| { | |
| "best_global_step": 410, | |
| "best_metric": 0.14746543778801843, | |
| "best_model_checkpoint": "out_qwen_0.6b_sft_distilled/checkpoint-410", | |
| "epoch": 6.721311475409836, | |
| "eval_steps": 10, | |
| "global_step": 410, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08196721311475409, | |
| "grad_norm": 131.30086444913783, | |
| "learning_rate": 4.0816326530612243e-07, | |
| "loss": 40.5707, | |
| "step": 5, | |
| "true_loss": 4.9328 | |
| }, | |
| { | |
| "epoch": 0.16393442622950818, | |
| "grad_norm": 126.20257823342612, | |
| "learning_rate": 9.183673469387756e-07, | |
| "loss": 40.4496, | |
| "step": 10, | |
| "true_loss": 4.9664 | |
| }, | |
| { | |
| "epoch": 0.16393442622950818, | |
| "eval_accuracy": 0.004608294930875576, | |
| "eval_loss": 5.019261360168457, | |
| "eval_runtime": 8.3229, | |
| "eval_samples_per_second": 52.145, | |
| "eval_steps_per_second": 6.608, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2459016393442623, | |
| "grad_norm": 136.9898759427637, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 40.502, | |
| "step": 15, | |
| "true_loss": 4.9781 | |
| }, | |
| { | |
| "epoch": 0.32786885245901637, | |
| "grad_norm": 134.72385927894973, | |
| "learning_rate": 1.938775510204082e-06, | |
| "loss": 39.6527, | |
| "step": 20, | |
| "true_loss": 4.9395 | |
| }, | |
| { | |
| "epoch": 0.32786885245901637, | |
| "eval_accuracy": 0.004608294930875576, | |
| "eval_loss": 4.9670939445495605, | |
| "eval_runtime": 7.9853, | |
| "eval_samples_per_second": 54.35, | |
| "eval_steps_per_second": 6.888, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4098360655737705, | |
| "grad_norm": 127.00331303837481, | |
| "learning_rate": 2.4489795918367347e-06, | |
| "loss": 38.9625, | |
| "step": 25, | |
| "true_loss": 4.9176 | |
| }, | |
| { | |
| "epoch": 0.4918032786885246, | |
| "grad_norm": 111.05596081816127, | |
| "learning_rate": 2.959183673469388e-06, | |
| "loss": 38.8523, | |
| "step": 30, | |
| "true_loss": 4.9895 | |
| }, | |
| { | |
| "epoch": 0.4918032786885246, | |
| "eval_accuracy": 0.009216589861751152, | |
| "eval_loss": 4.8343892097473145, | |
| "eval_runtime": 8.399, | |
| "eval_samples_per_second": 51.673, | |
| "eval_steps_per_second": 6.548, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5737704918032787, | |
| "grad_norm": 127.72432425565634, | |
| "learning_rate": 3.469387755102041e-06, | |
| "loss": 38.366, | |
| "step": 35, | |
| "true_loss": 4.7629 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 142.80923150687772, | |
| "learning_rate": 3.979591836734694e-06, | |
| "loss": 38.0703, | |
| "step": 40, | |
| "true_loss": 4.8902 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "eval_accuracy": 0.055299539170506916, | |
| "eval_loss": 4.662118434906006, | |
| "eval_runtime": 8.4731, | |
| "eval_samples_per_second": 51.221, | |
| "eval_steps_per_second": 6.491, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7377049180327869, | |
| "grad_norm": 179.79048183030648, | |
| "learning_rate": 4.489795918367348e-06, | |
| "loss": 36.2355, | |
| "step": 45, | |
| "true_loss": 4.6008 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "grad_norm": 161.88532993207818, | |
| "learning_rate": 5e-06, | |
| "loss": 37.6594, | |
| "step": 50, | |
| "true_loss": 5.0719 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "eval_accuracy": 0.08294930875576037, | |
| "eval_loss": 4.533751964569092, | |
| "eval_runtime": 8.6568, | |
| "eval_samples_per_second": 50.134, | |
| "eval_steps_per_second": 6.353, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9016393442622951, | |
| "grad_norm": 151.13368850588557, | |
| "learning_rate": 4.943052391799545e-06, | |
| "loss": 36.9232, | |
| "step": 55, | |
| "true_loss": 4.5199 | |
| }, | |
| { | |
| "epoch": 0.9836065573770492, | |
| "grad_norm": 140.76185960403066, | |
| "learning_rate": 4.886104783599089e-06, | |
| "loss": 35.987, | |
| "step": 60, | |
| "true_loss": 4.3872 | |
| }, | |
| { | |
| "epoch": 0.9836065573770492, | |
| "eval_accuracy": 0.08064516129032258, | |
| "eval_loss": 4.438742160797119, | |
| "eval_runtime": 8.6755, | |
| "eval_samples_per_second": 50.026, | |
| "eval_steps_per_second": 6.34, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0655737704918034, | |
| "grad_norm": 141.24088109006144, | |
| "learning_rate": 4.829157175398634e-06, | |
| "loss": 35.8602, | |
| "step": 65, | |
| "true_loss": 4.6277 | |
| }, | |
| { | |
| "epoch": 1.1475409836065573, | |
| "grad_norm": 147.2087879935333, | |
| "learning_rate": 4.772209567198178e-06, | |
| "loss": 35.6707, | |
| "step": 70, | |
| "true_loss": 4.1293 | |
| }, | |
| { | |
| "epoch": 1.1475409836065573, | |
| "eval_accuracy": 0.08294930875576037, | |
| "eval_loss": 4.400156497955322, | |
| "eval_runtime": 8.477, | |
| "eval_samples_per_second": 51.198, | |
| "eval_steps_per_second": 6.488, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.2295081967213115, | |
| "grad_norm": 153.44325788545655, | |
| "learning_rate": 4.7152619589977225e-06, | |
| "loss": 34.8141, | |
| "step": 75, | |
| "true_loss": 4.2855 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 167.21816733466747, | |
| "learning_rate": 4.658314350797267e-06, | |
| "loss": 35.2213, | |
| "step": 80, | |
| "true_loss": 4.4329 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "eval_accuracy": 0.08755760368663594, | |
| "eval_loss": 4.335811614990234, | |
| "eval_runtime": 8.385, | |
| "eval_samples_per_second": 51.759, | |
| "eval_steps_per_second": 6.559, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3934426229508197, | |
| "grad_norm": 170.8547829819815, | |
| "learning_rate": 4.601366742596811e-06, | |
| "loss": 34.6405, | |
| "step": 85, | |
| "true_loss": 4.2484 | |
| }, | |
| { | |
| "epoch": 1.4754098360655736, | |
| "grad_norm": 169.3659623205823, | |
| "learning_rate": 4.544419134396356e-06, | |
| "loss": 34.6621, | |
| "step": 90, | |
| "true_loss": 4.5617 | |
| }, | |
| { | |
| "epoch": 1.4754098360655736, | |
| "eval_accuracy": 0.10829493087557604, | |
| "eval_loss": 4.2690629959106445, | |
| "eval_runtime": 8.5736, | |
| "eval_samples_per_second": 50.62, | |
| "eval_steps_per_second": 6.415, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.5573770491803278, | |
| "grad_norm": 181.5354290153052, | |
| "learning_rate": 4.4874715261959e-06, | |
| "loss": 33.5805, | |
| "step": 95, | |
| "true_loss": 4.2242 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "grad_norm": 183.60203299469077, | |
| "learning_rate": 4.4305239179954446e-06, | |
| "loss": 34.323, | |
| "step": 100, | |
| "true_loss": 4.3387 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "eval_accuracy": 0.10368663594470046, | |
| "eval_loss": 4.227273464202881, | |
| "eval_runtime": 8.642, | |
| "eval_samples_per_second": 50.22, | |
| "eval_steps_per_second": 6.364, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.721311475409836, | |
| "grad_norm": 170.66504985673134, | |
| "learning_rate": 4.373576309794989e-06, | |
| "loss": 32.0365, | |
| "step": 105, | |
| "true_loss": 3.9484 | |
| }, | |
| { | |
| "epoch": 1.8032786885245902, | |
| "grad_norm": 185.72351413214275, | |
| "learning_rate": 4.316628701594533e-06, | |
| "loss": 33.875, | |
| "step": 110, | |
| "true_loss": 4.1586 | |
| }, | |
| { | |
| "epoch": 1.8032786885245902, | |
| "eval_accuracy": 0.11290322580645161, | |
| "eval_loss": 4.191784381866455, | |
| "eval_runtime": 8.026, | |
| "eval_samples_per_second": 54.074, | |
| "eval_steps_per_second": 6.853, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.8852459016393444, | |
| "grad_norm": 187.82807734370155, | |
| "learning_rate": 4.259681093394078e-06, | |
| "loss": 33.4, | |
| "step": 115, | |
| "true_loss": 4.2566 | |
| }, | |
| { | |
| "epoch": 1.9672131147540983, | |
| "grad_norm": 177.04120464657095, | |
| "learning_rate": 4.202733485193622e-06, | |
| "loss": 32.768, | |
| "step": 120, | |
| "true_loss": 4.1711 | |
| }, | |
| { | |
| "epoch": 1.9672131147540983, | |
| "eval_accuracy": 0.10138248847926268, | |
| "eval_loss": 4.166411876678467, | |
| "eval_runtime": 8.3731, | |
| "eval_samples_per_second": 51.833, | |
| "eval_steps_per_second": 6.569, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0491803278688523, | |
| "grad_norm": 175.70043001685525, | |
| "learning_rate": 4.145785876993167e-06, | |
| "loss": 32.9279, | |
| "step": 125, | |
| "true_loss": 4.2443 | |
| }, | |
| { | |
| "epoch": 2.1311475409836067, | |
| "grad_norm": 211.66606785751807, | |
| "learning_rate": 4.088838268792711e-06, | |
| "loss": 31.4897, | |
| "step": 130, | |
| "true_loss": 3.9807 | |
| }, | |
| { | |
| "epoch": 2.1311475409836067, | |
| "eval_accuracy": 0.09907834101382489, | |
| "eval_loss": 4.117466449737549, | |
| "eval_runtime": 9.4127, | |
| "eval_samples_per_second": 46.108, | |
| "eval_steps_per_second": 5.843, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.2131147540983607, | |
| "grad_norm": 243.03840327182303, | |
| "learning_rate": 4.0318906605922555e-06, | |
| "loss": 31.5314, | |
| "step": 135, | |
| "true_loss": 3.9421 | |
| }, | |
| { | |
| "epoch": 2.2950819672131146, | |
| "grad_norm": 220.78266878880433, | |
| "learning_rate": 3.9749430523918e-06, | |
| "loss": 31.4336, | |
| "step": 140, | |
| "true_loss": 3.7703 | |
| }, | |
| { | |
| "epoch": 2.2950819672131146, | |
| "eval_accuracy": 0.1336405529953917, | |
| "eval_loss": 4.065812110900879, | |
| "eval_runtime": 8.6071, | |
| "eval_samples_per_second": 50.423, | |
| "eval_steps_per_second": 6.39, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.3770491803278686, | |
| "grad_norm": 196.6859886983302, | |
| "learning_rate": 3.917995444191344e-06, | |
| "loss": 31.3979, | |
| "step": 145, | |
| "true_loss": 3.8875 | |
| }, | |
| { | |
| "epoch": 2.459016393442623, | |
| "grad_norm": 209.14552747888038, | |
| "learning_rate": 3.861047835990889e-06, | |
| "loss": 31.5513, | |
| "step": 150, | |
| "true_loss": 3.65 | |
| }, | |
| { | |
| "epoch": 2.459016393442623, | |
| "eval_accuracy": 0.12903225806451613, | |
| "eval_loss": 4.045776844024658, | |
| "eval_runtime": 8.5013, | |
| "eval_samples_per_second": 51.051, | |
| "eval_steps_per_second": 6.47, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.540983606557377, | |
| "grad_norm": 205.92078421639843, | |
| "learning_rate": 3.804100227790433e-06, | |
| "loss": 31.4361, | |
| "step": 155, | |
| "true_loss": 3.7869 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "grad_norm": 219.604580334424, | |
| "learning_rate": 3.7471526195899776e-06, | |
| "loss": 31.6139, | |
| "step": 160, | |
| "true_loss": 3.9903 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "eval_accuracy": 0.1175115207373272, | |
| "eval_loss": 4.006894588470459, | |
| "eval_runtime": 8.1353, | |
| "eval_samples_per_second": 53.348, | |
| "eval_steps_per_second": 6.761, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.7049180327868854, | |
| "grad_norm": 221.00907729918933, | |
| "learning_rate": 3.690205011389522e-06, | |
| "loss": 31.0029, | |
| "step": 165, | |
| "true_loss": 3.9396 | |
| }, | |
| { | |
| "epoch": 2.7868852459016393, | |
| "grad_norm": 200.63567221965303, | |
| "learning_rate": 3.6332574031890664e-06, | |
| "loss": 30.4827, | |
| "step": 170, | |
| "true_loss": 4.0088 | |
| }, | |
| { | |
| "epoch": 2.7868852459016393, | |
| "eval_accuracy": 0.12442396313364056, | |
| "eval_loss": 3.991098403930664, | |
| "eval_runtime": 8.4689, | |
| "eval_samples_per_second": 51.246, | |
| "eval_steps_per_second": 6.494, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.8688524590163933, | |
| "grad_norm": 208.08258154815047, | |
| "learning_rate": 3.5763097949886104e-06, | |
| "loss": 30.7274, | |
| "step": 175, | |
| "true_loss": 3.8941 | |
| }, | |
| { | |
| "epoch": 2.9508196721311473, | |
| "grad_norm": 209.30561480651423, | |
| "learning_rate": 3.519362186788155e-06, | |
| "loss": 31.2113, | |
| "step": 180, | |
| "true_loss": 3.5918 | |
| }, | |
| { | |
| "epoch": 2.9508196721311473, | |
| "eval_accuracy": 0.1175115207373272, | |
| "eval_loss": 3.9841365814208984, | |
| "eval_runtime": 8.6637, | |
| "eval_samples_per_second": 50.094, | |
| "eval_steps_per_second": 6.348, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.0327868852459017, | |
| "grad_norm": 214.16917085440517, | |
| "learning_rate": 3.4624145785876997e-06, | |
| "loss": 31.0295, | |
| "step": 185, | |
| "true_loss": 3.5908 | |
| }, | |
| { | |
| "epoch": 3.1147540983606556, | |
| "grad_norm": 235.71482357282463, | |
| "learning_rate": 3.405466970387244e-06, | |
| "loss": 28.5428, | |
| "step": 190, | |
| "true_loss": 3.1442 | |
| }, | |
| { | |
| "epoch": 3.1147540983606556, | |
| "eval_accuracy": 0.12442396313364056, | |
| "eval_loss": 3.974285364151001, | |
| "eval_runtime": 8.0976, | |
| "eval_samples_per_second": 53.596, | |
| "eval_steps_per_second": 6.792, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.19672131147541, | |
| "grad_norm": 226.00461681805723, | |
| "learning_rate": 3.3485193621867885e-06, | |
| "loss": 29.5642, | |
| "step": 195, | |
| "true_loss": 3.5915 | |
| }, | |
| { | |
| "epoch": 3.278688524590164, | |
| "grad_norm": 233.95245184744422, | |
| "learning_rate": 3.291571753986333e-06, | |
| "loss": 29.4133, | |
| "step": 200, | |
| "true_loss": 3.518 | |
| }, | |
| { | |
| "epoch": 3.278688524590164, | |
| "eval_accuracy": 0.1313364055299539, | |
| "eval_loss": 3.9394891262054443, | |
| "eval_runtime": 8.5951, | |
| "eval_samples_per_second": 50.494, | |
| "eval_steps_per_second": 6.399, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.360655737704918, | |
| "grad_norm": 239.65764806983628, | |
| "learning_rate": 3.2346241457858773e-06, | |
| "loss": 29.0733, | |
| "step": 205, | |
| "true_loss": 3.4392 | |
| }, | |
| { | |
| "epoch": 3.442622950819672, | |
| "grad_norm": 251.9041666596011, | |
| "learning_rate": 3.1776765375854217e-06, | |
| "loss": 28.5826, | |
| "step": 210, | |
| "true_loss": 3.4814 | |
| }, | |
| { | |
| "epoch": 3.442622950819672, | |
| "eval_accuracy": 0.14055299539170507, | |
| "eval_loss": 3.9186437129974365, | |
| "eval_runtime": 8.3264, | |
| "eval_samples_per_second": 52.123, | |
| "eval_steps_per_second": 6.605, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.5245901639344264, | |
| "grad_norm": 236.49516114079387, | |
| "learning_rate": 3.120728929384966e-06, | |
| "loss": 29.3459, | |
| "step": 215, | |
| "true_loss": 3.6947 | |
| }, | |
| { | |
| "epoch": 3.6065573770491803, | |
| "grad_norm": 232.10135728893482, | |
| "learning_rate": 3.0637813211845106e-06, | |
| "loss": 29.1922, | |
| "step": 220, | |
| "true_loss": 3.7867 | |
| }, | |
| { | |
| "epoch": 3.6065573770491803, | |
| "eval_accuracy": 0.11981566820276497, | |
| "eval_loss": 3.924264669418335, | |
| "eval_runtime": 8.114, | |
| "eval_samples_per_second": 53.488, | |
| "eval_steps_per_second": 6.778, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.6885245901639343, | |
| "grad_norm": 248.9470759438453, | |
| "learning_rate": 3.0068337129840546e-06, | |
| "loss": 29.3719, | |
| "step": 225, | |
| "true_loss": 3.6912 | |
| }, | |
| { | |
| "epoch": 3.7704918032786887, | |
| "grad_norm": 242.5668319946587, | |
| "learning_rate": 2.949886104783599e-06, | |
| "loss": 29.0788, | |
| "step": 230, | |
| "true_loss": 3.7821 | |
| }, | |
| { | |
| "epoch": 3.7704918032786887, | |
| "eval_accuracy": 0.12672811059907835, | |
| "eval_loss": 3.9106783866882324, | |
| "eval_runtime": 8.4282, | |
| "eval_samples_per_second": 51.494, | |
| "eval_steps_per_second": 6.526, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.8524590163934427, | |
| "grad_norm": 258.17481354757325, | |
| "learning_rate": 2.892938496583144e-06, | |
| "loss": 28.8174, | |
| "step": 235, | |
| "true_loss": 3.3456 | |
| }, | |
| { | |
| "epoch": 3.9344262295081966, | |
| "grad_norm": 242.242892316644, | |
| "learning_rate": 2.8359908883826882e-06, | |
| "loss": 28.4613, | |
| "step": 240, | |
| "true_loss": 3.3777 | |
| }, | |
| { | |
| "epoch": 3.9344262295081966, | |
| "eval_accuracy": 0.12211981566820276, | |
| "eval_loss": 3.8972718715667725, | |
| "eval_runtime": 8.5279, | |
| "eval_samples_per_second": 50.892, | |
| "eval_steps_per_second": 6.449, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.016393442622951, | |
| "grad_norm": 249.19080164598319, | |
| "learning_rate": 2.7790432801822326e-06, | |
| "loss": 27.6907, | |
| "step": 245, | |
| "true_loss": 3.153 | |
| }, | |
| { | |
| "epoch": 4.098360655737705, | |
| "grad_norm": 290.1903243585321, | |
| "learning_rate": 2.722095671981777e-06, | |
| "loss": 26.9221, | |
| "step": 250, | |
| "true_loss": 3.2854 | |
| }, | |
| { | |
| "epoch": 4.098360655737705, | |
| "eval_accuracy": 0.1175115207373272, | |
| "eval_loss": 3.8916871547698975, | |
| "eval_runtime": 8.1923, | |
| "eval_samples_per_second": 52.977, | |
| "eval_steps_per_second": 6.714, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.180327868852459, | |
| "grad_norm": 284.2190675087926, | |
| "learning_rate": 2.6651480637813215e-06, | |
| "loss": 26.3206, | |
| "step": 255, | |
| "true_loss": 3.2506 | |
| }, | |
| { | |
| "epoch": 4.262295081967213, | |
| "grad_norm": 279.44061029669723, | |
| "learning_rate": 2.608200455580866e-06, | |
| "loss": 26.9143, | |
| "step": 260, | |
| "true_loss": 3.4412 | |
| }, | |
| { | |
| "epoch": 4.262295081967213, | |
| "eval_accuracy": 0.1152073732718894, | |
| "eval_loss": 3.8716788291931152, | |
| "eval_runtime": 8.5568, | |
| "eval_samples_per_second": 50.72, | |
| "eval_steps_per_second": 6.428, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.344262295081967, | |
| "grad_norm": 266.7499728501794, | |
| "learning_rate": 2.5512528473804103e-06, | |
| "loss": 26.4962, | |
| "step": 265, | |
| "true_loss": 3.5133 | |
| }, | |
| { | |
| "epoch": 4.426229508196721, | |
| "grad_norm": 260.78822590196535, | |
| "learning_rate": 2.4943052391799547e-06, | |
| "loss": 26.4451, | |
| "step": 270, | |
| "true_loss": 3.4446 | |
| }, | |
| { | |
| "epoch": 4.426229508196721, | |
| "eval_accuracy": 0.12211981566820276, | |
| "eval_loss": 3.8494653701782227, | |
| "eval_runtime": 8.4627, | |
| "eval_samples_per_second": 51.284, | |
| "eval_steps_per_second": 6.499, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.508196721311475, | |
| "grad_norm": 274.64077279341876, | |
| "learning_rate": 2.437357630979499e-06, | |
| "loss": 27.3761, | |
| "step": 275, | |
| "true_loss": 3.4453 | |
| }, | |
| { | |
| "epoch": 4.590163934426229, | |
| "grad_norm": 273.19374429695523, | |
| "learning_rate": 2.3804100227790436e-06, | |
| "loss": 27.4194, | |
| "step": 280, | |
| "true_loss": 3.1874 | |
| }, | |
| { | |
| "epoch": 4.590163934426229, | |
| "eval_accuracy": 0.11059907834101383, | |
| "eval_loss": 3.846774101257324, | |
| "eval_runtime": 8.5426, | |
| "eval_samples_per_second": 50.804, | |
| "eval_steps_per_second": 6.438, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.672131147540983, | |
| "grad_norm": 275.7740703438606, | |
| "learning_rate": 2.323462414578588e-06, | |
| "loss": 26.827, | |
| "step": 285, | |
| "true_loss": 3.3258 | |
| }, | |
| { | |
| "epoch": 4.754098360655737, | |
| "grad_norm": 274.35156164348126, | |
| "learning_rate": 2.2665148063781324e-06, | |
| "loss": 27.2383, | |
| "step": 290, | |
| "true_loss": 3.9754 | |
| }, | |
| { | |
| "epoch": 4.754098360655737, | |
| "eval_accuracy": 0.11981566820276497, | |
| "eval_loss": 3.8400866985321045, | |
| "eval_runtime": 8.4749, | |
| "eval_samples_per_second": 51.21, | |
| "eval_steps_per_second": 6.49, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.836065573770492, | |
| "grad_norm": 279.2476311679269, | |
| "learning_rate": 2.209567198177677e-06, | |
| "loss": 26.5837, | |
| "step": 295, | |
| "true_loss": 3.2732 | |
| }, | |
| { | |
| "epoch": 4.918032786885246, | |
| "grad_norm": 318.84649232107, | |
| "learning_rate": 2.1526195899772212e-06, | |
| "loss": 28.2213, | |
| "step": 300, | |
| "true_loss": 3.8258 | |
| }, | |
| { | |
| "epoch": 4.918032786885246, | |
| "eval_accuracy": 0.1336405529953917, | |
| "eval_loss": 3.828943967819214, | |
| "eval_runtime": 8.3482, | |
| "eval_samples_per_second": 51.987, | |
| "eval_steps_per_second": 6.588, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 281.39270714708135, | |
| "learning_rate": 2.0956719817767656e-06, | |
| "loss": 26.5872, | |
| "step": 305, | |
| "true_loss": 3.2237 | |
| }, | |
| { | |
| "epoch": 5.081967213114754, | |
| "grad_norm": 297.3835718534045, | |
| "learning_rate": 2.03872437357631e-06, | |
| "loss": 24.571, | |
| "step": 310, | |
| "true_loss": 3.346 | |
| }, | |
| { | |
| "epoch": 5.081967213114754, | |
| "eval_accuracy": 0.14516129032258066, | |
| "eval_loss": 3.8257129192352295, | |
| "eval_runtime": 8.4071, | |
| "eval_samples_per_second": 51.623, | |
| "eval_steps_per_second": 6.542, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.163934426229508, | |
| "grad_norm": 333.18631426892176, | |
| "learning_rate": 1.9817767653758545e-06, | |
| "loss": 25.2512, | |
| "step": 315, | |
| "true_loss": 3.185 | |
| }, | |
| { | |
| "epoch": 5.245901639344262, | |
| "grad_norm": 307.93977906152685, | |
| "learning_rate": 1.924829157175399e-06, | |
| "loss": 24.5613, | |
| "step": 320, | |
| "true_loss": 3.1895 | |
| }, | |
| { | |
| "epoch": 5.245901639344262, | |
| "eval_accuracy": 0.14285714285714285, | |
| "eval_loss": 3.8230037689208984, | |
| "eval_runtime": 8.2033, | |
| "eval_samples_per_second": 52.906, | |
| "eval_steps_per_second": 6.705, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.327868852459017, | |
| "grad_norm": 312.5942332522537, | |
| "learning_rate": 1.8678815489749433e-06, | |
| "loss": 25.0569, | |
| "step": 325, | |
| "true_loss": 3.3557 | |
| }, | |
| { | |
| "epoch": 5.409836065573771, | |
| "grad_norm": 300.21567029382476, | |
| "learning_rate": 1.8109339407744877e-06, | |
| "loss": 25.5947, | |
| "step": 330, | |
| "true_loss": 3.3142 | |
| }, | |
| { | |
| "epoch": 5.409836065573771, | |
| "eval_accuracy": 0.14285714285714285, | |
| "eval_loss": 3.8151462078094482, | |
| "eval_runtime": 8.197, | |
| "eval_samples_per_second": 52.946, | |
| "eval_steps_per_second": 6.71, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.491803278688525, | |
| "grad_norm": 355.0409546655278, | |
| "learning_rate": 1.753986332574032e-06, | |
| "loss": 25.8608, | |
| "step": 335, | |
| "true_loss": 3.0482 | |
| }, | |
| { | |
| "epoch": 5.573770491803279, | |
| "grad_norm": 328.72773533463106, | |
| "learning_rate": 1.6970387243735763e-06, | |
| "loss": 25.1268, | |
| "step": 340, | |
| "true_loss": 3.103 | |
| }, | |
| { | |
| "epoch": 5.573770491803279, | |
| "eval_accuracy": 0.1336405529953917, | |
| "eval_loss": 3.811136484146118, | |
| "eval_runtime": 8.3155, | |
| "eval_samples_per_second": 52.192, | |
| "eval_steps_per_second": 6.614, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.655737704918033, | |
| "grad_norm": 335.47496045434843, | |
| "learning_rate": 1.640091116173121e-06, | |
| "loss": 25.9661, | |
| "step": 345, | |
| "true_loss": 3.5002 | |
| }, | |
| { | |
| "epoch": 5.737704918032787, | |
| "grad_norm": 318.3200333649924, | |
| "learning_rate": 1.5831435079726654e-06, | |
| "loss": 24.7426, | |
| "step": 350, | |
| "true_loss": 3.4293 | |
| }, | |
| { | |
| "epoch": 5.737704918032787, | |
| "eval_accuracy": 0.1336405529953917, | |
| "eval_loss": 3.7999937534332275, | |
| "eval_runtime": 8.9261, | |
| "eval_samples_per_second": 48.621, | |
| "eval_steps_per_second": 6.162, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.8196721311475414, | |
| "grad_norm": 315.7081677451309, | |
| "learning_rate": 1.5261958997722096e-06, | |
| "loss": 25.5119, | |
| "step": 355, | |
| "true_loss": 3.0279 | |
| }, | |
| { | |
| "epoch": 5.901639344262295, | |
| "grad_norm": 313.72316359405403, | |
| "learning_rate": 1.469248291571754e-06, | |
| "loss": 24.6192, | |
| "step": 360, | |
| "true_loss": 3.0785 | |
| }, | |
| { | |
| "epoch": 5.901639344262295, | |
| "eval_accuracy": 0.14055299539170507, | |
| "eval_loss": 3.7833380699157715, | |
| "eval_runtime": 8.9156, | |
| "eval_samples_per_second": 48.679, | |
| "eval_steps_per_second": 6.169, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.983606557377049, | |
| "grad_norm": 337.09696857571805, | |
| "learning_rate": 1.4123006833712984e-06, | |
| "loss": 24.576, | |
| "step": 365, | |
| "true_loss": 3.0792 | |
| }, | |
| { | |
| "epoch": 6.065573770491803, | |
| "grad_norm": 312.44171671989244, | |
| "learning_rate": 1.355353075170843e-06, | |
| "loss": 23.0454, | |
| "step": 370, | |
| "true_loss": 2.8838 | |
| }, | |
| { | |
| "epoch": 6.065573770491803, | |
| "eval_accuracy": 0.14285714285714285, | |
| "eval_loss": 3.78341007232666, | |
| "eval_runtime": 8.7024, | |
| "eval_samples_per_second": 49.871, | |
| "eval_steps_per_second": 6.32, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.147540983606557, | |
| "grad_norm": 312.0953900031812, | |
| "learning_rate": 1.2984054669703875e-06, | |
| "loss": 22.3877, | |
| "step": 375, | |
| "true_loss": 2.4284 | |
| }, | |
| { | |
| "epoch": 6.229508196721311, | |
| "grad_norm": 335.94846858957845, | |
| "learning_rate": 1.2414578587699317e-06, | |
| "loss": 23.5471, | |
| "step": 380, | |
| "true_loss": 3.0217 | |
| }, | |
| { | |
| "epoch": 6.229508196721311, | |
| "eval_accuracy": 0.1382488479262673, | |
| "eval_loss": 3.793076753616333, | |
| "eval_runtime": 8.1781, | |
| "eval_samples_per_second": 53.068, | |
| "eval_steps_per_second": 6.725, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.311475409836065, | |
| "grad_norm": 341.87803857824105, | |
| "learning_rate": 1.1845102505694763e-06, | |
| "loss": 23.2389, | |
| "step": 385, | |
| "true_loss": 2.6483 | |
| }, | |
| { | |
| "epoch": 6.39344262295082, | |
| "grad_norm": 369.08934119445, | |
| "learning_rate": 1.1275626423690205e-06, | |
| "loss": 23.6875, | |
| "step": 390, | |
| "true_loss": 2.932 | |
| }, | |
| { | |
| "epoch": 6.39344262295082, | |
| "eval_accuracy": 0.14055299539170507, | |
| "eval_loss": 3.795403480529785, | |
| "eval_runtime": 8.1757, | |
| "eval_samples_per_second": 53.084, | |
| "eval_steps_per_second": 6.727, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.475409836065574, | |
| "grad_norm": 369.5208687625068, | |
| "learning_rate": 1.0706150341685651e-06, | |
| "loss": 23.193, | |
| "step": 395, | |
| "true_loss": 2.8789 | |
| }, | |
| { | |
| "epoch": 6.557377049180328, | |
| "grad_norm": 376.6391661100538, | |
| "learning_rate": 1.0136674259681093e-06, | |
| "loss": 23.5847, | |
| "step": 400, | |
| "true_loss": 2.9588 | |
| }, | |
| { | |
| "epoch": 6.557377049180328, | |
| "eval_accuracy": 0.14516129032258066, | |
| "eval_loss": 3.8012988567352295, | |
| "eval_runtime": 8.302, | |
| "eval_samples_per_second": 52.276, | |
| "eval_steps_per_second": 6.625, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.639344262295082, | |
| "grad_norm": 335.2314208261569, | |
| "learning_rate": 9.567198177676538e-07, | |
| "loss": 22.4865, | |
| "step": 405, | |
| "true_loss": 3.1291 | |
| }, | |
| { | |
| "epoch": 6.721311475409836, | |
| "grad_norm": 383.2496458341536, | |
| "learning_rate": 8.997722095671982e-07, | |
| "loss": 24.1513, | |
| "step": 410, | |
| "true_loss": 2.858 | |
| }, | |
| { | |
| "epoch": 6.721311475409836, | |
| "eval_accuracy": 0.14746543778801843, | |
| "eval_loss": 3.801600217819214, | |
| "eval_runtime": 8.4227, | |
| "eval_samples_per_second": 51.528, | |
| "eval_steps_per_second": 6.53, | |
| "step": 410 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 488, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |