| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.7486371340876814, |
| "global_step": 180000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 2.9999999999999997e-06, |
| "loss": 0.8784, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 5.999999999999999e-06, |
| "loss": 0.77, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 8.999999999999999e-06, |
| "loss": 0.7664, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 1.1999999999999999e-05, |
| "loss": 0.7655, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 1.4999999999999999e-05, |
| "loss": 0.765, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_runtime": 1.3797, |
| "eval_samples_per_second": 724.791, |
| "eval_steps_per_second": 11.597, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 1.7999999999999997e-05, |
| "loss": 0.7647, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 2.1e-05, |
| "loss": 0.7644, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 2.3999999999999997e-05, |
| "loss": 0.7638, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 2.6999999999999996e-05, |
| "loss": 0.7633, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 2.9999999999999997e-05, |
| "loss": 0.76, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.15, |
| "eval_runtime": 1.1376, |
| "eval_samples_per_second": 879.066, |
| "eval_steps_per_second": 14.065, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 3.2999999999999996e-05, |
| "loss": 0.7148, |
| "step": 11000 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 3.5999999999999994e-05, |
| "loss": 0.6963, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 3.9e-05, |
| "loss": 0.6755, |
| "step": 13000 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 4.2e-05, |
| "loss": 0.6516, |
| "step": 14000 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 4.4999999999999996e-05, |
| "loss": 0.6412, |
| "step": 15000 |
| }, |
| { |
| "epoch": 0.23, |
| "eval_runtime": 1.1689, |
| "eval_samples_per_second": 855.472, |
| "eval_steps_per_second": 13.688, |
| "step": 15000 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 4.7999999999999994e-05, |
| "loss": 0.6348, |
| "step": 16000 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 5.1e-05, |
| "loss": 0.6295, |
| "step": 17000 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 5.399999999999999e-05, |
| "loss": 0.6224, |
| "step": 18000 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 5.6999999999999996e-05, |
| "loss": 0.6169, |
| "step": 19000 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 0.6113, |
| "step": 20000 |
| }, |
| { |
| "epoch": 0.31, |
| "eval_runtime": 1.0179, |
| "eval_samples_per_second": 982.441, |
| "eval_steps_per_second": 15.719, |
| "step": 20000 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 6.299999999999999e-05, |
| "loss": 0.6074, |
| "step": 21000 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 6.599999999999999e-05, |
| "loss": 0.6039, |
| "step": 22000 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 6.9e-05, |
| "loss": 0.6005, |
| "step": 23000 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 7.199999999999999e-05, |
| "loss": 0.5968, |
| "step": 24000 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 7.5e-05, |
| "loss": 0.5932, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.38, |
| "eval_runtime": 1.1249, |
| "eval_samples_per_second": 888.989, |
| "eval_steps_per_second": 14.224, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 7.8e-05, |
| "loss": 0.5912, |
| "step": 26000 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 8.1e-05, |
| "loss": 0.58, |
| "step": 27000 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 8.4e-05, |
| "loss": 0.5698, |
| "step": 28000 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 8.699999999999999e-05, |
| "loss": 0.5639, |
| "step": 29000 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 8.999999999999999e-05, |
| "loss": 0.5601, |
| "step": 30000 |
| }, |
| { |
| "epoch": 0.46, |
| "eval_runtime": 1.0096, |
| "eval_samples_per_second": 990.512, |
| "eval_steps_per_second": 15.848, |
| "step": 30000 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 9.3e-05, |
| "loss": 0.5536, |
| "step": 31000 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 9.599999999999999e-05, |
| "loss": 0.5496, |
| "step": 32000 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 9.9e-05, |
| "loss": 0.5458, |
| "step": 33000 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.000102, |
| "loss": 0.5426, |
| "step": 34000 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00010499999999999999, |
| "loss": 0.5394, |
| "step": 35000 |
| }, |
| { |
| "epoch": 0.53, |
| "eval_runtime": 1.3102, |
| "eval_samples_per_second": 763.27, |
| "eval_steps_per_second": 12.212, |
| "step": 35000 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00010799999999999998, |
| "loss": 0.5345, |
| "step": 36000 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00011099999999999999, |
| "loss": 0.5302, |
| "step": 37000 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00011399999999999999, |
| "loss": 0.527, |
| "step": 38000 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.000117, |
| "loss": 0.5232, |
| "step": 39000 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 0.5202, |
| "step": 40000 |
| }, |
| { |
| "epoch": 0.61, |
| "eval_runtime": 1.0146, |
| "eval_samples_per_second": 985.598, |
| "eval_steps_per_second": 15.77, |
| "step": 40000 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.00012299999999999998, |
| "loss": 0.5163, |
| "step": 41000 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.00012599999999999997, |
| "loss": 0.5126, |
| "step": 42000 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.000129, |
| "loss": 0.5094, |
| "step": 43000 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.00013199999999999998, |
| "loss": 0.5061, |
| "step": 44000 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.000135, |
| "loss": 0.5036, |
| "step": 45000 |
| }, |
| { |
| "epoch": 0.69, |
| "eval_runtime": 1.0362, |
| "eval_samples_per_second": 965.067, |
| "eval_steps_per_second": 15.441, |
| "step": 45000 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.000138, |
| "loss": 0.4995, |
| "step": 46000 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.00014099999999999998, |
| "loss": 0.4967, |
| "step": 47000 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.00014399999999999998, |
| "loss": 0.4934, |
| "step": 48000 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.000147, |
| "loss": 0.4898, |
| "step": 49000 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.00015, |
| "loss": 0.4863, |
| "step": 50000 |
| }, |
| { |
| "epoch": 0.76, |
| "eval_runtime": 1.0374, |
| "eval_samples_per_second": 963.96, |
| "eval_steps_per_second": 15.423, |
| "step": 50000 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.0001499996172456075, |
| "loss": 0.4824, |
| "step": 51000 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.00014999846898661572, |
| "loss": 0.4778, |
| "step": 52000 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.00014999655523558183, |
| "loss": 0.474, |
| "step": 53000 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00014999387601343436, |
| "loss": 0.4694, |
| "step": 54000 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00014999043134947282, |
| "loss": 0.4651, |
| "step": 55000 |
| }, |
| { |
| "epoch": 0.84, |
| "eval_runtime": 1.0465, |
| "eval_samples_per_second": 955.566, |
| "eval_steps_per_second": 15.289, |
| "step": 55000 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00014998622128136748, |
| "loss": 0.4608, |
| "step": 56000 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.000149981245855159, |
| "loss": 0.4566, |
| "step": 57000 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.00014997550512525784, |
| "loss": 0.4523, |
| "step": 58000 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.0001499689991544437, |
| "loss": 0.4483, |
| "step": 59000 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00014996172801386482, |
| "loss": 0.4447, |
| "step": 60000 |
| }, |
| { |
| "epoch": 0.92, |
| "eval_runtime": 1.2288, |
| "eval_samples_per_second": 813.826, |
| "eval_steps_per_second": 13.021, |
| "step": 60000 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.00014995369178303722, |
| "loss": 0.4408, |
| "step": 61000 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.0001499448905498439, |
| "loss": 0.4381, |
| "step": 62000 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.00014993532441053364, |
| "loss": 0.434, |
| "step": 63000 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.0001499249934697203, |
| "loss": 0.4316, |
| "step": 64000 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.0001499138978403813, |
| "loss": 0.4275, |
| "step": 65000 |
| }, |
| { |
| "epoch": 0.99, |
| "eval_runtime": 1.0345, |
| "eval_samples_per_second": 966.655, |
| "eval_steps_per_second": 15.466, |
| "step": 65000 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00014990203764385677, |
| "loss": 0.425, |
| "step": 66000 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00014988941300984784, |
| "loss": 0.422, |
| "step": 67000 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.0001498760240764155, |
| "loss": 0.4191, |
| "step": 68000 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.000149861870989979, |
| "loss": 0.4164, |
| "step": 69000 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.0001498469539053142, |
| "loss": 0.4138, |
| "step": 70000 |
| }, |
| { |
| "epoch": 1.07, |
| "eval_runtime": 1.1341, |
| "eval_samples_per_second": 881.784, |
| "eval_steps_per_second": 14.109, |
| "step": 70000 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 0.00014983127298555198, |
| "loss": 0.4114, |
| "step": 71000 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.00014981482840217632, |
| "loss": 0.4086, |
| "step": 72000 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.00014979762033502262, |
| "loss": 0.4066, |
| "step": 73000 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 0.00014977964897227547, |
| "loss": 0.4042, |
| "step": 74000 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 0.00014976091451046687, |
| "loss": 0.402, |
| "step": 75000 |
| }, |
| { |
| "epoch": 1.15, |
| "eval_runtime": 1.0331, |
| "eval_samples_per_second": 967.957, |
| "eval_steps_per_second": 15.487, |
| "step": 75000 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.00014974141715447386, |
| "loss": 0.3999, |
| "step": 76000 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 0.00014972115711751644, |
| "loss": 0.398, |
| "step": 77000 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.00014970013462115505, |
| "loss": 0.3971, |
| "step": 78000 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 0.00014967834989528843, |
| "loss": 0.3942, |
| "step": 79000 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.00014965580317815078, |
| "loss": 0.3926, |
| "step": 80000 |
| }, |
| { |
| "epoch": 1.22, |
| "eval_runtime": 1.084, |
| "eval_samples_per_second": 922.521, |
| "eval_steps_per_second": 14.76, |
| "step": 80000 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.00014963249471630944, |
| "loss": 0.3906, |
| "step": 81000 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 0.000149608424764662, |
| "loss": 0.391, |
| "step": 82000 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 0.0001495835935864336, |
| "loss": 0.3875, |
| "step": 83000 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 0.00014955800145317397, |
| "loss": 0.3861, |
| "step": 84000 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 0.00014953164864475466, |
| "loss": 0.3844, |
| "step": 85000 |
| }, |
| { |
| "epoch": 1.3, |
| "eval_runtime": 1.0992, |
| "eval_samples_per_second": 909.734, |
| "eval_steps_per_second": 14.556, |
| "step": 85000 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 0.0001495045354493657, |
| "loss": 0.3829, |
| "step": 86000 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.00014947666216351272, |
| "loss": 0.3815, |
| "step": 87000 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 0.00014944802909201344, |
| "loss": 0.38, |
| "step": 88000 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 0.00014941863654799456, |
| "loss": 0.3789, |
| "step": 89000 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 0.00014938848485288825, |
| "loss": 0.3785, |
| "step": 90000 |
| }, |
| { |
| "epoch": 1.37, |
| "eval_runtime": 0.9266, |
| "eval_samples_per_second": 1079.167, |
| "eval_steps_per_second": 17.267, |
| "step": 90000 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 0.0001493575743364286, |
| "loss": 0.3766, |
| "step": 91000 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.00014932590533664808, |
| "loss": 0.3745, |
| "step": 92000 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 0.0001492934781998738, |
| "loss": 0.3741, |
| "step": 93000 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.0001492602932807237, |
| "loss": 0.3729, |
| "step": 94000 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 0.00014922635094210277, |
| "loss": 0.3709, |
| "step": 95000 |
| }, |
| { |
| "epoch": 1.45, |
| "eval_runtime": 0.9895, |
| "eval_samples_per_second": 1010.579, |
| "eval_steps_per_second": 16.169, |
| "step": 95000 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 0.000149191651555199, |
| "loss": 0.3699, |
| "step": 96000 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.0001491561954994793, |
| "loss": 0.3688, |
| "step": 97000 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 0.00014911998316268537, |
| "loss": 0.3678, |
| "step": 98000 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 0.00014908301494082963, |
| "loss": 0.3666, |
| "step": 99000 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 0.00014904529123819054, |
| "loss": 0.3654, |
| "step": 100000 |
| }, |
| { |
| "epoch": 1.53, |
| "eval_runtime": 1.0046, |
| "eval_samples_per_second": 995.424, |
| "eval_steps_per_second": 15.927, |
| "step": 100000 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.00014900681246730852, |
| "loss": 0.3643, |
| "step": 101000 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.00014896757904898125, |
| "loss": 0.3646, |
| "step": 102000 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 0.00014892759141225904, |
| "loss": 0.3628, |
| "step": 103000 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.00014888684999444035, |
| "loss": 0.3616, |
| "step": 104000 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 0.00014884535524106675, |
| "loss": 0.3604, |
| "step": 105000 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_runtime": 1.0499, |
| "eval_samples_per_second": 952.499, |
| "eval_steps_per_second": 15.24, |
| "step": 105000 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 0.00014880310760591824, |
| "loss": 0.3594, |
| "step": 106000 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.0001487601075510082, |
| "loss": 0.3597, |
| "step": 107000 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 0.0001487163555465783, |
| "loss": 0.3583, |
| "step": 108000 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 0.0001486718520710935, |
| "loss": 0.3583, |
| "step": 109000 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 0.00014862659761123663, |
| "loss": 0.3558, |
| "step": 110000 |
| }, |
| { |
| "epoch": 1.68, |
| "eval_runtime": 1.0153, |
| "eval_samples_per_second": 984.91, |
| "eval_steps_per_second": 15.759, |
| "step": 110000 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 0.00014858059266190327, |
| "loss": 0.3552, |
| "step": 111000 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 0.00014853383772619612, |
| "loss": 0.3544, |
| "step": 112000 |
| }, |
| { |
| "epoch": 1.73, |
| "learning_rate": 0.00014848633331541967, |
| "loss": 0.3537, |
| "step": 113000 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 0.0001484380799490746, |
| "loss": 0.3524, |
| "step": 114000 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 0.00014838907815485194, |
| "loss": 0.3519, |
| "step": 115000 |
| }, |
| { |
| "epoch": 1.76, |
| "eval_runtime": 1.003, |
| "eval_samples_per_second": 997.001, |
| "eval_steps_per_second": 15.952, |
| "step": 115000 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 0.00014833932846862748, |
| "loss": 0.3511, |
| "step": 116000 |
| }, |
| { |
| "epoch": 1.79, |
| "learning_rate": 0.00014828883143445582, |
| "loss": 0.3502, |
| "step": 117000 |
| }, |
| { |
| "epoch": 1.8, |
| "learning_rate": 0.0001482375876045644, |
| "loss": 0.3493, |
| "step": 118000 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 0.0001481855975393476, |
| "loss": 0.3489, |
| "step": 119000 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 0.0001481328618073604, |
| "loss": 0.3482, |
| "step": 120000 |
| }, |
| { |
| "epoch": 1.83, |
| "eval_runtime": 1.0596, |
| "eval_samples_per_second": 943.744, |
| "eval_steps_per_second": 15.1, |
| "step": 120000 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 0.0001480793809853123, |
| "loss": 0.3478, |
| "step": 121000 |
| }, |
| { |
| "epoch": 1.86, |
| "learning_rate": 0.00014802515565806107, |
| "loss": 0.3468, |
| "step": 122000 |
| }, |
| { |
| "epoch": 1.88, |
| "learning_rate": 0.00014797018641860612, |
| "loss": 0.346, |
| "step": 123000 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 0.0001479144738680823, |
| "loss": 0.3474, |
| "step": 124000 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.00014785801861575312, |
| "loss": 0.3447, |
| "step": 125000 |
| }, |
| { |
| "epoch": 1.91, |
| "eval_runtime": 0.9375, |
| "eval_samples_per_second": 1066.699, |
| "eval_steps_per_second": 17.067, |
| "step": 125000 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 0.00014780082127900416, |
| "loss": 0.3439, |
| "step": 126000 |
| }, |
| { |
| "epoch": 1.94, |
| "learning_rate": 0.00014774288248333635, |
| "loss": 0.3436, |
| "step": 127000 |
| }, |
| { |
| "epoch": 1.95, |
| "learning_rate": 0.00014768420286235908, |
| "loss": 0.3429, |
| "step": 128000 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 0.00014762478305778328, |
| "loss": 0.3422, |
| "step": 129000 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 0.0001475646237194144, |
| "loss": 0.3414, |
| "step": 130000 |
| }, |
| { |
| "epoch": 1.99, |
| "eval_runtime": 1.0085, |
| "eval_samples_per_second": 991.553, |
| "eval_steps_per_second": 15.865, |
| "step": 130000 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0.00014750372550514533, |
| "loss": 0.3409, |
| "step": 131000 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 0.0001474420890809492, |
| "loss": 0.3401, |
| "step": 132000 |
| }, |
| { |
| "epoch": 2.03, |
| "learning_rate": 0.00014737971512087202, |
| "loss": 0.3396, |
| "step": 133000 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 0.00014731660430702552, |
| "loss": 0.339, |
| "step": 134000 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 0.00014725275732957937, |
| "loss": 0.3402, |
| "step": 135000 |
| }, |
| { |
| "epoch": 2.06, |
| "eval_runtime": 1.1005, |
| "eval_samples_per_second": 908.652, |
| "eval_steps_per_second": 14.538, |
| "step": 135000 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 0.00014718817488675387, |
| "loss": 0.3379, |
| "step": 136000 |
| }, |
| { |
| "epoch": 2.09, |
| "learning_rate": 0.00014712285768481235, |
| "loss": 0.3371, |
| "step": 137000 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 0.00014705680643805323, |
| "loss": 0.3368, |
| "step": 138000 |
| }, |
| { |
| "epoch": 2.12, |
| "learning_rate": 0.00014699002186880232, |
| "loss": 0.3363, |
| "step": 139000 |
| }, |
| { |
| "epoch": 2.14, |
| "learning_rate": 0.00014692250470740503, |
| "loss": 0.3361, |
| "step": 140000 |
| }, |
| { |
| "epoch": 2.14, |
| "eval_runtime": 1.0104, |
| "eval_samples_per_second": 989.716, |
| "eval_steps_per_second": 15.835, |
| "step": 140000 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 0.00014685425569221819, |
| "loss": 0.3353, |
| "step": 141000 |
| }, |
| { |
| "epoch": 2.17, |
| "learning_rate": 0.00014678527556960207, |
| "loss": 0.3346, |
| "step": 142000 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 0.0001467155650939123, |
| "loss": 0.3342, |
| "step": 143000 |
| }, |
| { |
| "epoch": 2.2, |
| "learning_rate": 0.00014664512502749141, |
| "loss": 0.3338, |
| "step": 144000 |
| }, |
| { |
| "epoch": 2.21, |
| "learning_rate": 0.00014657395614066075, |
| "loss": 0.3334, |
| "step": 145000 |
| }, |
| { |
| "epoch": 2.21, |
| "eval_runtime": 1.0369, |
| "eval_samples_per_second": 964.439, |
| "eval_steps_per_second": 15.431, |
| "step": 145000 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 0.0001465020592117118, |
| "loss": 0.3327, |
| "step": 146000 |
| }, |
| { |
| "epoch": 2.24, |
| "learning_rate": 0.0001464294350268979, |
| "loss": 0.3324, |
| "step": 147000 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 0.00014635608438042546, |
| "loss": 0.3319, |
| "step": 148000 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 0.00014628200807444543, |
| "loss": 0.3313, |
| "step": 149000 |
| }, |
| { |
| "epoch": 2.29, |
| "learning_rate": 0.0001462072069190444, |
| "loss": 0.3307, |
| "step": 150000 |
| }, |
| { |
| "epoch": 2.29, |
| "eval_runtime": 1.0431, |
| "eval_samples_per_second": 958.687, |
| "eval_steps_per_second": 15.339, |
| "step": 150000 |
| }, |
| { |
| "epoch": 2.31, |
| "learning_rate": 0.00014613168173223585, |
| "loss": 0.3308, |
| "step": 151000 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 0.00014605543333995113, |
| "loss": 0.3302, |
| "step": 152000 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 0.00014597846257603038, |
| "loss": 0.3294, |
| "step": 153000 |
| }, |
| { |
| "epoch": 2.35, |
| "learning_rate": 0.0001459007702822136, |
| "loss": 0.329, |
| "step": 154000 |
| }, |
| { |
| "epoch": 2.37, |
| "learning_rate": 0.00014582235730813128, |
| "loss": 0.3283, |
| "step": 155000 |
| }, |
| { |
| "epoch": 2.37, |
| "eval_runtime": 1.0629, |
| "eval_samples_per_second": 940.817, |
| "eval_steps_per_second": 15.053, |
| "step": 155000 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 0.00014574322451129507, |
| "loss": 0.3281, |
| "step": 156000 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 0.00014566337275708863, |
| "loss": 0.328, |
| "step": 157000 |
| }, |
| { |
| "epoch": 2.41, |
| "learning_rate": 0.0001455828029187579, |
| "loss": 0.3272, |
| "step": 158000 |
| }, |
| { |
| "epoch": 2.43, |
| "learning_rate": 0.00014550151587740178, |
| "loss": 0.3269, |
| "step": 159000 |
| }, |
| { |
| "epoch": 2.44, |
| "learning_rate": 0.00014541951252196225, |
| "loss": 0.3265, |
| "step": 160000 |
| }, |
| { |
| "epoch": 2.44, |
| "eval_runtime": 1.0199, |
| "eval_samples_per_second": 980.452, |
| "eval_steps_per_second": 15.687, |
| "step": 160000 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 0.00014533679374921493, |
| "loss": 0.3259, |
| "step": 161000 |
| }, |
| { |
| "epoch": 2.47, |
| "learning_rate": 0.00014525336046375905, |
| "loss": 0.3254, |
| "step": 162000 |
| }, |
| { |
| "epoch": 2.49, |
| "learning_rate": 0.00014516921357800766, |
| "loss": 0.3251, |
| "step": 163000 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 0.00014508435401217759, |
| "loss": 0.3244, |
| "step": 164000 |
| }, |
| { |
| "epoch": 2.52, |
| "learning_rate": 0.00014499878269427948, |
| "loss": 0.3243, |
| "step": 165000 |
| }, |
| { |
| "epoch": 2.52, |
| "eval_runtime": 1.0655, |
| "eval_samples_per_second": 938.486, |
| "eval_steps_per_second": 15.016, |
| "step": 165000 |
| }, |
| { |
| "epoch": 2.53, |
| "learning_rate": 0.00014491250056010758, |
| "loss": 0.3236, |
| "step": 166000 |
| }, |
| { |
| "epoch": 2.55, |
| "learning_rate": 0.00014482550855322943, |
| "loss": 0.3233, |
| "step": 167000 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 0.0001447378076249757, |
| "loss": 0.3231, |
| "step": 168000 |
| }, |
| { |
| "epoch": 2.58, |
| "learning_rate": 0.00014464939873442973, |
| "loss": 0.3228, |
| "step": 169000 |
| }, |
| { |
| "epoch": 2.6, |
| "learning_rate": 0.00014456028284841693, |
| "loss": 0.3221, |
| "step": 170000 |
| }, |
| { |
| "epoch": 2.6, |
| "eval_runtime": 1.1756, |
| "eval_samples_per_second": 850.656, |
| "eval_steps_per_second": 13.611, |
| "step": 170000 |
| }, |
| { |
| "epoch": 2.61, |
| "learning_rate": 0.00014447046094149437, |
| "loss": 0.3221, |
| "step": 171000 |
| }, |
| { |
| "epoch": 2.63, |
| "learning_rate": 0.00014437993399594003, |
| "loss": 0.3216, |
| "step": 172000 |
| }, |
| { |
| "epoch": 2.64, |
| "learning_rate": 0.0001442887030017421, |
| "loss": 0.3217, |
| "step": 173000 |
| }, |
| { |
| "epoch": 2.66, |
| "learning_rate": 0.00014419676895658807, |
| "loss": 0.3208, |
| "step": 174000 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 0.000144104132865854, |
| "loss": 0.3207, |
| "step": 175000 |
| }, |
| { |
| "epoch": 2.67, |
| "eval_runtime": 1.0679, |
| "eval_samples_per_second": 936.423, |
| "eval_steps_per_second": 14.983, |
| "step": 175000 |
| }, |
| { |
| "epoch": 2.69, |
| "learning_rate": 0.0001440107957425933, |
| "loss": 0.3203, |
| "step": 176000 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 0.0001439167586075258, |
| "loss": 0.3201, |
| "step": 177000 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 0.0001438220224890265, |
| "loss": 0.3191, |
| "step": 178000 |
| }, |
| { |
| "epoch": 2.73, |
| "learning_rate": 0.00014372658842311449, |
| "loss": 0.3195, |
| "step": 179000 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 0.00014363045745344137, |
| "loss": 0.3191, |
| "step": 180000 |
| }, |
| { |
| "epoch": 2.75, |
| "eval_runtime": 1.0169, |
| "eval_samples_per_second": 983.42, |
| "eval_steps_per_second": 15.735, |
| "step": 180000 |
| } |
| ], |
| "max_steps": 1000000, |
| "num_train_epochs": 16, |
| "total_flos": 1.261803384409951e+22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
