| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 5, | |
| "global_step": 910, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01098901098901099, | |
| "grad_norm": 2.787256796216871, | |
| "learning_rate": 1.098901098901099e-08, | |
| "loss": 2.6306, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.054945054945054944, | |
| "grad_norm": 2.7208828057352172, | |
| "learning_rate": 5.494505494505494e-08, | |
| "loss": 2.652, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.054945054945054944, | |
| "eval_loss": 2.6433982849121094, | |
| "eval_runtime": 98.8619, | |
| "eval_samples_per_second": 33.157, | |
| "eval_steps_per_second": 0.829, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10989010989010989, | |
| "grad_norm": 2.7039289723117808, | |
| "learning_rate": 1.0989010989010988e-07, | |
| "loss": 2.6262, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10989010989010989, | |
| "eval_loss": 2.6424529552459717, | |
| "eval_runtime": 96.9771, | |
| "eval_samples_per_second": 33.802, | |
| "eval_steps_per_second": 0.846, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16483516483516483, | |
| "grad_norm": 2.9271293165910413, | |
| "learning_rate": 1.6483516483516482e-07, | |
| "loss": 2.6452, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16483516483516483, | |
| "eval_loss": 2.6390280723571777, | |
| "eval_runtime": 94.3235, | |
| "eval_samples_per_second": 34.753, | |
| "eval_steps_per_second": 0.869, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21978021978021978, | |
| "grad_norm": 2.480796984302828, | |
| "learning_rate": 2.1978021978021976e-07, | |
| "loss": 2.6387, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21978021978021978, | |
| "eval_loss": 2.6297805309295654, | |
| "eval_runtime": 97.0464, | |
| "eval_samples_per_second": 33.778, | |
| "eval_steps_per_second": 0.845, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27472527472527475, | |
| "grad_norm": 2.3675810470522483, | |
| "learning_rate": 2.7472527472527475e-07, | |
| "loss": 2.6259, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27472527472527475, | |
| "eval_loss": 2.6251583099365234, | |
| "eval_runtime": 94.763, | |
| "eval_samples_per_second": 34.592, | |
| "eval_steps_per_second": 0.865, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32967032967032966, | |
| "grad_norm": 1.9222673443941214, | |
| "learning_rate": 3.2967032967032963e-07, | |
| "loss": 2.5997, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32967032967032966, | |
| "eval_loss": 2.603151559829712, | |
| "eval_runtime": 95.4458, | |
| "eval_samples_per_second": 34.344, | |
| "eval_steps_per_second": 0.859, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 1.9849926292026194, | |
| "learning_rate": 3.8461538461538463e-07, | |
| "loss": 2.5946, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "eval_loss": 2.593891143798828, | |
| "eval_runtime": 94.3775, | |
| "eval_samples_per_second": 34.733, | |
| "eval_steps_per_second": 0.869, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "grad_norm": 1.7366188084370735, | |
| "learning_rate": 4.395604395604395e-07, | |
| "loss": 2.5801, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "eval_loss": 2.5582449436187744, | |
| "eval_runtime": 95.1258, | |
| "eval_samples_per_second": 34.46, | |
| "eval_steps_per_second": 0.862, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4945054945054945, | |
| "grad_norm": 1.5634290965231614, | |
| "learning_rate": 4.945054945054945e-07, | |
| "loss": 2.5387, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4945054945054945, | |
| "eval_loss": 2.539731979370117, | |
| "eval_runtime": 94.4215, | |
| "eval_samples_per_second": 34.717, | |
| "eval_steps_per_second": 0.868, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5494505494505495, | |
| "grad_norm": 1.5589987032678356, | |
| "learning_rate": 5.494505494505495e-07, | |
| "loss": 2.5425, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5494505494505495, | |
| "eval_loss": 2.5231664180755615, | |
| "eval_runtime": 94.9946, | |
| "eval_samples_per_second": 34.507, | |
| "eval_steps_per_second": 0.863, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6043956043956044, | |
| "grad_norm": 1.357945104882359, | |
| "learning_rate": 6.043956043956043e-07, | |
| "loss": 2.5065, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6043956043956044, | |
| "eval_loss": 2.5029337406158447, | |
| "eval_runtime": 95.3244, | |
| "eval_samples_per_second": 34.388, | |
| "eval_steps_per_second": 0.86, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6593406593406593, | |
| "grad_norm": 1.351901982993815, | |
| "learning_rate": 6.593406593406593e-07, | |
| "loss": 2.4884, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6593406593406593, | |
| "eval_loss": 2.48612380027771, | |
| "eval_runtime": 94.5792, | |
| "eval_samples_per_second": 34.659, | |
| "eval_steps_per_second": 0.867, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 1.3411768977322787, | |
| "learning_rate": 7.142857142857143e-07, | |
| "loss": 2.4708, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "eval_loss": 2.4696457386016846, | |
| "eval_runtime": 95.9513, | |
| "eval_samples_per_second": 34.163, | |
| "eval_steps_per_second": 0.855, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 1.3228056998181177, | |
| "learning_rate": 7.692307692307693e-07, | |
| "loss": 2.4527, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "eval_loss": 2.4544637203216553, | |
| "eval_runtime": 94.037, | |
| "eval_samples_per_second": 34.859, | |
| "eval_steps_per_second": 0.872, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8241758241758241, | |
| "grad_norm": 1.3089892743121356, | |
| "learning_rate": 8.241758241758241e-07, | |
| "loss": 2.4525, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8241758241758241, | |
| "eval_loss": 2.4406723976135254, | |
| "eval_runtime": 96.5873, | |
| "eval_samples_per_second": 33.938, | |
| "eval_steps_per_second": 0.849, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 1.352286963239502, | |
| "learning_rate": 8.79120879120879e-07, | |
| "loss": 2.4281, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "eval_loss": 2.428374767303467, | |
| "eval_runtime": 94.3709, | |
| "eval_samples_per_second": 34.735, | |
| "eval_steps_per_second": 0.869, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9340659340659341, | |
| "grad_norm": 1.3538673636384089, | |
| "learning_rate": 9.340659340659341e-07, | |
| "loss": 2.4286, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.9340659340659341, | |
| "eval_loss": 2.417691946029663, | |
| "eval_runtime": 96.296, | |
| "eval_samples_per_second": 34.041, | |
| "eval_steps_per_second": 0.852, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.989010989010989, | |
| "grad_norm": 1.314242339957954, | |
| "learning_rate": 9.89010989010989e-07, | |
| "loss": 2.4127, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.989010989010989, | |
| "eval_loss": 2.4079270362854004, | |
| "eval_runtime": 94.1094, | |
| "eval_samples_per_second": 34.832, | |
| "eval_steps_per_second": 0.871, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.043956043956044, | |
| "grad_norm": 1.292934852988739, | |
| "learning_rate": 9.999411449933815e-07, | |
| "loss": 2.3982, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.043956043956044, | |
| "eval_loss": 2.3987655639648438, | |
| "eval_runtime": 96.8027, | |
| "eval_samples_per_second": 33.863, | |
| "eval_steps_per_second": 0.847, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.098901098901099, | |
| "grad_norm": 1.329633653617423, | |
| "learning_rate": 9.997020702755352e-07, | |
| "loss": 2.3983, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.098901098901099, | |
| "eval_loss": 2.390303611755371, | |
| "eval_runtime": 94.1549, | |
| "eval_samples_per_second": 34.815, | |
| "eval_steps_per_second": 0.871, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 1.3449275632813102, | |
| "learning_rate": 9.992791852820708e-07, | |
| "loss": 2.3845, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "eval_loss": 2.3824305534362793, | |
| "eval_runtime": 96.1609, | |
| "eval_samples_per_second": 34.089, | |
| "eval_steps_per_second": 0.853, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.2087912087912087, | |
| "grad_norm": 1.2976258496024031, | |
| "learning_rate": 9.986726455668912e-07, | |
| "loss": 2.3741, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2087912087912087, | |
| "eval_loss": 2.374979257583618, | |
| "eval_runtime": 93.9379, | |
| "eval_samples_per_second": 34.895, | |
| "eval_steps_per_second": 0.873, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2637362637362637, | |
| "grad_norm": 1.3352972965753644, | |
| "learning_rate": 9.978826742394025e-07, | |
| "loss": 2.374, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.2637362637362637, | |
| "eval_loss": 2.367839813232422, | |
| "eval_runtime": 95.5399, | |
| "eval_samples_per_second": 34.31, | |
| "eval_steps_per_second": 0.858, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.3186813186813187, | |
| "grad_norm": 1.351442511494053, | |
| "learning_rate": 9.969095618824461e-07, | |
| "loss": 2.354, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3186813186813187, | |
| "eval_loss": 2.360889434814453, | |
| "eval_runtime": 94.4101, | |
| "eval_samples_per_second": 34.721, | |
| "eval_steps_per_second": 0.869, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3736263736263736, | |
| "grad_norm": 1.3462760051666864, | |
| "learning_rate": 9.95753666445411e-07, | |
| "loss": 2.3498, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.3736263736263736, | |
| "eval_loss": 2.3541159629821777, | |
| "eval_runtime": 94.7992, | |
| "eval_samples_per_second": 34.578, | |
| "eval_steps_per_second": 0.865, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 1.3496352842968289, | |
| "learning_rate": 9.944154131125642e-07, | |
| "loss": 2.3324, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "eval_loss": 2.347334861755371, | |
| "eval_runtime": 95.6461, | |
| "eval_samples_per_second": 34.272, | |
| "eval_steps_per_second": 0.857, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4835164835164836, | |
| "grad_norm": 1.3292817866036872, | |
| "learning_rate": 9.928952941466537e-07, | |
| "loss": 2.3386, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.4835164835164836, | |
| "eval_loss": 2.3408091068267822, | |
| "eval_runtime": 94.7751, | |
| "eval_samples_per_second": 34.587, | |
| "eval_steps_per_second": 0.865, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 1.3030870244645119, | |
| "learning_rate": 9.911938687078323e-07, | |
| "loss": 2.3199, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "eval_loss": 2.334508180618286, | |
| "eval_runtime": 96.7229, | |
| "eval_samples_per_second": 33.891, | |
| "eval_steps_per_second": 0.848, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.5934065934065935, | |
| "grad_norm": 1.357889365983369, | |
| "learning_rate": 9.893117626479776e-07, | |
| "loss": 2.3192, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.5934065934065935, | |
| "eval_loss": 2.3284120559692383, | |
| "eval_runtime": 94.5936, | |
| "eval_samples_per_second": 34.654, | |
| "eval_steps_per_second": 0.867, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.6483516483516483, | |
| "grad_norm": 1.3682230754482416, | |
| "learning_rate": 9.87249668280478e-07, | |
| "loss": 2.3205, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.6483516483516483, | |
| "eval_loss": 2.322436809539795, | |
| "eval_runtime": 96.3599, | |
| "eval_samples_per_second": 34.018, | |
| "eval_steps_per_second": 0.851, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.7032967032967035, | |
| "grad_norm": 1.356238814707341, | |
| "learning_rate": 9.850083441255734e-07, | |
| "loss": 2.3152, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.7032967032967035, | |
| "eval_loss": 2.3167214393615723, | |
| "eval_runtime": 94.0628, | |
| "eval_samples_per_second": 34.849, | |
| "eval_steps_per_second": 0.872, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.7582417582417582, | |
| "grad_norm": 1.3669835941127673, | |
| "learning_rate": 9.8258861463134e-07, | |
| "loss": 2.309, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.7582417582417582, | |
| "eval_loss": 2.311154365539551, | |
| "eval_runtime": 95.3173, | |
| "eval_samples_per_second": 34.39, | |
| "eval_steps_per_second": 0.86, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.8131868131868132, | |
| "grad_norm": 1.370896874190673, | |
| "learning_rate": 9.799913698704268e-07, | |
| "loss": 2.2937, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.8131868131868132, | |
| "eval_loss": 2.3057687282562256, | |
| "eval_runtime": 95.653, | |
| "eval_samples_per_second": 34.27, | |
| "eval_steps_per_second": 0.857, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.8681318681318682, | |
| "grad_norm": 1.383985193963144, | |
| "learning_rate": 9.772175652126504e-07, | |
| "loss": 2.2957, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.8681318681318682, | |
| "eval_loss": 2.300417423248291, | |
| "eval_runtime": 94.5548, | |
| "eval_samples_per_second": 34.668, | |
| "eval_steps_per_second": 0.867, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "grad_norm": 1.3861435502681547, | |
| "learning_rate": 9.742682209735727e-07, | |
| "loss": 2.2941, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "eval_loss": 2.2951645851135254, | |
| "eval_runtime": 96.181, | |
| "eval_samples_per_second": 34.082, | |
| "eval_steps_per_second": 0.853, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.978021978021978, | |
| "grad_norm": 1.387939254087276, | |
| "learning_rate": 9.711444220391885e-07, | |
| "loss": 2.2986, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.978021978021978, | |
| "eval_loss": 2.290034055709839, | |
| "eval_runtime": 94.7723, | |
| "eval_samples_per_second": 34.588, | |
| "eval_steps_per_second": 0.865, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.032967032967033, | |
| "grad_norm": 1.4083527156579858, | |
| "learning_rate": 9.678473174668605e-07, | |
| "loss": 2.2759, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.032967032967033, | |
| "eval_loss": 2.2850897312164307, | |
| "eval_runtime": 96.6234, | |
| "eval_samples_per_second": 33.926, | |
| "eval_steps_per_second": 0.849, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.087912087912088, | |
| "grad_norm": 1.3901375675143754, | |
| "learning_rate": 9.64378120062651e-07, | |
| "loss": 2.26, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.087912087912088, | |
| "eval_loss": 2.2804834842681885, | |
| "eval_runtime": 94.7228, | |
| "eval_samples_per_second": 34.606, | |
| "eval_steps_per_second": 0.866, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 1.3559893959650073, | |
| "learning_rate": 9.607381059352038e-07, | |
| "loss": 2.2661, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "eval_loss": 2.27602481842041, | |
| "eval_runtime": 95.5105, | |
| "eval_samples_per_second": 34.321, | |
| "eval_steps_per_second": 0.859, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.197802197802198, | |
| "grad_norm": 1.4338659258910222, | |
| "learning_rate": 9.569286140263397e-07, | |
| "loss": 2.265, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.197802197802198, | |
| "eval_loss": 2.271735429763794, | |
| "eval_runtime": 95.2547, | |
| "eval_samples_per_second": 34.413, | |
| "eval_steps_per_second": 0.861, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.2527472527472527, | |
| "grad_norm": 1.3511461203348951, | |
| "learning_rate": 9.529510456185417e-07, | |
| "loss": 2.2554, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.2527472527472527, | |
| "eval_loss": 2.2676820755004883, | |
| "eval_runtime": 95.0959, | |
| "eval_samples_per_second": 34.47, | |
| "eval_steps_per_second": 0.862, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 1.3787695258849668, | |
| "learning_rate": 9.488068638195071e-07, | |
| "loss": 2.2558, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "eval_loss": 2.2637946605682373, | |
| "eval_runtime": 96.7344, | |
| "eval_samples_per_second": 33.887, | |
| "eval_steps_per_second": 0.848, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.3626373626373627, | |
| "grad_norm": 1.3944429206878337, | |
| "learning_rate": 9.444975930239581e-07, | |
| "loss": 2.2508, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.3626373626373627, | |
| "eval_loss": 2.2600150108337402, | |
| "eval_runtime": 94.3417, | |
| "eval_samples_per_second": 34.746, | |
| "eval_steps_per_second": 0.869, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.4175824175824174, | |
| "grad_norm": 1.36473652575597, | |
| "learning_rate": 9.400248183529092e-07, | |
| "loss": 2.2405, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.4175824175824174, | |
| "eval_loss": 2.256455898284912, | |
| "eval_runtime": 96.4969, | |
| "eval_samples_per_second": 33.97, | |
| "eval_steps_per_second": 0.85, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.4725274725274726, | |
| "grad_norm": 1.3975755281584308, | |
| "learning_rate": 9.353901850705972e-07, | |
| "loss": 2.2484, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.4725274725274726, | |
| "eval_loss": 2.2530221939086914, | |
| "eval_runtime": 94.3914, | |
| "eval_samples_per_second": 34.728, | |
| "eval_steps_per_second": 0.869, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.5274725274725274, | |
| "grad_norm": 1.4268198012910995, | |
| "learning_rate": 9.305953979792864e-07, | |
| "loss": 2.2388, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.5274725274725274, | |
| "eval_loss": 2.2498600482940674, | |
| "eval_runtime": 96.755, | |
| "eval_samples_per_second": 33.879, | |
| "eval_steps_per_second": 0.848, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.5824175824175826, | |
| "grad_norm": 1.405521450176673, | |
| "learning_rate": 9.256422207921756e-07, | |
| "loss": 2.2472, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.5824175824175826, | |
| "eval_loss": 2.2467663288116455, | |
| "eval_runtime": 94.2329, | |
| "eval_samples_per_second": 34.786, | |
| "eval_steps_per_second": 0.87, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.6373626373626373, | |
| "grad_norm": 1.3800086312953763, | |
| "learning_rate": 9.205324754846339e-07, | |
| "loss": 2.2253, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.6373626373626373, | |
| "eval_loss": 2.2438271045684814, | |
| "eval_runtime": 95.1079, | |
| "eval_samples_per_second": 34.466, | |
| "eval_steps_per_second": 0.862, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.6923076923076925, | |
| "grad_norm": 1.424541861104674, | |
| "learning_rate": 9.152680416240058e-07, | |
| "loss": 2.2356, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.6923076923076925, | |
| "eval_loss": 2.2410500049591064, | |
| "eval_runtime": 94.5581, | |
| "eval_samples_per_second": 34.667, | |
| "eval_steps_per_second": 0.867, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.7472527472527473, | |
| "grad_norm": 1.4211612108269323, | |
| "learning_rate": 9.09850855678232e-07, | |
| "loss": 2.2202, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.7472527472527473, | |
| "eval_loss": 2.2383668422698975, | |
| "eval_runtime": 95.1818, | |
| "eval_samples_per_second": 34.439, | |
| "eval_steps_per_second": 0.862, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.802197802197802, | |
| "grad_norm": 1.3505783784300605, | |
| "learning_rate": 9.042829103035389e-07, | |
| "loss": 2.2325, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.802197802197802, | |
| "eval_loss": 2.2357189655303955, | |
| "eval_runtime": 96.4181, | |
| "eval_samples_per_second": 33.998, | |
| "eval_steps_per_second": 0.85, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 1.413017015451658, | |
| "learning_rate": 8.985662536114612e-07, | |
| "loss": 2.2208, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_loss": 2.2331881523132324, | |
| "eval_runtime": 95.0055, | |
| "eval_samples_per_second": 34.503, | |
| "eval_steps_per_second": 0.863, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.912087912087912, | |
| "grad_norm": 1.4113571267131109, | |
| "learning_rate": 8.927029884154645e-07, | |
| "loss": 2.2228, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.912087912087912, | |
| "eval_loss": 2.2307634353637695, | |
| "eval_runtime": 95.2567, | |
| "eval_samples_per_second": 34.412, | |
| "eval_steps_per_second": 0.861, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.967032967032967, | |
| "grad_norm": 1.4351733805268447, | |
| "learning_rate": 8.866952714574469e-07, | |
| "loss": 2.204, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.967032967032967, | |
| "eval_loss": 2.228379964828491, | |
| "eval_runtime": 94.9872, | |
| "eval_samples_per_second": 34.51, | |
| "eval_steps_per_second": 0.863, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.021978021978022, | |
| "grad_norm": 1.4281979614756792, | |
| "learning_rate": 8.805453126144047e-07, | |
| "loss": 2.2071, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.021978021978022, | |
| "eval_loss": 2.2260966300964355, | |
| "eval_runtime": 95.0392, | |
| "eval_samples_per_second": 34.491, | |
| "eval_steps_per_second": 0.863, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 1.3917979753684913, | |
| "learning_rate": 8.742553740855505e-07, | |
| "loss": 2.2045, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "eval_loss": 2.2239363193511963, | |
| "eval_runtime": 95.5212, | |
| "eval_samples_per_second": 34.317, | |
| "eval_steps_per_second": 0.858, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.131868131868132, | |
| "grad_norm": 1.3437438345520127, | |
| "learning_rate": 8.678277695601871e-07, | |
| "loss": 2.201, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.131868131868132, | |
| "eval_loss": 2.221846103668213, | |
| "eval_runtime": 94.5168, | |
| "eval_samples_per_second": 34.682, | |
| "eval_steps_per_second": 0.868, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.186813186813187, | |
| "grad_norm": 1.4708322103599034, | |
| "learning_rate": 8.612648633666406e-07, | |
| "loss": 2.2055, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.186813186813187, | |
| "eval_loss": 2.2196929454803467, | |
| "eval_runtime": 96.225, | |
| "eval_samples_per_second": 34.066, | |
| "eval_steps_per_second": 0.852, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.241758241758242, | |
| "grad_norm": 1.3792124479226802, | |
| "learning_rate": 8.545690696025665e-07, | |
| "loss": 2.194, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.241758241758242, | |
| "eval_loss": 2.2177319526672363, | |
| "eval_runtime": 95.0779, | |
| "eval_samples_per_second": 34.477, | |
| "eval_steps_per_second": 0.862, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.2967032967032965, | |
| "grad_norm": 1.3913138741477784, | |
| "learning_rate": 8.477428512469487e-07, | |
| "loss": 2.2053, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.2967032967032965, | |
| "eval_loss": 2.215750217437744, | |
| "eval_runtime": 96.5467, | |
| "eval_samples_per_second": 33.952, | |
| "eval_steps_per_second": 0.849, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.3516483516483517, | |
| "grad_norm": 1.3956533495293986, | |
| "learning_rate": 8.407887192541176e-07, | |
| "loss": 2.1918, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.3516483516483517, | |
| "eval_loss": 2.2138054370880127, | |
| "eval_runtime": 94.5042, | |
| "eval_samples_per_second": 34.686, | |
| "eval_steps_per_second": 0.868, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.4065934065934065, | |
| "grad_norm": 1.403182174578336, | |
| "learning_rate": 8.337092316301222e-07, | |
| "loss": 2.1896, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.4065934065934065, | |
| "eval_loss": 2.2118804454803467, | |
| "eval_runtime": 95.8227, | |
| "eval_samples_per_second": 34.209, | |
| "eval_steps_per_second": 0.856, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.4615384615384617, | |
| "grad_norm": 1.455355254263044, | |
| "learning_rate": 8.265069924917924e-07, | |
| "loss": 2.2064, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 3.4615384615384617, | |
| "eval_loss": 2.2100589275360107, | |
| "eval_runtime": 94.8251, | |
| "eval_samples_per_second": 34.569, | |
| "eval_steps_per_second": 0.865, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 3.5164835164835164, | |
| "grad_norm": 1.3983545229342624, | |
| "learning_rate": 8.191846511088434e-07, | |
| "loss": 2.1783, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.5164835164835164, | |
| "eval_loss": 2.2082486152648926, | |
| "eval_runtime": 95.215, | |
| "eval_samples_per_second": 34.427, | |
| "eval_steps_per_second": 0.861, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.571428571428571, | |
| "grad_norm": 1.4400799384553278, | |
| "learning_rate": 8.117449009293668e-07, | |
| "loss": 2.1767, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 3.571428571428571, | |
| "eval_loss": 2.2065377235412598, | |
| "eval_runtime": 95.7035, | |
| "eval_samples_per_second": 34.252, | |
| "eval_steps_per_second": 0.857, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 3.6263736263736264, | |
| "grad_norm": 1.3475863787147715, | |
| "learning_rate": 8.041904785890748e-07, | |
| "loss": 2.1903, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.6263736263736264, | |
| "eval_loss": 2.20478892326355, | |
| "eval_runtime": 94.3907, | |
| "eval_samples_per_second": 34.728, | |
| "eval_steps_per_second": 0.869, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.6813186813186816, | |
| "grad_norm": 1.3998921895857097, | |
| "learning_rate": 7.96524162904657e-07, | |
| "loss": 2.1832, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 3.6813186813186816, | |
| "eval_loss": 2.2030811309814453, | |
| "eval_runtime": 96.3082, | |
| "eval_samples_per_second": 34.037, | |
| "eval_steps_per_second": 0.851, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 3.7362637362637363, | |
| "grad_norm": 1.4095299216187385, | |
| "learning_rate": 7.8874877385162e-07, | |
| "loss": 2.175, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.7362637362637363, | |
| "eval_loss": 2.2014122009277344, | |
| "eval_runtime": 94.5209, | |
| "eval_samples_per_second": 34.68, | |
| "eval_steps_per_second": 0.868, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.791208791208791, | |
| "grad_norm": 1.4014291539296442, | |
| "learning_rate": 7.808671715269894e-07, | |
| "loss": 2.1822, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 3.791208791208791, | |
| "eval_loss": 2.199869155883789, | |
| "eval_runtime": 96.9073, | |
| "eval_samples_per_second": 33.826, | |
| "eval_steps_per_second": 0.846, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 1.4012685963925429, | |
| "learning_rate": 7.728822550972522e-07, | |
| "loss": 2.1737, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "eval_loss": 2.1982617378234863, | |
| "eval_runtime": 94.1727, | |
| "eval_samples_per_second": 34.808, | |
| "eval_steps_per_second": 0.871, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.901098901098901, | |
| "grad_norm": 1.429348338650559, | |
| "learning_rate": 7.647969617319282e-07, | |
| "loss": 2.1792, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 3.901098901098901, | |
| "eval_loss": 2.1967613697052, | |
| "eval_runtime": 96.0694, | |
| "eval_samples_per_second": 34.121, | |
| "eval_steps_per_second": 0.854, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 3.956043956043956, | |
| "grad_norm": 1.417580581225819, | |
| "learning_rate": 7.566142655231621e-07, | |
| "loss": 2.1815, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.956043956043956, | |
| "eval_loss": 2.1953213214874268, | |
| "eval_runtime": 94.1895, | |
| "eval_samples_per_second": 34.802, | |
| "eval_steps_per_second": 0.871, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.010989010989011, | |
| "grad_norm": 1.3810060520884369, | |
| "learning_rate": 7.483371763917345e-07, | |
| "loss": 2.1754, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 4.010989010989011, | |
| "eval_loss": 2.19380259513855, | |
| "eval_runtime": 95.3311, | |
| "eval_samples_per_second": 34.385, | |
| "eval_steps_per_second": 0.86, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 4.065934065934066, | |
| "grad_norm": 1.3763895625796003, | |
| "learning_rate": 7.399687389798932e-07, | |
| "loss": 2.1689, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.065934065934066, | |
| "eval_loss": 2.192410945892334, | |
| "eval_runtime": 94.2976, | |
| "eval_samples_per_second": 34.762, | |
| "eval_steps_per_second": 0.87, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.1208791208791204, | |
| "grad_norm": 1.4248863012562965, | |
| "learning_rate": 7.315120315314134e-07, | |
| "loss": 2.1618, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.1208791208791204, | |
| "eval_loss": 2.1910791397094727, | |
| "eval_runtime": 95.4906, | |
| "eval_samples_per_second": 34.328, | |
| "eval_steps_per_second": 0.859, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.175824175824176, | |
| "grad_norm": 1.3935879500953352, | |
| "learning_rate": 7.229701647592965e-07, | |
| "loss": 2.1729, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.175824175824176, | |
| "eval_loss": 2.1896872520446777, | |
| "eval_runtime": 94.2919, | |
| "eval_samples_per_second": 34.764, | |
| "eval_steps_per_second": 0.87, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.230769230769231, | |
| "grad_norm": 1.3317520241186727, | |
| "learning_rate": 7.14346280701527e-07, | |
| "loss": 2.1576, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 4.230769230769231, | |
| "eval_loss": 2.188359498977661, | |
| "eval_runtime": 95.1008, | |
| "eval_samples_per_second": 34.469, | |
| "eval_steps_per_second": 0.862, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 1.4243898404737314, | |
| "learning_rate": 7.056435515653058e-07, | |
| "loss": 2.1719, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "eval_loss": 2.1870105266571045, | |
| "eval_runtime": 95.4713, | |
| "eval_samples_per_second": 34.335, | |
| "eval_steps_per_second": 0.859, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.34065934065934, | |
| "grad_norm": 1.4055766721244105, | |
| "learning_rate": 6.968651785601858e-07, | |
| "loss": 2.1569, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 4.34065934065934, | |
| "eval_loss": 2.1857264041900635, | |
| "eval_runtime": 94.6681, | |
| "eval_samples_per_second": 34.626, | |
| "eval_steps_per_second": 0.866, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 4.395604395604396, | |
| "grad_norm": 1.4109071900833123, | |
| "learning_rate": 6.88014390720541e-07, | |
| "loss": 2.1602, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.395604395604396, | |
| "eval_loss": 2.1845154762268066, | |
| "eval_runtime": 96.5176, | |
| "eval_samples_per_second": 33.963, | |
| "eval_steps_per_second": 0.85, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.450549450549451, | |
| "grad_norm": 1.3966564162441588, | |
| "learning_rate": 6.790944437177983e-07, | |
| "loss": 2.1444, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 4.450549450549451, | |
| "eval_loss": 2.183314800262451, | |
| "eval_runtime": 94.7139, | |
| "eval_samples_per_second": 34.61, | |
| "eval_steps_per_second": 0.866, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 4.5054945054945055, | |
| "grad_norm": 1.4078350070104653, | |
| "learning_rate": 6.701086186628731e-07, | |
| "loss": 2.1507, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.5054945054945055, | |
| "eval_loss": 2.182114362716675, | |
| "eval_runtime": 95.3459, | |
| "eval_samples_per_second": 34.38, | |
| "eval_steps_per_second": 0.86, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.56043956043956, | |
| "grad_norm": 1.3979239637585987, | |
| "learning_rate": 6.610602208992452e-07, | |
| "loss": 2.1562, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 4.56043956043956, | |
| "eval_loss": 2.1809184551239014, | |
| "eval_runtime": 94.8819, | |
| "eval_samples_per_second": 34.548, | |
| "eval_steps_per_second": 0.864, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 1.4173323621445668, | |
| "learning_rate": 6.519525787871234e-07, | |
| "loss": 2.1507, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "eval_loss": 2.179769992828369, | |
| "eval_runtime": 94.615, | |
| "eval_samples_per_second": 34.646, | |
| "eval_steps_per_second": 0.867, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.670329670329671, | |
| "grad_norm": 1.4495494766154244, | |
| "learning_rate": 6.427890424791413e-07, | |
| "loss": 2.1456, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 4.670329670329671, | |
| "eval_loss": 2.1786587238311768, | |
| "eval_runtime": 95.2766, | |
| "eval_samples_per_second": 34.405, | |
| "eval_steps_per_second": 0.861, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 4.725274725274725, | |
| "grad_norm": 1.3978628311813146, | |
| "learning_rate": 6.335729826880389e-07, | |
| "loss": 2.1527, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.725274725274725, | |
| "eval_loss": 2.177562713623047, | |
| "eval_runtime": 95.0839, | |
| "eval_samples_per_second": 34.475, | |
| "eval_steps_per_second": 0.862, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.78021978021978, | |
| "grad_norm": 1.3616533998206952, | |
| "learning_rate": 6.243077894467799e-07, | |
| "loss": 2.1523, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 4.78021978021978, | |
| "eval_loss": 2.1765596866607666, | |
| "eval_runtime": 95.2854, | |
| "eval_samples_per_second": 34.402, | |
| "eval_steps_per_second": 0.861, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 4.835164835164835, | |
| "grad_norm": 1.40687668442058, | |
| "learning_rate": 6.149968708615634e-07, | |
| "loss": 2.1514, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.835164835164835, | |
| "eval_loss": 2.175467014312744, | |
| "eval_runtime": 94.6288, | |
| "eval_samples_per_second": 34.641, | |
| "eval_steps_per_second": 0.867, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.8901098901098905, | |
| "grad_norm": 1.3739992174314783, | |
| "learning_rate": 6.056436518581864e-07, | |
| "loss": 2.1363, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 4.8901098901098905, | |
| "eval_loss": 2.174509048461914, | |
| "eval_runtime": 95.7561, | |
| "eval_samples_per_second": 34.233, | |
| "eval_steps_per_second": 0.856, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 4.945054945054945, | |
| "grad_norm": 1.4046699052180842, | |
| "learning_rate": 5.962515729222208e-07, | |
| "loss": 2.1515, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.945054945054945, | |
| "eval_loss": 2.173485040664673, | |
| "eval_runtime": 94.9608, | |
| "eval_samples_per_second": 34.52, | |
| "eval_steps_per_second": 0.864, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.3856994205796709, | |
| "learning_rate": 5.868240888334652e-07, | |
| "loss": 2.1446, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.1724860668182373, | |
| "eval_runtime": 95.9629, | |
| "eval_samples_per_second": 34.159, | |
| "eval_steps_per_second": 0.854, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 5.054945054945055, | |
| "grad_norm": 1.359907555644168, | |
| "learning_rate": 5.773646673951406e-07, | |
| "loss": 2.1449, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.054945054945055, | |
| "eval_loss": 2.1716203689575195, | |
| "eval_runtime": 94.6944, | |
| "eval_samples_per_second": 34.617, | |
| "eval_steps_per_second": 0.866, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.1098901098901095, | |
| "grad_norm": 1.397318242165103, | |
| "learning_rate": 5.67876788158294e-07, | |
| "loss": 2.151, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 5.1098901098901095, | |
| "eval_loss": 2.170758008956909, | |
| "eval_runtime": 94.1168, | |
| "eval_samples_per_second": 34.829, | |
| "eval_steps_per_second": 0.871, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 5.164835164835165, | |
| "grad_norm": 1.4236578949268166, | |
| "learning_rate": 5.58363941141881e-07, | |
| "loss": 2.135, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.164835164835165, | |
| "eval_loss": 2.1698837280273438, | |
| "eval_runtime": 95.886, | |
| "eval_samples_per_second": 34.186, | |
| "eval_steps_per_second": 0.855, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.21978021978022, | |
| "grad_norm": 1.3923617942385993, | |
| "learning_rate": 5.48829625548999e-07, | |
| "loss": 2.1378, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 5.21978021978022, | |
| "eval_loss": 2.169065475463867, | |
| "eval_runtime": 94.683, | |
| "eval_samples_per_second": 34.621, | |
| "eval_steps_per_second": 0.866, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 5.274725274725275, | |
| "grad_norm": 1.3673257335946538, | |
| "learning_rate": 5.392773484797406e-07, | |
| "loss": 2.1312, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.274725274725275, | |
| "eval_loss": 2.1681604385375977, | |
| "eval_runtime": 96.7854, | |
| "eval_samples_per_second": 33.869, | |
| "eval_steps_per_second": 0.847, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.329670329670329, | |
| "grad_norm": 1.376334253291603, | |
| "learning_rate": 5.297106236411431e-07, | |
| "loss": 2.1334, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 5.329670329670329, | |
| "eval_loss": 2.1673035621643066, | |
| "eval_runtime": 94.0748, | |
| "eval_samples_per_second": 34.845, | |
| "eval_steps_per_second": 0.872, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 5.384615384615385, | |
| "grad_norm": 1.4116620429830442, | |
| "learning_rate": 5.201329700547076e-07, | |
| "loss": 2.1287, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.384615384615385, | |
| "eval_loss": 2.1665842533111572, | |
| "eval_runtime": 97.1342, | |
| "eval_samples_per_second": 33.747, | |
| "eval_steps_per_second": 0.844, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.43956043956044, | |
| "grad_norm": 1.3882977350312697, | |
| "learning_rate": 5.105479107619623e-07, | |
| "loss": 2.1371, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 5.43956043956044, | |
| "eval_loss": 2.1657893657684326, | |
| "eval_runtime": 94.6092, | |
| "eval_samples_per_second": 34.648, | |
| "eval_steps_per_second": 0.867, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 5.4945054945054945, | |
| "grad_norm": 1.3387430328337173, | |
| "learning_rate": 5.009589715285492e-07, | |
| "loss": 2.1283, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.4945054945054945, | |
| "eval_loss": 2.1649773120880127, | |
| "eval_runtime": 95.6455, | |
| "eval_samples_per_second": 34.272, | |
| "eval_steps_per_second": 0.857, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.549450549450549, | |
| "grad_norm": 1.3369955383377354, | |
| "learning_rate": 4.913696795473058e-07, | |
| "loss": 2.1304, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 5.549450549450549, | |
| "eval_loss": 2.1642661094665527, | |
| "eval_runtime": 94.082, | |
| "eval_samples_per_second": 34.842, | |
| "eval_steps_per_second": 0.872, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 5.604395604395604, | |
| "grad_norm": 1.4094356210593881, | |
| "learning_rate": 4.81783562140825e-07, | |
| "loss": 2.1263, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.604395604395604, | |
| "eval_loss": 2.1635727882385254, | |
| "eval_runtime": 96.1766, | |
| "eval_samples_per_second": 34.083, | |
| "eval_steps_per_second": 0.853, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.65934065934066, | |
| "grad_norm": 1.304106079776388, | |
| "learning_rate": 4.722041454639645e-07, | |
| "loss": 2.1367, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 5.65934065934066, | |
| "eval_loss": 2.1628613471984863, | |
| "eval_runtime": 94.3841, | |
| "eval_samples_per_second": 34.73, | |
| "eval_steps_per_second": 0.869, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 1.3827334256393926, | |
| "learning_rate": 4.626349532067879e-07, | |
| "loss": 2.1207, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "eval_loss": 2.162167549133301, | |
| "eval_runtime": 95.9116, | |
| "eval_samples_per_second": 34.177, | |
| "eval_steps_per_second": 0.855, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.769230769230769, | |
| "grad_norm": 1.4133703140162626, | |
| "learning_rate": 4.530795052984104e-07, | |
| "loss": 2.126, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 5.769230769230769, | |
| "eval_loss": 2.161437511444092, | |
| "eval_runtime": 94.7934, | |
| "eval_samples_per_second": 34.58, | |
| "eval_steps_per_second": 0.865, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 5.824175824175824, | |
| "grad_norm": 1.3623534884797142, | |
| "learning_rate": 4.4354131661222993e-07, | |
| "loss": 2.1178, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.824175824175824, | |
| "eval_loss": 2.1607697010040283, | |
| "eval_runtime": 95.1583, | |
| "eval_samples_per_second": 34.448, | |
| "eval_steps_per_second": 0.862, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.8791208791208796, | |
| "grad_norm": 1.3721824145937465, | |
| "learning_rate": 4.3402389567301687e-07, | |
| "loss": 2.1317, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 5.8791208791208796, | |
| "eval_loss": 2.1601507663726807, | |
| "eval_runtime": 95.1179, | |
| "eval_samples_per_second": 34.462, | |
| "eval_steps_per_second": 0.862, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 5.934065934065934, | |
| "grad_norm": 1.354947196331287, | |
| "learning_rate": 4.245307433663388e-07, | |
| "loss": 2.1208, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.934065934065934, | |
| "eval_loss": 2.15952730178833, | |
| "eval_runtime": 95.2363, | |
| "eval_samples_per_second": 34.42, | |
| "eval_steps_per_second": 0.861, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.989010989010989, | |
| "grad_norm": 1.3836862806091863, | |
| "learning_rate": 4.1506535165079637e-07, | |
| "loss": 2.131, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 5.989010989010989, | |
| "eval_loss": 2.1588995456695557, | |
| "eval_runtime": 95.977, | |
| "eval_samples_per_second": 34.154, | |
| "eval_steps_per_second": 0.854, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 6.043956043956044, | |
| "grad_norm": 1.4174811691080422, | |
| "learning_rate": 4.056312022735417e-07, | |
| "loss": 2.1282, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.043956043956044, | |
| "eval_loss": 2.1583850383758545, | |
| "eval_runtime": 94.9634, | |
| "eval_samples_per_second": 34.519, | |
| "eval_steps_per_second": 0.863, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.0989010989010985, | |
| "grad_norm": 1.386136241074018, | |
| "learning_rate": 3.962317654895532e-07, | |
| "loss": 2.1071, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 6.0989010989010985, | |
| "eval_loss": 2.157827854156494, | |
| "eval_runtime": 96.6235, | |
| "eval_samples_per_second": 33.925, | |
| "eval_steps_per_second": 0.849, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 1.382143872347298, | |
| "learning_rate": 3.86870498785139e-07, | |
| "loss": 2.1152, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "eval_loss": 2.1572675704956055, | |
| "eval_runtime": 94.9844, | |
| "eval_samples_per_second": 34.511, | |
| "eval_steps_per_second": 0.863, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.208791208791209, | |
| "grad_norm": 1.3117267968176445, | |
| "learning_rate": 3.7755084560613454e-07, | |
| "loss": 2.1274, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 6.208791208791209, | |
| "eval_loss": 2.156782865524292, | |
| "eval_runtime": 95.0906, | |
| "eval_samples_per_second": 34.472, | |
| "eval_steps_per_second": 0.862, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 6.263736263736264, | |
| "grad_norm": 1.3153022809674055, | |
| "learning_rate": 3.682762340912681e-07, | |
| "loss": 2.125, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.263736263736264, | |
| "eval_loss": 2.156236410140991, | |
| "eval_runtime": 94.7673, | |
| "eval_samples_per_second": 34.59, | |
| "eval_steps_per_second": 0.865, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.318681318681318, | |
| "grad_norm": 1.363719531307913, | |
| "learning_rate": 3.590500758111537e-07, | |
| "loss": 2.1253, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 6.318681318681318, | |
| "eval_loss": 2.1556880474090576, | |
| "eval_runtime": 95.0783, | |
| "eval_samples_per_second": 34.477, | |
| "eval_steps_per_second": 0.862, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 6.373626373626374, | |
| "grad_norm": 1.3306699270632527, | |
| "learning_rate": 3.498757645133805e-07, | |
| "loss": 2.1105, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.373626373626374, | |
| "eval_loss": 2.1551740169525146, | |
| "eval_runtime": 95.3795, | |
| "eval_samples_per_second": 34.368, | |
| "eval_steps_per_second": 0.86, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.428571428571429, | |
| "grad_norm": 1.4013786507282588, | |
| "learning_rate": 3.4075667487415785e-07, | |
| "loss": 2.1233, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 6.428571428571429, | |
| "eval_loss": 2.1547253131866455, | |
| "eval_runtime": 94.9401, | |
| "eval_samples_per_second": 34.527, | |
| "eval_steps_per_second": 0.864, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 6.483516483516484, | |
| "grad_norm": 1.340212819021932, | |
| "learning_rate": 3.3169616125697485e-07, | |
| "loss": 2.1082, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.483516483516484, | |
| "eval_loss": 2.1542816162109375, | |
| "eval_runtime": 96.1807, | |
| "eval_samples_per_second": 34.082, | |
| "eval_steps_per_second": 0.853, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.538461538461538, | |
| "grad_norm": 1.37559843039388, | |
| "learning_rate": 3.2269755647873214e-07, | |
| "loss": 2.116, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 6.538461538461538, | |
| "eval_loss": 2.153905153274536, | |
| "eval_runtime": 94.5357, | |
| "eval_samples_per_second": 34.675, | |
| "eval_steps_per_second": 0.867, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 6.593406593406593, | |
| "grad_norm": 1.3234676252365452, | |
| "learning_rate": 3.137641705838003e-07, | |
| "loss": 2.114, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.593406593406593, | |
| "eval_loss": 2.153465747833252, | |
| "eval_runtime": 96.7145, | |
| "eval_samples_per_second": 33.894, | |
| "eval_steps_per_second": 0.848, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.648351648351649, | |
| "grad_norm": 1.2963273381270386, | |
| "learning_rate": 3.048992896264527e-07, | |
| "loss": 2.1025, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 6.648351648351649, | |
| "eval_loss": 2.153031587600708, | |
| "eval_runtime": 94.9067, | |
| "eval_samples_per_second": 34.539, | |
| "eval_steps_per_second": 0.864, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 6.7032967032967035, | |
| "grad_norm": 1.363956310159158, | |
| "learning_rate": 2.9610617446212494e-07, | |
| "loss": 2.1174, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.7032967032967035, | |
| "eval_loss": 2.1526174545288086, | |
| "eval_runtime": 96.5514, | |
| "eval_samples_per_second": 33.951, | |
| "eval_steps_per_second": 0.849, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.758241758241758, | |
| "grad_norm": 1.324164018147815, | |
| "learning_rate": 2.8738805954794295e-07, | |
| "loss": 2.1158, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 6.758241758241758, | |
| "eval_loss": 2.1521835327148438, | |
| "eval_runtime": 94.9388, | |
| "eval_samples_per_second": 34.527, | |
| "eval_steps_per_second": 0.864, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 6.813186813186813, | |
| "grad_norm": 1.3310397406861454, | |
| "learning_rate": 2.7874815175296e-07, | |
| "loss": 2.1118, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.813186813186813, | |
| "eval_loss": 2.1518325805664062, | |
| "eval_runtime": 95.7818, | |
| "eval_samples_per_second": 34.224, | |
| "eval_steps_per_second": 0.856, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.868131868131869, | |
| "grad_norm": 1.306713284641784, | |
| "learning_rate": 2.7018962917854416e-07, | |
| "loss": 2.1219, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 6.868131868131869, | |
| "eval_loss": 2.1515119075775146, | |
| "eval_runtime": 94.8621, | |
| "eval_samples_per_second": 34.555, | |
| "eval_steps_per_second": 0.864, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 6.923076923076923, | |
| "grad_norm": 1.328321525865242, | |
| "learning_rate": 2.61715639989346e-07, | |
| "loss": 2.1088, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.923076923076923, | |
| "eval_loss": 2.1511785984039307, | |
| "eval_runtime": 94.9757, | |
| "eval_samples_per_second": 34.514, | |
| "eval_steps_per_second": 0.863, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.978021978021978, | |
| "grad_norm": 1.3354659608167203, | |
| "learning_rate": 2.5332930125527785e-07, | |
| "loss": 2.1188, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 6.978021978021978, | |
| "eval_loss": 2.150792360305786, | |
| "eval_runtime": 95.0995, | |
| "eval_samples_per_second": 34.469, | |
| "eval_steps_per_second": 0.862, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 7.032967032967033, | |
| "grad_norm": 1.3252421337619178, | |
| "learning_rate": 2.4503369780493216e-07, | |
| "loss": 2.0958, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 7.032967032967033, | |
| "eval_loss": 2.150482416152954, | |
| "eval_runtime": 94.5987, | |
| "eval_samples_per_second": 34.652, | |
| "eval_steps_per_second": 0.867, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 7.087912087912088, | |
| "grad_norm": 1.3025182371568629, | |
| "learning_rate": 2.3683188109085877e-07, | |
| "loss": 2.1162, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 7.087912087912088, | |
| "eval_loss": 2.150195598602295, | |
| "eval_runtime": 95.7892, | |
| "eval_samples_per_second": 34.221, | |
| "eval_steps_per_second": 0.856, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 7.142857142857143, | |
| "grad_norm": 1.3417203401169715, | |
| "learning_rate": 2.2872686806712032e-07, | |
| "loss": 2.112, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.142857142857143, | |
| "eval_loss": 2.14986515045166, | |
| "eval_runtime": 94.108, | |
| "eval_samples_per_second": 34.832, | |
| "eval_steps_per_second": 0.871, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.197802197802198, | |
| "grad_norm": 1.3125833946773793, | |
| "learning_rate": 2.2072164007953515e-07, | |
| "loss": 2.1108, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 7.197802197802198, | |
| "eval_loss": 2.1495869159698486, | |
| "eval_runtime": 96.3106, | |
| "eval_samples_per_second": 34.036, | |
| "eval_steps_per_second": 0.851, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 7.252747252747253, | |
| "grad_norm": 1.3727056594091913, | |
| "learning_rate": 2.1281914176902106e-07, | |
| "loss": 2.1105, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 7.252747252747253, | |
| "eval_loss": 2.149327039718628, | |
| "eval_runtime": 94.0785, | |
| "eval_samples_per_second": 34.843, | |
| "eval_steps_per_second": 0.872, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 7.3076923076923075, | |
| "grad_norm": 1.26720608418739, | |
| "learning_rate": 2.050222799884387e-07, | |
| "loss": 2.1119, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 7.3076923076923075, | |
| "eval_loss": 2.1490209102630615, | |
| "eval_runtime": 95.0812, | |
| "eval_samples_per_second": 34.476, | |
| "eval_steps_per_second": 0.862, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 7.362637362637362, | |
| "grad_norm": 1.3075408289058195, | |
| "learning_rate": 1.9733392273333595e-07, | |
| "loss": 2.1125, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 7.362637362637362, | |
| "eval_loss": 2.148756980895996, | |
| "eval_runtime": 94.7034, | |
| "eval_samples_per_second": 34.613, | |
| "eval_steps_per_second": 0.866, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 7.417582417582418, | |
| "grad_norm": 1.338274034103587, | |
| "learning_rate": 1.8975689808698546e-07, | |
| "loss": 2.1085, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 7.417582417582418, | |
| "eval_loss": 2.1485321521759033, | |
| "eval_runtime": 95.2917, | |
| "eval_samples_per_second": 34.4, | |
| "eval_steps_per_second": 0.861, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 7.472527472527473, | |
| "grad_norm": 1.2732739133631568, | |
| "learning_rate": 1.8229399318010234e-07, | |
| "loss": 2.113, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 7.472527472527473, | |
| "eval_loss": 2.1483404636383057, | |
| "eval_runtime": 96.15, | |
| "eval_samples_per_second": 34.093, | |
| "eval_steps_per_second": 0.853, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 7.527472527472527, | |
| "grad_norm": 1.3397177765715196, | |
| "learning_rate": 1.7494795316562787e-07, | |
| "loss": 2.1022, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 7.527472527472527, | |
| "eval_loss": 2.1481196880340576, | |
| "eval_runtime": 94.6054, | |
| "eval_samples_per_second": 34.649, | |
| "eval_steps_per_second": 0.867, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 7.582417582417582, | |
| "grad_norm": 1.315974901665471, | |
| "learning_rate": 1.6772148020895227e-07, | |
| "loss": 2.1005, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.582417582417582, | |
| "eval_loss": 2.1478824615478516, | |
| "eval_runtime": 96.7642, | |
| "eval_samples_per_second": 33.876, | |
| "eval_steps_per_second": 0.847, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.637362637362637, | |
| "grad_norm": 1.3175415298356188, | |
| "learning_rate": 1.6061723249395103e-07, | |
| "loss": 2.1061, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 7.637362637362637, | |
| "eval_loss": 2.147655963897705, | |
| "eval_runtime": 94.8865, | |
| "eval_samples_per_second": 34.547, | |
| "eval_steps_per_second": 0.864, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "grad_norm": 1.2676400902435017, | |
| "learning_rate": 1.536378232452003e-07, | |
| "loss": 2.1113, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "eval_loss": 2.147427797317505, | |
| "eval_runtime": 96.4923, | |
| "eval_samples_per_second": 33.972, | |
| "eval_steps_per_second": 0.85, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.747252747252747, | |
| "grad_norm": 1.3178958103097314, | |
| "learning_rate": 1.4678581976672748e-07, | |
| "loss": 2.0939, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 7.747252747252747, | |
| "eval_loss": 2.147228479385376, | |
| "eval_runtime": 94.325, | |
| "eval_samples_per_second": 34.752, | |
| "eval_steps_per_second": 0.869, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 7.802197802197802, | |
| "grad_norm": 1.3384998637586858, | |
| "learning_rate": 1.4006374249765596e-07, | |
| "loss": 2.0993, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 7.802197802197802, | |
| "eval_loss": 2.147052764892578, | |
| "eval_runtime": 96.9054, | |
| "eval_samples_per_second": 33.827, | |
| "eval_steps_per_second": 0.846, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 7.857142857142857, | |
| "grad_norm": 1.280750721967852, | |
| "learning_rate": 1.3347406408508694e-07, | |
| "loss": 2.1115, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 7.857142857142857, | |
| "eval_loss": 2.146883249282837, | |
| "eval_runtime": 94.446, | |
| "eval_samples_per_second": 34.708, | |
| "eval_steps_per_second": 0.868, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 7.912087912087912, | |
| "grad_norm": 1.3140429519277008, | |
| "learning_rate": 1.2701920847456166e-07, | |
| "loss": 2.1043, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 7.912087912087912, | |
| "eval_loss": 2.146697998046875, | |
| "eval_runtime": 95.4996, | |
| "eval_samples_per_second": 34.325, | |
| "eval_steps_per_second": 0.859, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 7.967032967032967, | |
| "grad_norm": 1.3312499353255274, | |
| "learning_rate": 1.2070155001843835e-07, | |
| "loss": 2.1032, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 7.967032967032967, | |
| "eval_loss": 2.1465156078338623, | |
| "eval_runtime": 93.9989, | |
| "eval_samples_per_second": 34.873, | |
| "eval_steps_per_second": 0.872, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 8.021978021978022, | |
| "grad_norm": 1.3390325157168175, | |
| "learning_rate": 1.1452341260251019e-07, | |
| "loss": 2.0988, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 8.021978021978022, | |
| "eval_loss": 2.1463658809661865, | |
| "eval_runtime": 94.8926, | |
| "eval_samples_per_second": 34.544, | |
| "eval_steps_per_second": 0.864, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 8.076923076923077, | |
| "grad_norm": 1.3132771567223507, | |
| "learning_rate": 1.084870687911889e-07, | |
| "loss": 2.1021, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 8.076923076923077, | |
| "eval_loss": 2.146247625350952, | |
| "eval_runtime": 96.2255, | |
| "eval_samples_per_second": 34.066, | |
| "eval_steps_per_second": 0.852, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 8.131868131868131, | |
| "grad_norm": 1.2967777616488498, | |
| "learning_rate": 1.0259473899156429e-07, | |
| "loss": 2.0972, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 8.131868131868131, | |
| "eval_loss": 2.1461329460144043, | |
| "eval_runtime": 94.5501, | |
| "eval_samples_per_second": 34.669, | |
| "eval_steps_per_second": 0.867, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 8.186813186813186, | |
| "grad_norm": 1.2698397159733246, | |
| "learning_rate": 9.684859063665057e-08, | |
| "loss": 2.1034, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 8.186813186813186, | |
| "eval_loss": 2.1460211277008057, | |
| "eval_runtime": 95.3329, | |
| "eval_samples_per_second": 34.385, | |
| "eval_steps_per_second": 0.86, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 8.241758241758241, | |
| "grad_norm": 1.278484842006247, | |
| "learning_rate": 9.125073738811917e-08, | |
| "loss": 2.0955, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.241758241758241, | |
| "eval_loss": 2.1458938121795654, | |
| "eval_runtime": 94.9309, | |
| "eval_samples_per_second": 34.53, | |
| "eval_steps_per_second": 0.864, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.296703296703297, | |
| "grad_norm": 1.289197769580351, | |
| "learning_rate": 8.580323835880859e-08, | |
| "loss": 2.0997, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 8.296703296703297, | |
| "eval_loss": 2.1457700729370117, | |
| "eval_runtime": 94.6214, | |
| "eval_samples_per_second": 34.643, | |
| "eval_steps_per_second": 0.867, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 8.351648351648352, | |
| "grad_norm": 1.301153991983438, | |
| "learning_rate": 8.050809735530207e-08, | |
| "loss": 2.1016, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 8.351648351648352, | |
| "eval_loss": 2.1456449031829834, | |
| "eval_runtime": 95.3277, | |
| "eval_samples_per_second": 34.387, | |
| "eval_steps_per_second": 0.86, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 8.406593406593407, | |
| "grad_norm": 1.3044699064545437, | |
| "learning_rate": 7.53672621408472e-08, | |
| "loss": 2.107, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 8.406593406593407, | |
| "eval_loss": 2.145549774169922, | |
| "eval_runtime": 93.7346, | |
| "eval_samples_per_second": 34.971, | |
| "eval_steps_per_second": 0.875, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 8.461538461538462, | |
| "grad_norm": 1.2805052222372935, | |
| "learning_rate": 7.038262371889159e-08, | |
| "loss": 2.1033, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 8.461538461538462, | |
| "eval_loss": 2.145460605621338, | |
| "eval_runtime": 95.8972, | |
| "eval_samples_per_second": 34.182, | |
| "eval_steps_per_second": 0.855, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 8.516483516483516, | |
| "grad_norm": 1.3344128534699025, | |
| "learning_rate": 6.555601563749674e-08, | |
| "loss": 2.1081, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 8.516483516483516, | |
| "eval_loss": 2.1453983783721924, | |
| "eval_runtime": 94.7645, | |
| "eval_samples_per_second": 34.591, | |
| "eval_steps_per_second": 0.865, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "grad_norm": 1.3534141294417172, | |
| "learning_rate": 6.088921331488566e-08, | |
| "loss": 2.1007, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "eval_loss": 2.1453309059143066, | |
| "eval_runtime": 95.9005, | |
| "eval_samples_per_second": 34.181, | |
| "eval_steps_per_second": 0.855, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 8.626373626373626, | |
| "grad_norm": 1.289360061293496, | |
| "learning_rate": 5.6383933386374316e-08, | |
| "loss": 2.0954, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 8.626373626373626, | |
| "eval_loss": 2.1452713012695312, | |
| "eval_runtime": 94.327, | |
| "eval_samples_per_second": 34.751, | |
| "eval_steps_per_second": 0.869, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 8.68131868131868, | |
| "grad_norm": 1.290799173451955, | |
| "learning_rate": 5.204183307292409e-08, | |
| "loss": 2.0966, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.68131868131868, | |
| "eval_loss": 2.1452112197875977, | |
| "eval_runtime": 96.6287, | |
| "eval_samples_per_second": 33.924, | |
| "eval_steps_per_second": 0.849, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.736263736263737, | |
| "grad_norm": 1.296710622293866, | |
| "learning_rate": 4.786450957155064e-08, | |
| "loss": 2.105, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 8.736263736263737, | |
| "eval_loss": 2.1451542377471924, | |
| "eval_runtime": 94.7724, | |
| "eval_samples_per_second": 34.588, | |
| "eval_steps_per_second": 0.865, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 8.791208791208792, | |
| "grad_norm": 1.293112762829761, | |
| "learning_rate": 4.385349946781136e-08, | |
| "loss": 2.11, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.791208791208792, | |
| "eval_loss": 2.145106315612793, | |
| "eval_runtime": 95.5587, | |
| "eval_samples_per_second": 34.304, | |
| "eval_steps_per_second": 0.858, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.846153846153847, | |
| "grad_norm": 1.326895910564294, | |
| "learning_rate": 4.0010278170587884e-08, | |
| "loss": 2.1025, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 8.846153846153847, | |
| "eval_loss": 2.1450610160827637, | |
| "eval_runtime": 94.083, | |
| "eval_samples_per_second": 34.842, | |
| "eval_steps_per_second": 0.872, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 8.901098901098901, | |
| "grad_norm": 1.303529256363753, | |
| "learning_rate": 3.633625936937229e-08, | |
| "loss": 2.1057, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 8.901098901098901, | |
| "eval_loss": 2.145014762878418, | |
| "eval_runtime": 94.2778, | |
| "eval_samples_per_second": 34.77, | |
| "eval_steps_per_second": 0.87, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 8.956043956043956, | |
| "grad_norm": 1.300189968606814, | |
| "learning_rate": 3.28327945142558e-08, | |
| "loss": 2.1084, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 8.956043956043956, | |
| "eval_loss": 2.1449670791625977, | |
| "eval_runtime": 95.579, | |
| "eval_samples_per_second": 34.296, | |
| "eval_steps_per_second": 0.858, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 9.010989010989011, | |
| "grad_norm": 1.3121642088661138, | |
| "learning_rate": 2.950117231881183e-08, | |
| "loss": 2.0948, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 9.010989010989011, | |
| "eval_loss": 2.144935131072998, | |
| "eval_runtime": 93.9326, | |
| "eval_samples_per_second": 34.897, | |
| "eval_steps_per_second": 0.873, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 9.065934065934066, | |
| "grad_norm": 1.2914729270696104, | |
| "learning_rate": 2.634261828605594e-08, | |
| "loss": 2.1031, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 9.065934065934066, | |
| "eval_loss": 2.144901752471924, | |
| "eval_runtime": 96.1619, | |
| "eval_samples_per_second": 34.088, | |
| "eval_steps_per_second": 0.853, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 9.12087912087912, | |
| "grad_norm": 1.2899551643117746, | |
| "learning_rate": 2.335829425765712e-08, | |
| "loss": 2.0946, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 9.12087912087912, | |
| "eval_loss": 2.1448748111724854, | |
| "eval_runtime": 93.6382, | |
| "eval_samples_per_second": 35.007, | |
| "eval_steps_per_second": 0.876, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 9.175824175824175, | |
| "grad_norm": 1.2788813311509164, | |
| "learning_rate": 2.0549297986566183e-08, | |
| "loss": 2.1076, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 9.175824175824175, | |
| "eval_loss": 2.144841194152832, | |
| "eval_runtime": 96.4177, | |
| "eval_samples_per_second": 33.998, | |
| "eval_steps_per_second": 0.85, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 1.3297319077943937, | |
| "learning_rate": 1.7916662733218846e-08, | |
| "loss": 2.0962, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "eval_loss": 2.144815683364868, | |
| "eval_runtime": 94.5433, | |
| "eval_samples_per_second": 34.672, | |
| "eval_steps_per_second": 0.867, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.285714285714286, | |
| "grad_norm": 1.3729180320680576, | |
| "learning_rate": 1.5461356885461075e-08, | |
| "loss": 2.0884, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 9.285714285714286, | |
| "eval_loss": 2.1447927951812744, | |
| "eval_runtime": 96.9528, | |
| "eval_samples_per_second": 33.81, | |
| "eval_steps_per_second": 0.846, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 9.340659340659341, | |
| "grad_norm": 1.3282581119274621, | |
| "learning_rate": 1.3184283602337864e-08, | |
| "loss": 2.1016, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 9.340659340659341, | |
| "eval_loss": 2.144777536392212, | |
| "eval_runtime": 94.2281, | |
| "eval_samples_per_second": 34.788, | |
| "eval_steps_per_second": 0.87, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 9.395604395604396, | |
| "grad_norm": 1.303774253858923, | |
| "learning_rate": 1.1086280481875653e-08, | |
| "loss": 2.1091, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 9.395604395604396, | |
| "eval_loss": 2.144756555557251, | |
| "eval_runtime": 96.7444, | |
| "eval_samples_per_second": 33.883, | |
| "eval_steps_per_second": 0.848, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 9.45054945054945, | |
| "grad_norm": 1.3340713352584999, | |
| "learning_rate": 9.168119252979945e-09, | |
| "loss": 2.1084, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 9.45054945054945, | |
| "eval_loss": 2.1447436809539795, | |
| "eval_runtime": 94.7907, | |
| "eval_samples_per_second": 34.581, | |
| "eval_steps_per_second": 0.865, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 9.505494505494505, | |
| "grad_norm": 1.297522419820979, | |
| "learning_rate": 7.430505491563099e-09, | |
| "loss": 2.1069, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 9.505494505494505, | |
| "eval_loss": 2.14473295211792, | |
| "eval_runtime": 95.2303, | |
| "eval_samples_per_second": 34.422, | |
| "eval_steps_per_second": 0.861, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 9.56043956043956, | |
| "grad_norm": 1.2976358260740801, | |
| "learning_rate": 5.874078361005563e-09, | |
| "loss": 2.1049, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 9.56043956043956, | |
| "eval_loss": 2.1447255611419678, | |
| "eval_runtime": 94.6371, | |
| "eval_samples_per_second": 34.638, | |
| "eval_steps_per_second": 0.866, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 9.615384615384615, | |
| "grad_norm": 1.30150242446251, | |
| "learning_rate": 4.499410377045765e-09, | |
| "loss": 2.0981, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 9.615384615384615, | |
| "eval_loss": 2.144716739654541, | |
| "eval_runtime": 94.4817, | |
| "eval_samples_per_second": 34.695, | |
| "eval_steps_per_second": 0.868, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 9.67032967032967, | |
| "grad_norm": 1.265689030842284, | |
| "learning_rate": 3.3070071971867398e-09, | |
| "loss": 2.0975, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 9.67032967032967, | |
| "eval_loss": 2.1447131633758545, | |
| "eval_runtime": 97.3588, | |
| "eval_samples_per_second": 33.669, | |
| "eval_steps_per_second": 0.842, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 9.725274725274724, | |
| "grad_norm": 1.3221353338950448, | |
| "learning_rate": 2.297307434694473e-09, | |
| "loss": 2.1033, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 9.725274725274724, | |
| "eval_loss": 2.14471173286438, | |
| "eval_runtime": 94.4717, | |
| "eval_samples_per_second": 34.698, | |
| "eval_steps_per_second": 0.868, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 9.780219780219781, | |
| "grad_norm": 1.2607874314626535, | |
| "learning_rate": 1.4706824972591237e-09, | |
| "loss": 2.1034, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 9.780219780219781, | |
| "eval_loss": 2.1447081565856934, | |
| "eval_runtime": 96.6148, | |
| "eval_samples_per_second": 33.929, | |
| "eval_steps_per_second": 0.849, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 9.835164835164836, | |
| "grad_norm": 1.293461540963835, | |
| "learning_rate": 8.274364503760845e-10, | |
| "loss": 2.0956, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 9.835164835164836, | |
| "eval_loss": 2.1447083950042725, | |
| "eval_runtime": 94.3064, | |
| "eval_samples_per_second": 34.759, | |
| "eval_steps_per_second": 0.87, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 9.89010989010989, | |
| "grad_norm": 1.279822041703267, | |
| "learning_rate": 3.678059054988969e-10, | |
| "loss": 2.0917, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.89010989010989, | |
| "eval_loss": 2.1447057723999023, | |
| "eval_runtime": 96.7952, | |
| "eval_samples_per_second": 33.865, | |
| "eval_steps_per_second": 0.847, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.945054945054945, | |
| "grad_norm": 1.3339227803991875, | |
| "learning_rate": 9.19599330039822e-11, | |
| "loss": 2.0983, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 9.945054945054945, | |
| "eval_loss": 2.144705295562744, | |
| "eval_runtime": 93.8029, | |
| "eval_samples_per_second": 34.946, | |
| "eval_steps_per_second": 0.874, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.2734998688150378, | |
| "learning_rate": 0.0, | |
| "loss": 2.1039, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.1447036266326904, | |
| "eval_runtime": 97.1323, | |
| "eval_samples_per_second": 33.748, | |
| "eval_steps_per_second": 0.844, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 910, | |
| "total_flos": 7.930133386100736e+16, | |
| "train_loss": 2.201316048024775, | |
| "train_runtime": 48928.7509, | |
| "train_samples_per_second": 5.948, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 910, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.930133386100736e+16, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |