| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.8831531217300315, | |
| "global_step": 7000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.2783, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.079, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.937721160651098e-05, | |
| "loss": 0.0502, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.86694975230007e-05, | |
| "loss": 0.0464, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.029130851849913597, | |
| "eval_runtime": 1098.3952, | |
| "eval_samples_per_second": 6.711, | |
| "eval_steps_per_second": 0.28, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.796178343949045e-05, | |
| "loss": 0.0331, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.725406935598019e-05, | |
| "loss": 0.0292, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.654635527246992e-05, | |
| "loss": 0.0292, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.583864118895966e-05, | |
| "loss": 0.032, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.02652278169989586, | |
| "eval_runtime": 1094.8086, | |
| "eval_samples_per_second": 6.733, | |
| "eval_steps_per_second": 0.281, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.513092710544941e-05, | |
| "loss": 0.0272, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.442321302193913e-05, | |
| "loss": 0.026, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.371549893842888e-05, | |
| "loss": 0.0227, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.300778485491862e-05, | |
| "loss": 0.0246, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.02081386186182499, | |
| "eval_runtime": 1091.9223, | |
| "eval_samples_per_second": 6.75, | |
| "eval_steps_per_second": 0.282, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.230007077140835e-05, | |
| "loss": 0.0263, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.159235668789809e-05, | |
| "loss": 0.0252, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.088464260438783e-05, | |
| "loss": 0.0253, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.017692852087756e-05, | |
| "loss": 0.0274, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 0.019421329721808434, | |
| "eval_runtime": 1091.9762, | |
| "eval_samples_per_second": 6.75, | |
| "eval_steps_per_second": 0.282, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.946921443736731e-05, | |
| "loss": 0.0211, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.876150035385705e-05, | |
| "loss": 0.0234, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.805378627034678e-05, | |
| "loss": 0.0227, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.734607218683652e-05, | |
| "loss": 0.02, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.01722061075270176, | |
| "eval_runtime": 1091.8825, | |
| "eval_samples_per_second": 6.751, | |
| "eval_steps_per_second": 0.282, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.663835810332625e-05, | |
| "loss": 0.0229, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.5930644019816e-05, | |
| "loss": 0.0189, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.522292993630574e-05, | |
| "loss": 0.0188, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.451521585279548e-05, | |
| "loss": 0.018, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.017043238505721092, | |
| "eval_runtime": 1091.8986, | |
| "eval_samples_per_second": 6.751, | |
| "eval_steps_per_second": 0.282, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.380750176928521e-05, | |
| "loss": 0.0183, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 8.309978768577495e-05, | |
| "loss": 0.0207, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 8.239207360226468e-05, | |
| "loss": 0.0147, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 8.168435951875443e-05, | |
| "loss": 0.0151, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.015169227495789528, | |
| "eval_runtime": 1091.8795, | |
| "eval_samples_per_second": 6.751, | |
| "eval_steps_per_second": 0.282, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 8.097664543524417e-05, | |
| "loss": 0.0148, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 8.02689313517339e-05, | |
| "loss": 0.0125, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.956121726822364e-05, | |
| "loss": 0.0129, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 7.885350318471339e-05, | |
| "loss": 0.0138, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.014357708394527435, | |
| "eval_runtime": 1091.7946, | |
| "eval_samples_per_second": 6.751, | |
| "eval_steps_per_second": 0.282, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.814578910120311e-05, | |
| "loss": 0.015, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 7.743807501769286e-05, | |
| "loss": 0.0152, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 7.67303609341826e-05, | |
| "loss": 0.014, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 7.602264685067233e-05, | |
| "loss": 0.015, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 0.013772633858025074, | |
| "eval_runtime": 1091.9078, | |
| "eval_samples_per_second": 6.751, | |
| "eval_steps_per_second": 0.282, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 7.531493276716207e-05, | |
| "loss": 0.0134, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 7.46072186836518e-05, | |
| "loss": 0.0116, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 7.389950460014154e-05, | |
| "loss": 0.0136, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7.319179051663129e-05, | |
| "loss": 0.0134, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.013411927036941051, | |
| "eval_runtime": 1091.4452, | |
| "eval_samples_per_second": 6.753, | |
| "eval_steps_per_second": 0.282, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 7.248407643312101e-05, | |
| "loss": 0.0129, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 7.177636234961076e-05, | |
| "loss": 0.0144, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.10686482661005e-05, | |
| "loss": 0.0119, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.036093418259024e-05, | |
| "loss": 0.0152, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.014650107361376286, | |
| "eval_runtime": 1091.4623, | |
| "eval_samples_per_second": 6.753, | |
| "eval_steps_per_second": 0.282, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.965322009907997e-05, | |
| "loss": 0.0145, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.894550601556972e-05, | |
| "loss": 0.0154, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 6.823779193205944e-05, | |
| "loss": 0.013, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 6.75300778485492e-05, | |
| "loss": 0.0123, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.013516324572265148, | |
| "eval_runtime": 1091.733, | |
| "eval_samples_per_second": 6.752, | |
| "eval_steps_per_second": 0.282, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 6.682236376503893e-05, | |
| "loss": 0.0123, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 6.611464968152867e-05, | |
| "loss": 0.0132, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 6.54069355980184e-05, | |
| "loss": 0.0172, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 6.469922151450815e-05, | |
| "loss": 0.0121, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.013174451887607574, | |
| "eval_runtime": 1091.4369, | |
| "eval_samples_per_second": 6.753, | |
| "eval_steps_per_second": 0.282, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 6.399150743099787e-05, | |
| "loss": 0.0112, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 6.328379334748762e-05, | |
| "loss": 0.0137, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.257607926397736e-05, | |
| "loss": 0.0107, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 6.18683651804671e-05, | |
| "loss": 0.0115, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 0.01469574123620987, | |
| "eval_runtime": 1091.5407, | |
| "eval_samples_per_second": 6.753, | |
| "eval_steps_per_second": 0.282, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 6.116065109695683e-05, | |
| "loss": 0.015, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 6.045293701344657e-05, | |
| "loss": 0.0123, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 5.974522292993631e-05, | |
| "loss": 0.0101, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 5.9037508846426045e-05, | |
| "loss": 0.0115, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 0.01295243389904499, | |
| "eval_runtime": 1091.2144, | |
| "eval_samples_per_second": 6.755, | |
| "eval_steps_per_second": 0.282, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.832979476291578e-05, | |
| "loss": 0.0116, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 5.7622080679405524e-05, | |
| "loss": 0.0117, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 5.6914366595895267e-05, | |
| "loss": 0.0148, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 5.6206652512384996e-05, | |
| "loss": 0.0104, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 0.012959270738065243, | |
| "eval_runtime": 1091.2195, | |
| "eval_samples_per_second": 6.755, | |
| "eval_steps_per_second": 0.282, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 5.549893842887474e-05, | |
| "loss": 0.01, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 5.479122434536448e-05, | |
| "loss": 0.0095, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 5.408351026185421e-05, | |
| "loss": 0.0108, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 5.337579617834395e-05, | |
| "loss": 0.0112, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.013205363415181637, | |
| "eval_runtime": 1091.0349, | |
| "eval_samples_per_second": 6.756, | |
| "eval_steps_per_second": 0.282, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.2668082094833696e-05, | |
| "loss": 0.0119, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.1960368011323425e-05, | |
| "loss": 0.0107, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.125265392781317e-05, | |
| "loss": 0.0129, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 5.054493984430291e-05, | |
| "loss": 0.0103, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_loss": 0.013000305742025375, | |
| "eval_runtime": 1091.2105, | |
| "eval_samples_per_second": 6.755, | |
| "eval_steps_per_second": 0.282, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.9837225760792646e-05, | |
| "loss": 0.0114, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.912951167728238e-05, | |
| "loss": 0.0116, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.842179759377212e-05, | |
| "loss": 0.0106, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 4.771408351026186e-05, | |
| "loss": 0.0099, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 0.01273022498935461, | |
| "eval_runtime": 1091.0891, | |
| "eval_samples_per_second": 6.756, | |
| "eval_steps_per_second": 0.282, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 4.70063694267516e-05, | |
| "loss": 0.0109, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.629865534324133e-05, | |
| "loss": 0.0125, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.559094125973107e-05, | |
| "loss": 0.0135, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 4.488322717622081e-05, | |
| "loss": 0.0111, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 0.012479917146265507, | |
| "eval_runtime": 1091.0461, | |
| "eval_samples_per_second": 6.756, | |
| "eval_steps_per_second": 0.282, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 4.417551309271055e-05, | |
| "loss": 0.0106, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 4.3467799009200284e-05, | |
| "loss": 0.0115, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 4.2760084925690026e-05, | |
| "loss": 0.0107, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 4.205237084217976e-05, | |
| "loss": 0.0094, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 0.0125270402058959, | |
| "eval_runtime": 1091.2851, | |
| "eval_samples_per_second": 6.754, | |
| "eval_steps_per_second": 0.282, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 4.13446567586695e-05, | |
| "loss": 0.0127, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.063694267515924e-05, | |
| "loss": 0.0088, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 3.992922859164898e-05, | |
| "loss": 0.008, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3.922151450813871e-05, | |
| "loss": 0.0083, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_loss": 0.012798724696040154, | |
| "eval_runtime": 1090.8595, | |
| "eval_samples_per_second": 6.757, | |
| "eval_steps_per_second": 0.282, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.8513800424628456e-05, | |
| "loss": 0.0101, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 3.780608634111819e-05, | |
| "loss": 0.0085, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 3.709837225760793e-05, | |
| "loss": 0.0083, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.6390658174097663e-05, | |
| "loss": 0.0093, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "eval_loss": 0.012657725252211094, | |
| "eval_runtime": 1090.8271, | |
| "eval_samples_per_second": 6.757, | |
| "eval_steps_per_second": 0.282, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 3.5682944090587406e-05, | |
| "loss": 0.0099, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 3.497523000707714e-05, | |
| "loss": 0.0107, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 3.426751592356688e-05, | |
| "loss": 0.0097, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 3.355980184005662e-05, | |
| "loss": 0.0099, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_loss": 0.012795734219253063, | |
| "eval_runtime": 1090.6151, | |
| "eval_samples_per_second": 6.759, | |
| "eval_steps_per_second": 0.282, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 3.285208775654636e-05, | |
| "loss": 0.0094, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 3.214437367303609e-05, | |
| "loss": 0.0099, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 3.1436659589525835e-05, | |
| "loss": 0.0097, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 3.072894550601557e-05, | |
| "loss": 0.0109, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "eval_loss": 0.01254407037049532, | |
| "eval_runtime": 1090.2952, | |
| "eval_samples_per_second": 6.761, | |
| "eval_steps_per_second": 0.282, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 3.0021231422505307e-05, | |
| "loss": 0.009, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 2.931351733899505e-05, | |
| "loss": 0.0106, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 2.8605803255484786e-05, | |
| "loss": 0.0112, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 2.7898089171974522e-05, | |
| "loss": 0.0089, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "eval_loss": 0.012657931074500084, | |
| "eval_runtime": 1090.5111, | |
| "eval_samples_per_second": 6.759, | |
| "eval_steps_per_second": 0.282, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 2.7190375088464258e-05, | |
| "loss": 0.0088, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 2.6482661004954e-05, | |
| "loss": 0.0113, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 2.5774946921443737e-05, | |
| "loss": 0.0105, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 2.5067232837933473e-05, | |
| "loss": 0.0095, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "eval_loss": 0.012662014923989773, | |
| "eval_runtime": 1090.6147, | |
| "eval_samples_per_second": 6.759, | |
| "eval_steps_per_second": 0.282, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 2.4359518754423212e-05, | |
| "loss": 0.0098, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 2.365180467091295e-05, | |
| "loss": 0.0083, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 2.294409058740269e-05, | |
| "loss": 0.0109, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 2.2236376503892427e-05, | |
| "loss": 0.0101, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "eval_loss": 0.012734564021229744, | |
| "eval_runtime": 1090.6719, | |
| "eval_samples_per_second": 6.758, | |
| "eval_steps_per_second": 0.282, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 2.1528662420382166e-05, | |
| "loss": 0.0103, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 2.0820948336871905e-05, | |
| "loss": 0.0084, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 2.0113234253361645e-05, | |
| "loss": 0.0092, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 1.9405520169851384e-05, | |
| "loss": 0.0098, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_loss": 0.01291683316230774, | |
| "eval_runtime": 1090.3976, | |
| "eval_samples_per_second": 6.76, | |
| "eval_steps_per_second": 0.282, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.869780608634112e-05, | |
| "loss": 0.0081, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 1.799009200283086e-05, | |
| "loss": 0.0082, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1.7282377919320595e-05, | |
| "loss": 0.0074, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 1.6574663835810334e-05, | |
| "loss": 0.0084, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_loss": 0.012655936181545258, | |
| "eval_runtime": 1090.3951, | |
| "eval_samples_per_second": 6.76, | |
| "eval_steps_per_second": 0.282, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 1.5866949752300074e-05, | |
| "loss": 0.0084, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 1.515923566878981e-05, | |
| "loss": 0.0095, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 1.4451521585279547e-05, | |
| "loss": 0.0108, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 1.3743807501769285e-05, | |
| "loss": 0.0082, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_loss": 0.012752115726470947, | |
| "eval_runtime": 1090.0724, | |
| "eval_samples_per_second": 6.762, | |
| "eval_steps_per_second": 0.283, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 1.3036093418259024e-05, | |
| "loss": 0.0091, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 1.2328379334748762e-05, | |
| "loss": 0.0083, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 1.1620665251238501e-05, | |
| "loss": 0.0082, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 1.0912951167728239e-05, | |
| "loss": 0.0088, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "eval_loss": 0.013044040650129318, | |
| "eval_runtime": 1090.0452, | |
| "eval_samples_per_second": 6.762, | |
| "eval_steps_per_second": 0.283, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 1.0205237084217977e-05, | |
| "loss": 0.0084, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 9.497523000707714e-06, | |
| "loss": 0.0086, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 8.789808917197452e-06, | |
| "loss": 0.0089, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 8.082094833687191e-06, | |
| "loss": 0.0077, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_loss": 0.012679013423621655, | |
| "eval_runtime": 1089.906, | |
| "eval_samples_per_second": 6.763, | |
| "eval_steps_per_second": 0.283, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 7.374380750176929e-06, | |
| "loss": 0.0086, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0075, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 5.958952583156405e-06, | |
| "loss": 0.008, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 5.251238499646143e-06, | |
| "loss": 0.0082, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_loss": 0.01266387477517128, | |
| "eval_runtime": 1090.0881, | |
| "eval_samples_per_second": 6.762, | |
| "eval_steps_per_second": 0.283, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 4.543524416135881e-06, | |
| "loss": 0.0075, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 3.83581033262562e-06, | |
| "loss": 0.0077, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 3.1280962491153574e-06, | |
| "loss": 0.0089, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 2.420382165605096e-06, | |
| "loss": 0.0093, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "eval_loss": 0.012687072157859802, | |
| "eval_runtime": 1089.9152, | |
| "eval_samples_per_second": 6.763, | |
| "eval_steps_per_second": 0.283, | |
| "step": 7000 | |
| } | |
| ], | |
| "max_steps": 7165, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.675440592244441e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |