | |
| "eval_runtime": 33.9527, | |
| "eval_samples_per_second": 11.575, | |
| "eval_steps_per_second": 1.473, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 47.17948717948718, | |
| "grad_norm": 28.342052459716797, | |
| "learning_rate": 9.0811e-06, | |
| "loss": 1.12, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 47.17948717948718, | |
| "eval_loss": 1.1799968481063843, | |
| "eval_runtime": 34.1077, | |
| "eval_samples_per_second": 11.522, | |
| "eval_steps_per_second": 1.466, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 47.69230769230769, | |
| "grad_norm": 18.034202575683594, | |
| "learning_rate": 9.0711e-06, | |
| "loss": 1.1023, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 47.69230769230769, | |
| "eval_loss": 1.1863212585449219, | |
| "eval_runtime": 33.8209, | |
| "eval_samples_per_second": 11.62, | |
| "eval_steps_per_second": 1.478, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 48.205128205128204, | |
| "grad_norm": 18.521087646484375, | |
| "learning_rate": 9.0611e-06, | |
| "loss": 1.1776, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 48.205128205128204, | |
| "eval_loss": 1.1852102279663086, | |
| "eval_runtime": 33.8724, | |
| "eval_samples_per_second": 11.602, | |
| "eval_steps_per_second": 1.476, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 48.717948717948715, | |
| "grad_norm": 54.735145568847656, | |
| "learning_rate": 9.0511e-06, | |
| "loss": 1.1108, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 48.717948717948715, | |
| "eval_loss": 1.1690032482147217, | |
| "eval_runtime": 33.7943, | |
| "eval_samples_per_second": 11.629, | |
| "eval_steps_per_second": 1.48, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 49.23076923076923, | |
| "grad_norm": 24.619985580444336, | |
| "learning_rate": 9.0411e-06, | |
| "loss": 1.1173, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 49.23076923076923, | |
| "eval_loss": 1.1739821434020996, | |
| "eval_runtime": 33.8187, | |
| "eval_samples_per_second": 11.621, | |
| "eval_steps_per_second": 1.478, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 49.743589743589745, | |
| "grad_norm": 27.19590950012207, | |
| "learning_rate": 9.0311e-06, | |
| "loss": 1.0959, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 49.743589743589745, | |
| "eval_loss": 1.1569674015045166, | |
| "eval_runtime": 33.8966, | |
| "eval_samples_per_second": 11.594, | |
| "eval_steps_per_second": 1.475, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 50.256410256410255, | |
| "grad_norm": 66.81871032714844, | |
| "learning_rate": 9.0211e-06, | |
| "loss": 1.1213, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 50.256410256410255, | |
| "eval_loss": 1.1669386625289917, | |
| "eval_runtime": 33.9461, | |
| "eval_samples_per_second": 11.577, | |
| "eval_steps_per_second": 1.473, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 50.76923076923077, | |
| "grad_norm": 20.71648406982422, | |
| "learning_rate": 9.011100000000001e-06, | |
| "loss": 1.0801, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 50.76923076923077, | |
| "eval_loss": 1.1752002239227295, | |
| "eval_runtime": 33.6927, | |
| "eval_samples_per_second": 11.664, | |
| "eval_steps_per_second": 1.484, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 51.282051282051285, | |
| "grad_norm": 27.14691925048828, | |
| "learning_rate": 9.001100000000001e-06, | |
| "loss": 1.1269, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 51.282051282051285, | |
| "eval_loss": 1.1753243207931519, | |
| "eval_runtime": 33.7905, | |
| "eval_samples_per_second": 11.63, | |
| "eval_steps_per_second": 1.48, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 51.794871794871796, | |
| "grad_norm": 16.967599868774414, | |
| "learning_rate": 8.991100000000001e-06, | |
| "loss": 1.0956, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 51.794871794871796, | |
| "eval_loss": 1.1728534698486328, | |
| "eval_runtime": 33.9831, | |
| "eval_samples_per_second": 11.565, | |
| "eval_steps_per_second": 1.471, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 52.30769230769231, | |
| "grad_norm": 25.84881019592285, | |
| "learning_rate": 8.981100000000001e-06, | |
| "loss": 1.1034, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 52.30769230769231, | |
| "eval_loss": 1.1675057411193848, | |
| "eval_runtime": 33.8047, | |
| "eval_samples_per_second": 11.626, | |
| "eval_steps_per_second": 1.479, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 52.82051282051282, | |
| "grad_norm": 27.911279678344727, | |
| "learning_rate": 8.9711e-06, | |
| "loss": 1.1109, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 52.82051282051282, | |
| "eval_loss": 1.1695001125335693, | |
| "eval_runtime": 33.9411, | |
| "eval_samples_per_second": 11.579, | |
| "eval_steps_per_second": 1.473, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 53.333333333333336, | |
| "grad_norm": 30.883014678955078, | |
| "learning_rate": 8.9611e-06, | |
| "loss": 1.0748, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 53.333333333333336, | |
| "eval_loss": 1.166171908378601, | |
| "eval_runtime": 33.7307, | |
| "eval_samples_per_second": 11.651, | |
| "eval_steps_per_second": 1.482, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 53.84615384615385, | |
| "grad_norm": 30.53699493408203, | |
| "learning_rate": 8.9511e-06, | |
| "loss": 1.1039, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 53.84615384615385, | |
| "eval_loss": 1.1673123836517334, | |
| "eval_runtime": 33.8942, | |
| "eval_samples_per_second": 11.595, | |
| "eval_steps_per_second": 1.475, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 54.35897435897436, | |
| "grad_norm": 32.961483001708984, | |
| "learning_rate": 8.9411e-06, | |
| "loss": 1.1203, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 54.35897435897436, | |
| "eval_loss": 1.1615757942199707, | |
| "eval_runtime": 33.9176, | |
| "eval_samples_per_second": 11.587, | |
| "eval_steps_per_second": 1.474, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 54.87179487179487, | |
| "grad_norm": 26.77215003967285, | |
| "learning_rate": 8.9311e-06, | |
| "loss": 1.1109, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 54.87179487179487, | |
| "eval_loss": 1.1798686981201172, | |
| "eval_runtime": 34.1898, | |
| "eval_samples_per_second": 11.495, | |
| "eval_steps_per_second": 1.462, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 55.38461538461539, | |
| "grad_norm": 42.99930191040039, | |
| "learning_rate": 8.9211e-06, | |
| "loss": 1.0651, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 55.38461538461539, | |
| "eval_loss": 1.1585968732833862, | |
| "eval_runtime": 33.9129, | |
| "eval_samples_per_second": 11.589, | |
| "eval_steps_per_second": 1.474, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 55.8974358974359, | |
| "grad_norm": 22.420515060424805, | |
| "learning_rate": 8.9111e-06, | |
| "loss": 1.0901, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 55.8974358974359, | |
| "eval_loss": 1.182327151298523, | |
| "eval_runtime": 34.0546, | |
| "eval_samples_per_second": 11.54, | |
| "eval_steps_per_second": 1.468, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 56.41025641025641, | |
| "grad_norm": 34.271324157714844, | |
| "learning_rate": 8.9011e-06, | |
| "loss": 1.0969, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 56.41025641025641, | |
| "eval_loss": 1.1700419187545776, | |
| "eval_runtime": 34.0913, | |
| "eval_samples_per_second": 11.528, | |
| "eval_steps_per_second": 1.467, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 56.92307692307692, | |
| "grad_norm": 25.083974838256836, | |
| "learning_rate": 8.8911e-06, | |
| "loss": 1.0825, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 56.92307692307692, | |
| "eval_loss": 1.1617279052734375, | |
| "eval_runtime": 33.9494, | |
| "eval_samples_per_second": 11.576, | |
| "eval_steps_per_second": 1.473, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 57.43589743589744, | |
| "grad_norm": 45.67741012573242, | |
| "learning_rate": 8.8811e-06, | |
| "loss": 1.1105, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 57.43589743589744, | |
| "eval_loss": 1.1558475494384766, | |
| "eval_runtime": 33.8739, | |
| "eval_samples_per_second": 11.602, | |
| "eval_steps_per_second": 1.476, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 57.94871794871795, | |
| "grad_norm": 40.9770622253418, | |
| "learning_rate": 8.8711e-06, | |
| "loss": 1.0714, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 57.94871794871795, | |
| "eval_loss": 1.158663272857666, | |
| "eval_runtime": 33.8651, | |
| "eval_samples_per_second": 11.605, | |
| "eval_steps_per_second": 1.476, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 58.46153846153846, | |
| "grad_norm": 26.5457763671875, | |
| "learning_rate": 8.8611e-06, | |
| "loss": 1.053, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 58.46153846153846, | |
| "eval_loss": 1.1581999063491821, | |
| "eval_runtime": 33.9299, | |
| "eval_samples_per_second": 11.583, | |
| "eval_steps_per_second": 1.474, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 58.97435897435897, | |
| "grad_norm": 21.226743698120117, | |
| "learning_rate": 8.8511e-06, | |
| "loss": 1.1005, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 58.97435897435897, | |
| "eval_loss": 1.1427479982376099, | |
| "eval_runtime": 33.8652, | |
| "eval_samples_per_second": 11.605, | |
| "eval_steps_per_second": 1.476, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 59.48717948717949, | |
| "grad_norm": 35.32261657714844, | |
| "learning_rate": 8.8411e-06, | |
| "loss": 1.1142, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 59.48717948717949, | |
| "eval_loss": 1.1504665613174438, | |
| "eval_runtime": 33.9719, | |
| "eval_samples_per_second": 11.568, | |
| "eval_steps_per_second": 1.472, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 62.73653793334961, | |
| "learning_rate": 8.831200000000001e-06, | |
| "loss": 1.0317, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_loss": 1.166619896888733, | |
| "eval_runtime": 33.7919, | |
| "eval_samples_per_second": 11.63, | |
| "eval_steps_per_second": 1.48, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 60.51282051282051, | |
| "grad_norm": 32.88017654418945, | |
| "learning_rate": 8.821200000000001e-06, | |
| "loss": 1.053, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 60.51282051282051, | |
| "eval_loss": 1.151050090789795, | |
| "eval_runtime": 33.8088, | |
| "eval_samples_per_second": 11.624, | |
| "eval_steps_per_second": 1.479, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 61.02564102564103, | |
| "grad_norm": 25.249664306640625, | |
| "learning_rate": 8.811200000000001e-06, | |
| "loss": 1.083, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 61.02564102564103, | |
| "eval_loss": 1.1466352939605713, | |
| "eval_runtime": 33.7084, | |
| "eval_samples_per_second": 11.659, | |
| "eval_steps_per_second": 1.483, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 61.53846153846154, | |
| "grad_norm": 25.186697006225586, | |
| "learning_rate": 8.801200000000001e-06, | |
| "loss": 1.023, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 61.53846153846154, | |
| "eval_loss": 1.1523329019546509, | |
| "eval_runtime": 33.8963, | |
| "eval_samples_per_second": 11.594, | |
| "eval_steps_per_second": 1.475, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 62.05128205128205, | |
| "grad_norm": 65.74333953857422, | |
| "learning_rate": 8.791200000000001e-06, | |
| "loss": 1.1023, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 62.05128205128205, | |
| "eval_loss": 1.1539132595062256, | |
| "eval_runtime": 33.8501, | |
| "eval_samples_per_second": 11.61, | |
| "eval_steps_per_second": 1.477, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 62.56410256410256, | |
| "grad_norm": 37.643035888671875, | |
| "learning_rate": 8.781200000000002e-06, | |
| "loss": 1.096, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 62.56410256410256, | |
| "eval_loss": 1.1323292255401611, | |
| "eval_runtime": 33.9504, | |
| "eval_samples_per_second": 11.576, | |
| "eval_steps_per_second": 1.473, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 63.07692307692308, | |
| "grad_norm": 41.54033279418945, | |
| "learning_rate": 8.7712e-06, | |
| "loss": 1.04, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 63.07692307692308, | |
| "eval_loss": 1.1349562406539917, | |
| "eval_runtime": 33.8242, | |
| "eval_samples_per_second": 11.619, | |
| "eval_steps_per_second": 1.478, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 63.58974358974359, | |
| "grad_norm": 32.337890625, | |
| "learning_rate": 8.7612e-06, | |
| "loss": 1.0729, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 63.58974358974359, | |
| "eval_loss": 1.1326929330825806, | |
| "eval_runtime": 33.7768, | |
| "eval_samples_per_second": 11.635, | |
| "eval_steps_per_second": 1.48, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 64.1025641025641, | |
| "grad_norm": 32.026912689208984, | |
| "learning_rate": 8.7512e-06, | |
| "loss": 1.0467, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 64.1025641025641, | |
| "eval_loss": 1.13288414478302, | |
| "eval_runtime": 34.2235, | |
| "eval_samples_per_second": 11.483, | |
| "eval_steps_per_second": 1.461, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 64.61538461538461, | |
| "grad_norm": 17.785661697387695, | |
| "learning_rate": 8.7412e-06, | |
| "loss": 1.0339, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 64.61538461538461, | |
| "eval_loss": 1.1395562887191772, | |
| "eval_runtime": 33.752, | |
| "eval_samples_per_second": 11.644, | |
| "eval_steps_per_second": 1.481, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 65.12820512820512, | |
| "grad_norm": 30.277780532836914, | |
| "learning_rate": 8.7312e-06, | |
| "loss": 1.0828, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 65.12820512820512, | |
| "eval_loss": 1.1387863159179688, | |
| "eval_runtime": 33.8766, | |
| "eval_samples_per_second": 11.601, | |
| "eval_steps_per_second": 1.476, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 65.64102564102564, | |
| "grad_norm": 41.21147918701172, | |
| "learning_rate": 8.7212e-06, | |
| "loss": 1.0502, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 65.64102564102564, | |
| "eval_loss": 1.143326997756958, | |
| "eval_runtime": 33.9279, | |
| "eval_samples_per_second": 11.583, | |
| "eval_steps_per_second": 1.474, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 66.15384615384616, | |
| "grad_norm": 12.04747486114502, | |
| "learning_rate": 8.7112e-06, | |
| "loss": 1.0099, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 66.15384615384616, | |
| "eval_loss": 1.130028247833252, | |
| "eval_runtime": 33.9548, | |
| "eval_samples_per_second": 11.574, | |
| "eval_steps_per_second": 1.473, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 66.66666666666667, | |
| "grad_norm": 46.18159866333008, | |
| "learning_rate": 8.7012e-06, | |
| "loss": 1.026, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 66.66666666666667, | |
| "eval_loss": 1.135296106338501, | |
| "eval_runtime": 33.8939, | |
| "eval_samples_per_second": 11.595, | |
| "eval_steps_per_second": 1.475, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 67.17948717948718, | |
| "grad_norm": 34.04996109008789, | |
| "learning_rate": 8.6912e-06, | |
| "loss": 1.0969, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 67.17948717948718, | |
| "eval_loss": 1.1394113302230835, | |
| "eval_runtime": 33.7863, | |
| "eval_samples_per_second": 11.632, | |
| "eval_steps_per_second": 1.48, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 67.6923076923077, | |
| "grad_norm": 57.76072692871094, | |
| "learning_rate": 8.6812e-06, | |
| "loss": 1.0345, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 67.6923076923077, | |
| "eval_loss": 1.1415585279464722, | |
| "eval_runtime": 33.8137, | |
| "eval_samples_per_second": 11.622, | |
| "eval_steps_per_second": 1.479, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 68.2051282051282, | |
| "grad_norm": 26.72646713256836, | |
| "learning_rate": 8.671200000000001e-06, | |
| "loss": 1.0679, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 68.2051282051282, | |
| "eval_loss": 1.140710473060608, | |
| "eval_runtime": 34.6101, | |
| "eval_samples_per_second": 11.355, | |
| "eval_steps_per_second": 1.445, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 68.71794871794872, | |
| "grad_norm": 48.05488586425781, | |
| "learning_rate": 8.661200000000001e-06, | |
| "loss": 1.0037, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 68.71794871794872, | |
| "eval_loss": 1.1428287029266357, | |
| "eval_runtime": 34.2239, | |
| "eval_samples_per_second": 11.483, | |
| "eval_steps_per_second": 1.461, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 69.23076923076923, | |
| "grad_norm": 15.574548721313477, | |
| "learning_rate": 8.651200000000001e-06, | |
| "loss": 1.0348, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 69.23076923076923, | |
| "eval_loss": 1.1325479745864868, | |
| "eval_runtime": 34.131, | |
| "eval_samples_per_second": 11.514, | |
| "eval_steps_per_second": 1.465, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 69.74358974358974, | |
| "grad_norm": 52.864234924316406, | |
| "learning_rate": 8.641200000000001e-06, | |
| "loss": 1.0529, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 69.74358974358974, | |
| "eval_loss": 1.126291036605835, | |
| "eval_runtime": 34.0945, | |
| "eval_samples_per_second": 11.527, | |
| "eval_steps_per_second": 1.467, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 70.25641025641026, | |
| "grad_norm": 43.43352127075195, | |
| "learning_rate": 8.631200000000001e-06, | |
| "loss": 1.0605, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 70.25641025641026, | |
| "eval_loss": 1.129713773727417, | |
| "eval_runtime": 33.9866, | |
| "eval_samples_per_second": 11.563, | |
| "eval_steps_per_second": 1.471, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 70.76923076923077, | |
| "grad_norm": 26.118932723999023, | |
| "learning_rate": 8.621200000000001e-06, | |
| "loss": 1.0422, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 70.76923076923077, | |
| "eval_loss": 1.130542278289795, | |
| "eval_runtime": 33.9346, | |
| "eval_samples_per_second": 11.581, | |
| "eval_steps_per_second": 1.473, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 71.28205128205128, | |
| "grad_norm": 37.925621032714844, | |
| "learning_rate": 8.611200000000002e-06, | |
| "loss": 1.0397, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 71.28205128205128, | |
| "eval_loss": 1.141406536102295, | |
| "eval_runtime": 34.0654, | |
| "eval_samples_per_second": 11.537, | |
| "eval_steps_per_second": 1.468, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 71.7948717948718, | |
| "grad_norm": 62.41912078857422, | |
| "learning_rate": 8.6012e-06, | |
| "loss": 1.0287, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 71.7948717948718, | |
| "eval_loss": 1.131140112876892, | |
| "eval_runtime": 33.9622, | |
| "eval_samples_per_second": 11.572, | |
| "eval_steps_per_second": 1.472, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 72.3076923076923, | |
| "grad_norm": 23.217283248901367, | |
| "learning_rate": 8.5912e-06, | |
| "loss": 1.0324, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 72.3076923076923, | |
| "eval_loss": 1.1330175399780273, | |
| "eval_runtime": 33.8419, | |
| "eval_samples_per_second": 11.613, | |
| "eval_steps_per_second": 1.477, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 72.82051282051282, | |
| "grad_norm": 32.80116271972656, | |
| "learning_rate": 8.5812e-06, | |
| "loss": 1.0388, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 72.82051282051282, | |
| "eval_loss": 1.1305664777755737, | |
| "eval_runtime": 33.8519, | |
| "eval_samples_per_second": 11.609, | |
| "eval_steps_per_second": 1.477, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 73.33333333333333, | |
| "grad_norm": 82.27204132080078, | |
| "learning_rate": 8.5712e-06, | |
| "loss": 1.0258, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 73.33333333333333, | |
| "eval_loss": 1.131137728691101, | |
| "eval_runtime": 33.915, | |
| "eval_samples_per_second": 11.588, | |
| "eval_steps_per_second": 1.474, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 73.84615384615384, | |
| "grad_norm": 81.36099243164062, | |
| "learning_rate": 8.5612e-06, | |
| "loss": 1.0176, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 73.84615384615384, | |
| "eval_loss": 1.1416622400283813, | |
| "eval_runtime": 34.0376, | |
| "eval_samples_per_second": 11.546, | |
| "eval_steps_per_second": 1.469, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 74.35897435897436, | |
| "grad_norm": 72.8280258178711, | |
| "learning_rate": 8.5512e-06, | |
| "loss": 1.0269, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 74.35897435897436, | |
| "eval_loss": 1.1399762630462646, | |
| "eval_runtime": 33.8029, | |
| "eval_samples_per_second": 11.626, | |
| "eval_steps_per_second": 1.479, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 74.87179487179488, | |
| "grad_norm": 31.938396453857422, | |
| "learning_rate": 8.5412e-06, | |
| "loss": 1.0038, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 74.87179487179488, | |
| "eval_loss": 1.1206576824188232, | |
| "eval_runtime": 33.7774, | |
| "eval_samples_per_second": 11.635, | |
| "eval_steps_per_second": 1.48, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 75.38461538461539, | |
| "grad_norm": 41.431663513183594, | |
| "learning_rate": 8.5312e-06, | |
| "loss": 1.028, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 75.38461538461539, | |
| "eval_loss": 1.1250663995742798, | |
| "eval_runtime": 33.8079, | |
| "eval_samples_per_second": 11.624, | |
| "eval_steps_per_second": 1.479, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 75.8974358974359, | |
| "grad_norm": 32.541805267333984, | |
| "learning_rate": 8.5212e-06, | |
| "loss": 1.0191, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 75.8974358974359, | |
| "eval_loss": 1.1266955137252808, | |
| "eval_runtime": 33.9427, | |
| "eval_samples_per_second": 11.578, | |
| "eval_steps_per_second": 1.473, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 76.41025641025641, | |
| "grad_norm": 28.85361671447754, | |
| "learning_rate": 8.5112e-06, | |
| "loss": 1.045, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 76.41025641025641, | |
| "eval_loss": 1.1317839622497559, | |
| "eval_runtime": 33.8219, | |
| "eval_samples_per_second": 11.62, | |
| "eval_steps_per_second": 1.478, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 76.92307692307692, | |
| "grad_norm": 22.870845794677734, | |
| "learning_rate": 8.501200000000001e-06, | |
| "loss": 0.9832, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 76.92307692307692, | |
| "eval_loss": 1.1070276498794556, | |
| "eval_runtime": 33.8987, | |
| "eval_samples_per_second": 11.593, | |
| "eval_steps_per_second": 1.475, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 77.43589743589743, | |
| "grad_norm": 18.483102798461914, | |
| "learning_rate": 8.491200000000001e-06, | |
| "loss": 1.0155, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 77.43589743589743, | |
| "eval_loss": 1.10912024974823, | |
| "eval_runtime": 33.8107, | |
| "eval_samples_per_second": 11.624, | |
| "eval_steps_per_second": 1.479, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 77.94871794871794, | |
| "grad_norm": 19.445619583129883, | |
| "learning_rate": 8.481200000000001e-06, | |
| "loss": 1.0398, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 77.94871794871794, | |
| "eval_loss": 1.1232614517211914, | |
| "eval_runtime": 33.8148, | |
| "eval_samples_per_second": 11.622, | |
| "eval_steps_per_second": 1.479, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 78.46153846153847, | |
| "grad_norm": 18.695117950439453, | |
| "learning_rate": 8.471300000000001e-06, | |
| "loss": 1.0403, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 78.46153846153847, | |
| "eval_loss": 1.1138592958450317, | |
| "eval_runtime": 33.6752, | |
| "eval_samples_per_second": 11.67, | |
| "eval_steps_per_second": 1.485, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 78.97435897435898, | |
| "grad_norm": 44.09070587158203, | |
| "learning_rate": 8.461300000000001e-06, | |
| "loss": 0.9847, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 78.97435897435898, | |
| "eval_loss": 1.1114585399627686, | |
| "eval_runtime": 33.7907, | |
| "eval_samples_per_second": 11.63, | |
| "eval_steps_per_second": 1.48, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 79.48717948717949, | |
| "grad_norm": 49.75135040283203, | |
| "learning_rate": 8.451300000000002e-06, | |
| "loss": 1.0351, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 79.48717948717949, | |
| "eval_loss": 1.1093136072158813, | |
| "eval_runtime": 33.8604, | |
| "eval_samples_per_second": 11.606, | |
| "eval_steps_per_second": 1.477, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 32.891754150390625, | |
| "learning_rate": 8.441300000000002e-06, | |
| "loss": 0.9776, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 1.1244064569473267, | |
| "eval_runtime": 33.8414, | |
| "eval_samples_per_second": 11.613, | |
| "eval_steps_per_second": 1.477, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 80.51282051282051, | |
| "grad_norm": 19.692750930786133, | |
| "learning_rate": 8.431300000000002e-06, | |
| "loss": 0.9815, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 80.51282051282051, | |
| "eval_loss": 1.1285768747329712, | |
| "eval_runtime": 33.7284, | |
| "eval_samples_per_second": 11.652, | |
| "eval_steps_per_second": 1.482, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 81.02564102564102, | |
| "grad_norm": 46.99306869506836, | |
| "learning_rate": 8.421300000000002e-06, | |
| "loss": 1.0426, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 81.02564102564102, | |
| "eval_loss": 1.1372685432434082, | |
| "eval_runtime": 33.7726, | |
| "eval_samples_per_second": 11.637, | |
| "eval_steps_per_second": 1.48, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 81.53846153846153, | |
| "grad_norm": 19.263620376586914, | |
| "learning_rate": 8.411300000000002e-06, | |
| "loss": 0.9906, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 81.53846153846153, | |
| "eval_loss": 1.1213167905807495, | |
| "eval_runtime": 33.8885, | |
| "eval_samples_per_second": 11.597, | |
| "eval_steps_per_second": 1.475, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 82.05128205128206, | |
| "grad_norm": 19.580486297607422, | |
| "learning_rate": 8.4013e-06, | |
| "loss": 1.0321, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 82.05128205128206, | |
| "eval_loss": 1.1251707077026367, | |
| "eval_runtime": 33.7214, | |
| "eval_samples_per_second": 11.654, | |
| "eval_steps_per_second": 1.483, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 82.56410256410257, | |
| "grad_norm": 18.83529281616211, | |
| "learning_rate": 8.3913e-06, | |
| "loss": 1.0043, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 82.56410256410257, | |
| "eval_loss": 1.1074498891830444, | |
| "eval_runtime": 34.0109, | |
| "eval_samples_per_second": 11.555, | |
| "eval_steps_per_second": 1.47, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 83.07692307692308, | |
| "grad_norm": 16.603994369506836, | |
| "learning_rate": 8.3813e-06, | |
| "loss": 0.9935, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 83.07692307692308, | |
| "eval_loss": 1.1357744932174683, | |
| "eval_runtime": 33.9144, | |
| "eval_samples_per_second": 11.588, | |
| "eval_steps_per_second": 1.474, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 83.58974358974359, | |
| "grad_norm": 33.002960205078125, | |
| "learning_rate": 8.3713e-06, | |
| "loss": 0.9659, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 83.58974358974359, | |
| "eval_loss": 1.1160190105438232, | |
| "eval_runtime": 34.0015, | |
| "eval_samples_per_second": 11.558, | |
| "eval_steps_per_second": 1.471, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 84.1025641025641, | |
| "grad_norm": 37.87334060668945, | |
| "learning_rate": 8.3613e-06, | |
| "loss": 0.987, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 84.1025641025641, | |
| "eval_loss": 1.1338489055633545, | |
| "eval_runtime": 33.8043, | |
| "eval_samples_per_second": 11.626, | |
| "eval_steps_per_second": 1.479, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 84.61538461538461, | |
| "grad_norm": 29.907007217407227, | |
| "learning_rate": 8.3513e-06, | |
| "loss": 1.0051, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 84.61538461538461, | |
| "eval_loss": 1.1136332750320435, | |
| "eval_runtime": 33.6613, | |
| "eval_samples_per_second": 11.675, | |
| "eval_steps_per_second": 1.485, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 85.12820512820512, | |
| "grad_norm": 29.1041259765625, | |
| "learning_rate": 8.341300000000001e-06, | |
| "loss": 1.0379, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 85.12820512820512, | |
| "eval_loss": 1.1357380151748657, | |
| "eval_runtime": 33.7783, | |
| "eval_samples_per_second": 11.635, | |
| "eval_steps_per_second": 1.48, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 85.64102564102564, | |
| "grad_norm": 36.248313903808594, | |
| "learning_rate": 8.331400000000001e-06, | |
| "loss": 1.0121, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 85.64102564102564, | |
| "eval_loss": 1.1128472089767456, | |
| "eval_runtime": 33.7439, | |
| "eval_samples_per_second": 11.647, | |
| "eval_steps_per_second": 1.482, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 86.15384615384616, | |
| "grad_norm": 25.37560272216797, | |
| "learning_rate": 8.321400000000001e-06, | |
| "loss": 0.9787, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 86.15384615384616, | |
| "eval_loss": 1.1043667793273926, | |
| "eval_runtime": 34.15, | |
| "eval_samples_per_second": 11.508, | |
| "eval_steps_per_second": 1.464, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 86.66666666666667, | |
| "grad_norm": 16.18814468383789, | |
| "learning_rate": 8.3114e-06, | |
| "loss": 0.9772, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 86.66666666666667, | |
| "eval_loss": 1.1302591562271118, | |
| "eval_runtime": 33.755, | |
| "eval_samples_per_second": 11.643, | |
| "eval_steps_per_second": 1.481, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 87.17948717948718, | |
| "grad_norm": 31.982431411743164, | |
| "learning_rate": 8.3014e-06, | |
| "loss": 0.9904, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 87.17948717948718, | |
| "eval_loss": 1.1226387023925781, | |
| "eval_runtime": 33.8382, | |
| "eval_samples_per_second": 11.614, | |
| "eval_steps_per_second": 1.478, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 87.6923076923077, | |
| "grad_norm": 37.292362213134766, | |
| "learning_rate": 8.2914e-06, | |
| "loss": 0.9413, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 87.6923076923077, | |
| "eval_loss": 1.1049525737762451, | |
| "eval_runtime": 33.7667, | |
| "eval_samples_per_second": 11.639, | |
| "eval_steps_per_second": 1.481, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 88.2051282051282, | |
| "grad_norm": 28.432649612426758, | |
| "learning_rate": 8.2814e-06, | |
| "loss": 1.0127, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 88.2051282051282, | |
| "eval_loss": 1.1197983026504517, | |
| "eval_runtime": 33.7266, | |
| "eval_samples_per_second": 11.653, | |
| "eval_steps_per_second": 1.483, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 88.71794871794872, | |
| "grad_norm": 34.415977478027344, | |
| "learning_rate": 8.2714e-06, | |
| "loss": 0.9891, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 88.71794871794872, | |
| "eval_loss": 1.1233532428741455, | |
| "eval_runtime": 33.9939, | |
| "eval_samples_per_second": 11.561, | |
| "eval_steps_per_second": 1.471, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 89.23076923076923, | |
| "grad_norm": 22.9134521484375, | |
| "learning_rate": 8.2614e-06, | |
| "loss": 0.9868, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 89.23076923076923, | |
| "eval_loss": 1.1397521495819092, | |
| "eval_runtime": 33.9535, | |
| "eval_samples_per_second": 11.575, | |
| "eval_steps_per_second": 1.473, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 89.74358974358974, | |
| "grad_norm": 26.470407485961914, | |
| "learning_rate": 8.2514e-06, | |
| "loss": 1.0048, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 89.74358974358974, | |
| "eval_loss": 1.103281855583191, | |
| "eval_runtime": 33.932, | |
| "eval_samples_per_second": 11.582, | |
| "eval_steps_per_second": 1.474, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 90.25641025641026, | |
| "grad_norm": 13.81521987915039, | |
| "learning_rate": 8.2414e-06, | |
| "loss": 0.9952, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 90.25641025641026, | |
| "eval_loss": 1.1103590726852417, | |
| "eval_runtime": 33.8805, | |
| "eval_samples_per_second": 11.6, | |
| "eval_steps_per_second": 1.476, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 90.76923076923077, | |
| "grad_norm": 39.196781158447266, | |
| "learning_rate": 8.2314e-06, | |
| "loss": 0.9787, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 90.76923076923077, | |
| "eval_loss": 1.1147035360336304, | |
| "eval_runtime": 34.0993, | |
| "eval_samples_per_second": 11.525, | |
| "eval_steps_per_second": 1.466, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 91.28205128205128, | |
| "grad_norm": 36.378990173339844, | |
| "learning_rate": 8.2214e-06, | |
| "loss": 0.985, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 91.28205128205128, | |
| "eval_loss": 1.120380163192749, | |
| "eval_runtime": 33.8597, | |
| "eval_samples_per_second": 11.607, | |
| "eval_steps_per_second": 1.477, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 91.7948717948718, | |
| "grad_norm": 29.002111434936523, | |
| "learning_rate": 8.2114e-06, | |
| "loss": 0.9828, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 91.7948717948718, | |
| "eval_loss": 1.1089298725128174, | |
| "eval_runtime": 33.8537, | |
| "eval_samples_per_second": 11.609, | |
| "eval_steps_per_second": 1.477, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 92.3076923076923, | |
| "grad_norm": 20.288036346435547, | |
| "learning_rate": 8.2014e-06, | |
| "loss": 0.966, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 92.3076923076923, | |
| "eval_loss": 1.104116678237915, | |
| "eval_runtime": 33.8513, | |
| "eval_samples_per_second": 11.61, | |
| "eval_steps_per_second": 1.477, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 92.82051282051282, | |
| "grad_norm": 32.15245819091797, | |
| "learning_rate": 8.191400000000001e-06, | |
| "loss": 0.9607, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 92.82051282051282, | |
| "eval_loss": 1.1346195936203003, | |
| "eval_runtime": 33.8192, | |
| "eval_samples_per_second": 11.621, | |
| "eval_steps_per_second": 1.478, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 93.33333333333333, | |
| "grad_norm": 30.35234832763672, | |
| "learning_rate": 8.181400000000001e-06, | |
| "loss": 0.9816, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 93.33333333333333, | |
| "eval_loss": 1.1086933612823486, | |
| "eval_runtime": 33.866, | |
| "eval_samples_per_second": 11.605, | |
| "eval_steps_per_second": 1.476, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 93.84615384615384, | |
| "grad_norm": 84.19772338867188, | |
| "learning_rate": 8.171400000000001e-06, | |
| "loss": 0.9945, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 93.84615384615384, | |
| "eval_loss": 1.1133761405944824, | |
| "eval_runtime": 33.8302, | |
| "eval_samples_per_second": 11.617, | |
| "eval_steps_per_second": 1.478, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 94.35897435897436, | |
| "grad_norm": 93.01074981689453, | |
| "learning_rate": 8.161400000000001e-06, | |
| "loss": 0.9509, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 94.35897435897436, | |
| "eval_loss": 1.0900119543075562, | |
| "eval_runtime": 33.8482, | |
| "eval_samples_per_second": 11.611, | |
| "eval_steps_per_second": 1.477, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 94.87179487179488, | |
| "grad_norm": 33.34095001220703, | |
| "learning_rate": 8.1514e-06, | |
| "loss": 0.9695, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 94.87179487179488, | |
| "eval_loss": 1.0987663269042969, | |
| "eval_runtime": 34.0189, | |
| "eval_samples_per_second": 11.552, | |
| "eval_steps_per_second": 1.47, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 95.38461538461539, | |
| "grad_norm": 40.531585693359375, | |
| "learning_rate": 8.1414e-06, | |
| "loss": 0.9567, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 95.38461538461539, | |
| "eval_loss": 1.1120296716690063, | |
| "eval_runtime": 33.8468, | |
| "eval_samples_per_second": 11.611, | |
| "eval_steps_per_second": 1.477, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 95.8974358974359, | |
| "grad_norm": 20.810407638549805, | |
| "learning_rate": 8.1314e-06, | |
| "loss": 1.0048, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 95.8974358974359, | |
| "eval_loss": 1.1099683046340942, | |
| "eval_runtime": 33.8925, | |
| "eval_samples_per_second": 11.595, | |
| "eval_steps_per_second": 1.475, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 96.41025641025641, | |
| "grad_norm": 20.797433853149414, | |
| "learning_rate": 8.1214e-06, | |
| "loss": 0.9339, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 96.41025641025641, | |
| "eval_loss": 1.1000967025756836, | |
| "eval_runtime": 33.8669, | |
| "eval_samples_per_second": 11.604, | |
| "eval_steps_per_second": 1.476, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 96.92307692307692, | |
| "grad_norm": 36.17203140258789, | |
| "learning_rate": 8.1114e-06, | |
| "loss": 0.9502, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 96.92307692307692, | |
| "eval_loss": 1.1125061511993408, | |
| "eval_runtime": 33.8939, | |
| "eval_samples_per_second": 11.595, | |
| "eval_steps_per_second": 1.475, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 97.43589743589743, | |
| "grad_norm": 34.18137741088867, | |
| "learning_rate": 8.1014e-06, | |
| "loss": 0.9115, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 97.43589743589743, | |
| "eval_loss": 1.1053694486618042, | |
| "eval_runtime": 34.1495, | |
| "eval_samples_per_second": 11.508, | |
| "eval_steps_per_second": 1.464, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 97.94871794871794, | |
| "grad_norm": 27.006271362304688, | |
| "learning_rate": 8.0914e-06, | |
| "loss": 0.9906, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 97.94871794871794, | |
| "eval_loss": 1.0994688272476196, | |
| "eval_runtime": 33.8004, | |
| "eval_samples_per_second": 11.627, | |
| "eval_steps_per_second": 1.479, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 98.46153846153847, | |
| "grad_norm": 35.52959442138672, | |
| "learning_rate": 8.0814e-06, | |
| "loss": 0.9616, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 98.46153846153847, | |
| "eval_loss": 1.12260103225708, | |
| "eval_runtime": 33.7133, | |
| "eval_samples_per_second": 11.657, | |
| "eval_steps_per_second": 1.483, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 98.97435897435898, | |
| "grad_norm": 31.87555694580078, | |
| "learning_rate": 8.0714e-06, | |
| "loss": 0.96, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 98.97435897435898, | |
| "eval_loss": 1.1023892164230347, | |
| "eval_runtime": 33.8183, | |
| "eval_samples_per_second": 11.621, | |
| "eval_steps_per_second": 1.478, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 99.48717948717949, | |
| "grad_norm": 39.26782989501953, | |
| "learning_rate": 8.0614e-06, | |
| "loss": 0.9458, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 99.48717948717949, | |
| "eval_loss": 1.1115421056747437, | |
| "eval_runtime": 34.199, | |
| "eval_samples_per_second": 11.492, | |
| "eval_steps_per_second": 1.462, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 52.86429214477539, | |
| "learning_rate": 8.0514e-06, | |
| "loss": 0.9764, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 1.096418857574463, | |
| "eval_runtime": 33.8472, | |
| "eval_samples_per_second": 11.611, | |
| "eval_steps_per_second": 1.477, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 100.51282051282051, | |
| "grad_norm": 25.798358917236328, | |
| "learning_rate": 8.0414e-06, | |
| "loss": 0.9651, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 100.51282051282051, | |
| "eval_loss": 1.0968595743179321, | |
| "eval_runtime": 33.8602, | |
| "eval_samples_per_second": 11.607, | |
| "eval_steps_per_second": 1.477, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 101.02564102564102, | |
| "grad_norm": 25.59754180908203, | |
| "learning_rate": 8.0314e-06, | |
| "loss": 0.9414, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 101.02564102564102, | |
| "eval_loss": 1.1089657545089722, | |
| "eval_runtime": 33.6692, | |
| "eval_samples_per_second": 11.672, | |
| "eval_steps_per_second": 1.485, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 101.53846153846153, | |
| "grad_norm": 38.994361877441406, | |
| "learning_rate": 8.0214e-06, | |
| "loss": 0.9628, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 101.53846153846153, | |
| "eval_loss": 1.085176706314087, | |
| "eval_runtime": 33.7721, | |
| "eval_samples_per_second": 11.637, | |
| "eval_steps_per_second": 1.481, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 102.05128205128206, | |
| "grad_norm": 28.150468826293945, | |
| "learning_rate": 8.011400000000001e-06, | |
| "loss": 0.9321, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 102.05128205128206, | |
| "eval_loss": 1.0919770002365112, | |
| "eval_runtime": 34.0271, | |
| "eval_samples_per_second": 11.55, | |
| "eval_steps_per_second": 1.469, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 102.56410256410257, | |
| "grad_norm": 22.67235565185547, | |
| "learning_rate": 8.001400000000001e-06, | |
| "loss": 0.987, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 102.56410256410257, | |
| "eval_loss": 1.084847092628479, | |
| "eval_runtime": 33.8029, | |
| "eval_samples_per_second": 11.626, | |
| "eval_steps_per_second": 1.479, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 103.07692307692308, | |
| "grad_norm": 23.50147819519043, | |
| "learning_rate": 7.991400000000001e-06, | |
| "loss": 0.9442, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 103.07692307692308, | |
| "eval_loss": 1.0791277885437012, | |
| "eval_runtime": 33.9754, | |
| "eval_samples_per_second": 11.567, | |
| "eval_steps_per_second": 1.472, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 103.58974358974359, | |
| "grad_norm": 28.83344078063965, | |
| "learning_rate": 7.9814e-06, | |
| "loss": 0.9624, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 103.58974358974359, | |
| "eval_loss": 1.0788371562957764, | |
| "eval_runtime": 33.8139, | |
| "eval_samples_per_second": 11.622, | |
| "eval_steps_per_second": 1.479, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 104.1025641025641, | |
| "grad_norm": 23.166961669921875, | |
| "learning_rate": 7.9714e-06, | |
| "loss": 0.9365, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 104.1025641025641, | |
| "eval_loss": 1.0833864212036133, | |
| "eval_runtime": 34.4656, | |
| "eval_samples_per_second": 11.403, | |
| "eval_steps_per_second": 1.451, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 104.61538461538461, | |
| "grad_norm": 43.671165466308594, | |
| "learning_rate": 7.9614e-06, | |
| "loss": 0.9429, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 104.61538461538461, | |
| "eval_loss": 1.0890021324157715, | |
| "eval_runtime": 34.1248, | |
| "eval_samples_per_second": 11.517, | |
| "eval_steps_per_second": 1.465, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 105.12820512820512, | |
| "grad_norm": 19.534181594848633, | |
| "learning_rate": 7.9514e-06, | |
| "loss": 0.9771, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 105.12820512820512, | |
| "eval_loss": 1.0997905731201172, | |
| "eval_runtime": 34.0699, | |
| "eval_samples_per_second": 11.535, | |
| "eval_steps_per_second": 1.468, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 105.64102564102564, | |
| "grad_norm": 15.605002403259277, | |
| "learning_rate": 7.9414e-06, | |
| "loss": 0.947, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 105.64102564102564, | |
| "eval_loss": 1.0916997194290161, | |
| "eval_runtime": 34.057, | |
| "eval_samples_per_second": 11.539, | |
| "eval_steps_per_second": 1.468, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 106.15384615384616, | |
| "grad_norm": 33.188629150390625, | |
| "learning_rate": 7.9314e-06, | |
| "loss": 0.9413, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 106.15384615384616, | |
| "eval_loss": 1.1046770811080933, | |
| "eval_runtime": 33.9382, | |
| "eval_samples_per_second": 11.58, | |
| "eval_steps_per_second": 1.473, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 106.66666666666667, | |
| "grad_norm": 27.891300201416016, | |
| "learning_rate": 7.9214e-06, | |
| "loss": 0.953, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 106.66666666666667, | |
| "eval_loss": 1.1009467840194702, | |
| "eval_runtime": 34.0607, | |
| "eval_samples_per_second": 11.538, | |
| "eval_steps_per_second": 1.468, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 107.17948717948718, | |
| "grad_norm": 27.26763916015625, | |
| "learning_rate": 7.9114e-06, | |
| "loss": 0.9506, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 107.17948717948718, | |
| "eval_loss": 1.0977036952972412, | |
| "eval_runtime": 33.9327, | |
| "eval_samples_per_second": 11.582, | |
| "eval_steps_per_second": 1.474, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 107.6923076923077, | |
| "grad_norm": 21.317838668823242, | |
| "learning_rate": 7.9014e-06, | |
| "loss": 0.9407, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 107.6923076923077, | |
| "eval_loss": 1.1164356470108032, | |
| "eval_runtime": 34.1907, | |
| "eval_samples_per_second": 11.494, | |
| "eval_steps_per_second": 1.462, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 108.2051282051282, | |
| "grad_norm": 24.29534339904785, | |
| "learning_rate": 7.8914e-06, | |
| "loss": 0.9317, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 108.2051282051282, | |
| "eval_loss": 1.0796505212783813, | |
| "eval_runtime": 34.0823, | |
| "eval_samples_per_second": 11.531, | |
| "eval_steps_per_second": 1.467, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 108.71794871794872, | |
| "grad_norm": 23.155261993408203, | |
| "learning_rate": 7.8814e-06, | |
| "loss": 0.9172, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 108.71794871794872, | |
| "eval_loss": 1.1064153909683228, | |
| "eval_runtime": 34.0712, | |
| "eval_samples_per_second": 11.535, | |
| "eval_steps_per_second": 1.468, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 109.23076923076923, | |
| "grad_norm": 102.01934051513672, | |
| "learning_rate": 7.8715e-06, | |
| "loss": 1.006, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 109.23076923076923, | |
| "eval_loss": 1.0971482992172241, | |
| "eval_runtime": 34.0629, | |
| "eval_samples_per_second": 11.537, | |
| "eval_steps_per_second": 1.468, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 109.74358974358974, | |
| "grad_norm": 90.6104965209961, | |
| "learning_rate": 7.861500000000001e-06, | |
| "loss": 0.9273, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 109.74358974358974, | |
| "eval_loss": 1.0784090757369995, | |
| "eval_runtime": 33.9381, | |
| "eval_samples_per_second": 11.58, | |
| "eval_steps_per_second": 1.473, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 110.25641025641026, | |
| "grad_norm": 15.22960090637207, | |
| "learning_rate": 7.851500000000001e-06, | |
| "loss": 0.9306, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 110.25641025641026, | |
| "eval_loss": 1.0971401929855347, | |
| "eval_runtime": 34.1723, | |
| "eval_samples_per_second": 11.501, | |
| "eval_steps_per_second": 1.463, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 110.76923076923077, | |
| "grad_norm": 40.347999572753906, | |
| "learning_rate": 7.841500000000001e-06, | |
| "loss": 0.9607, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 110.76923076923077, | |
| "eval_loss": 1.086938500404358, | |
| "eval_runtime": 33.9506, | |
| "eval_samples_per_second": 11.576, | |
| "eval_steps_per_second": 1.473, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 111.28205128205128, | |
| "grad_norm": 23.18324089050293, | |
| "learning_rate": 7.831500000000001e-06, | |
| "loss": 0.9431, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 111.28205128205128, | |
| "eval_loss": 1.0866228342056274, | |
| "eval_runtime": 34.128, | |
| "eval_samples_per_second": 11.515, | |
| "eval_steps_per_second": 1.465, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 111.7948717948718, | |
| "grad_norm": 49.34690475463867, | |
| "learning_rate": 7.821500000000001e-06, | |
| "loss": 0.9316, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 111.7948717948718, | |
| "eval_loss": 1.0955440998077393, | |
| "eval_runtime": 34.0714, | |
| "eval_samples_per_second": 11.535, | |
| "eval_steps_per_second": 1.468, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 112.3076923076923, | |
| "grad_norm": 45.29327392578125, | |
| "learning_rate": 7.811500000000001e-06, | |
| "loss": 0.9248, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 112.3076923076923, | |
| "eval_loss": 1.0963120460510254, | |
| "eval_runtime": 34.0052, | |
| "eval_samples_per_second": 11.557, | |
| "eval_steps_per_second": 1.47, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 112.82051282051282, | |
| "grad_norm": 29.918447494506836, | |
| "learning_rate": 7.801500000000001e-06, | |
| "loss": 0.929, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 112.82051282051282, | |
| "eval_loss": 1.0954854488372803, | |
| "eval_runtime": 34.4653, | |
| "eval_samples_per_second": 11.403, | |
| "eval_steps_per_second": 1.451, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 113.33333333333333, | |
| "grad_norm": 24.213356018066406, | |
| "learning_rate": 7.791500000000002e-06, | |
| "loss": 0.9472, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 113.33333333333333, | |
| "eval_loss": 1.1072837114334106, | |
| "eval_runtime": 34.0842, | |
| "eval_samples_per_second": 11.53, | |
| "eval_steps_per_second": 1.467, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 113.84615384615384, | |
| "grad_norm": 31.872329711914062, | |
| "learning_rate": 7.7815e-06, | |
| "loss": 0.9149, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 113.84615384615384, | |
| "eval_loss": 1.1297913789749146, | |
| "eval_runtime": 33.9499, | |
| "eval_samples_per_second": 11.576, | |
| "eval_steps_per_second": 1.473, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 114.35897435897436, | |
| "grad_norm": 29.122095108032227, | |
| "learning_rate": 7.7715e-06, | |
| "loss": 0.9373, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 114.35897435897436, | |
| "eval_loss": 1.1010404825210571, | |
| "eval_runtime": 34.038, | |
| "eval_samples_per_second": 11.546, | |
| "eval_steps_per_second": 1.469, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 114.87179487179488, | |
| "grad_norm": 61.661808013916016, | |
| "learning_rate": 7.7615e-06, | |
| "loss": 0.942, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 114.87179487179488, | |
| "eval_loss": 1.1000746488571167, | |
| "eval_runtime": 34.0776, | |
| "eval_samples_per_second": 11.533, | |
| "eval_steps_per_second": 1.467, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 115.38461538461539, | |
| "grad_norm": 32.940059661865234, | |
| "learning_rate": 7.7515e-06, | |
| "loss": 0.9259, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 115.38461538461539, | |
| "eval_loss": 1.0878592729568481, | |
| "eval_runtime": 34.0411, | |
| "eval_samples_per_second": 11.545, | |
| "eval_steps_per_second": 1.469, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 115.8974358974359, | |
| "grad_norm": 24.981050491333008, | |
| "learning_rate": 7.7415e-06, | |
| "loss": 0.9315, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 115.8974358974359, | |
| "eval_loss": 1.071781039237976, | |
| "eval_runtime": 33.9996, | |
| "eval_samples_per_second": 11.559, | |
| "eval_steps_per_second": 1.471, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 116.41025641025641, | |
| "grad_norm": 29.54717254638672, | |
| "learning_rate": 7.7315e-06, | |
| "loss": 0.9141, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 116.41025641025641, | |
| "eval_loss": 1.0897409915924072, | |
| "eval_runtime": 34.0038, | |
| "eval_samples_per_second": 11.558, | |
| "eval_steps_per_second": 1.47, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 116.92307692307692, | |
| "grad_norm": 55.15362548828125, | |
| "learning_rate": 7.7215e-06, | |
| "loss": 0.9504, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 116.92307692307692, | |
| "eval_loss": 1.0998215675354004, | |
| "eval_runtime": 34.1575, | |
| "eval_samples_per_second": 11.506, | |
| "eval_steps_per_second": 1.464, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 117.43589743589743, | |
| "grad_norm": 28.481815338134766, | |
| "learning_rate": 7.7115e-06, | |
| "loss": 0.9227, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 117.43589743589743, | |
| "eval_loss": 1.0956928730010986, | |
| "eval_runtime": 34.0805, | |
| "eval_samples_per_second": 11.532, | |
| "eval_steps_per_second": 1.467, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 117.94871794871794, | |
| "grad_norm": 21.423744201660156, | |
| "learning_rate": 7.7015e-06, | |
| "loss": 0.9235, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 117.94871794871794, | |
| "eval_loss": 1.0744383335113525, | |
| "eval_runtime": 34.0591, | |
| "eval_samples_per_second": 11.539, | |
| "eval_steps_per_second": 1.468, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 118.46153846153847, | |
| "grad_norm": 41.02705383300781, | |
| "learning_rate": 7.6915e-06, | |
| "loss": 0.8931, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 118.46153846153847, | |
| "eval_loss": 1.0844883918762207, | |
| "eval_runtime": 33.9091, | |
| "eval_samples_per_second": 11.59, | |
| "eval_steps_per_second": 1.475, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 118.97435897435898, | |
| "grad_norm": 63.89754104614258, | |
| "learning_rate": 7.681500000000001e-06, | |
| "loss": 0.9388, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 118.97435897435898, | |
| "eval_loss": 1.10041344165802, | |
| "eval_runtime": 33.9999, | |
| "eval_samples_per_second": 11.559, | |
| "eval_steps_per_second": 1.471, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 119.48717948717949, | |
| "grad_norm": 46.03657531738281, | |
| "learning_rate": 7.671500000000001e-06, | |
| "loss": 0.9, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 119.48717948717949, | |
| "eval_loss": 1.1028199195861816, | |
| "eval_runtime": 34.2808, | |
| "eval_samples_per_second": 11.464, | |
| "eval_steps_per_second": 1.459, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "grad_norm": 23.22905158996582, | |
| "learning_rate": 7.661500000000001e-06, | |
| "loss": 0.9223, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_loss": 1.0903513431549072, | |
| "eval_runtime": 34.0346, | |
| "eval_samples_per_second": 11.547, | |
| "eval_steps_per_second": 1.469, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 120.51282051282051, | |
| "grad_norm": 40.20142364501953, | |
| "learning_rate": 7.651500000000001e-06, | |
| "loss": 0.918, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 120.51282051282051, | |
| "eval_loss": 1.0990569591522217, | |
| "eval_runtime": 34.0066, | |
| "eval_samples_per_second": 11.557, | |
| "eval_steps_per_second": 1.47, | |
| "step": 23500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 100000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 513, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.982714405888e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |