| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 53.84615384615385, | |
| "eval_steps": 100, | |
| "global_step": 10500, | |
| "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 | |
| } | |
| ], | |
| "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": 4.013553245184e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |