| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7601094557616297, | |
| "global_step": 210000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.996983692635866e-05, | |
| "loss": 7.2434, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9939673852717336e-05, | |
| "loss": 6.3951, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 6.350970268249512, | |
| "eval_runtime": 3.8385, | |
| "eval_samples_per_second": 260.78, | |
| "eval_steps_per_second": 16.413, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9909510779075997e-05, | |
| "loss": 6.2791, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9879347705434663e-05, | |
| "loss": 6.2011, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 6.223337173461914, | |
| "eval_runtime": 3.7358, | |
| "eval_samples_per_second": 267.946, | |
| "eval_steps_per_second": 16.864, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.984918463179333e-05, | |
| "loss": 6.15, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9819021558152e-05, | |
| "loss": 6.121, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 6.134737014770508, | |
| "eval_runtime": 3.7442, | |
| "eval_samples_per_second": 267.346, | |
| "eval_steps_per_second": 16.826, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.978885848451066e-05, | |
| "loss": 6.0839, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9758695410869325e-05, | |
| "loss": 6.0626, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 6.063777923583984, | |
| "eval_runtime": 4.0904, | |
| "eval_samples_per_second": 244.72, | |
| "eval_steps_per_second": 15.402, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.972853233722799e-05, | |
| "loss": 6.0263, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.969836926358666e-05, | |
| "loss": 6.0177, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 6.02394962310791, | |
| "eval_runtime": 3.9573, | |
| "eval_samples_per_second": 252.948, | |
| "eval_steps_per_second": 15.92, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.966820618994532e-05, | |
| "loss": 5.9988, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.963804311630399e-05, | |
| "loss": 5.9921, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 6.0168046951293945, | |
| "eval_runtime": 4.0579, | |
| "eval_samples_per_second": 246.677, | |
| "eval_steps_per_second": 15.525, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9607940368809935e-05, | |
| "loss": 5.9751, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9577837621315885e-05, | |
| "loss": 5.9632, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 5.997592926025391, | |
| "eval_runtime": 4.2019, | |
| "eval_samples_per_second": 238.224, | |
| "eval_steps_per_second": 14.993, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.954767454767455e-05, | |
| "loss": 5.9386, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.951751147403322e-05, | |
| "loss": 5.9524, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 5.969239711761475, | |
| "eval_runtime": 4.0231, | |
| "eval_samples_per_second": 248.812, | |
| "eval_steps_per_second": 15.659, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.948734840039188e-05, | |
| "loss": 5.9376, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9457185326750546e-05, | |
| "loss": 5.9328, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 5.940969944000244, | |
| "eval_runtime": 3.8844, | |
| "eval_samples_per_second": 257.697, | |
| "eval_steps_per_second": 16.219, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.942702225310921e-05, | |
| "loss": 5.9177, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.939685917946787e-05, | |
| "loss": 5.9162, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 5.932608604431152, | |
| "eval_runtime": 4.0642, | |
| "eval_samples_per_second": 246.298, | |
| "eval_steps_per_second": 15.501, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.936669610582654e-05, | |
| "loss": 5.9054, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.933659335833249e-05, | |
| "loss": 5.8906, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 5.921965599060059, | |
| "eval_runtime": 4.2691, | |
| "eval_samples_per_second": 234.477, | |
| "eval_steps_per_second": 14.757, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9306430284691156e-05, | |
| "loss": 5.8952, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9276267211049823e-05, | |
| "loss": 5.8868, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 5.910747528076172, | |
| "eval_runtime": 4.3284, | |
| "eval_samples_per_second": 231.264, | |
| "eval_steps_per_second": 14.555, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.924610413740849e-05, | |
| "loss": 5.8829, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.921600138991443e-05, | |
| "loss": 5.8738, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 5.895788669586182, | |
| "eval_runtime": 4.2991, | |
| "eval_samples_per_second": 232.842, | |
| "eval_steps_per_second": 14.654, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.91858383162731e-05, | |
| "loss": 5.8717, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.915567524263177e-05, | |
| "loss": 5.8642, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 5.891711235046387, | |
| "eval_runtime": 4.3228, | |
| "eval_samples_per_second": 231.564, | |
| "eval_steps_per_second": 14.574, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9125512168990434e-05, | |
| "loss": 5.8667, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.909540942149638e-05, | |
| "loss": 5.8494, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 5.886107921600342, | |
| "eval_runtime": 4.4064, | |
| "eval_samples_per_second": 227.167, | |
| "eval_steps_per_second": 14.297, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.906524634785505e-05, | |
| "loss": 5.8369, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.903508327421371e-05, | |
| "loss": 5.8414, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 5.89373254776001, | |
| "eval_runtime": 4.3188, | |
| "eval_samples_per_second": 231.776, | |
| "eval_steps_per_second": 14.587, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.900492020057238e-05, | |
| "loss": 5.851, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.8974757126931045e-05, | |
| "loss": 5.8512, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 5.9001264572143555, | |
| "eval_runtime": 4.3173, | |
| "eval_samples_per_second": 231.857, | |
| "eval_steps_per_second": 14.592, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.8944594053289705e-05, | |
| "loss": 5.8471, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.8914491305795654e-05, | |
| "loss": 5.8319, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 5.870309829711914, | |
| "eval_runtime": 4.2282, | |
| "eval_samples_per_second": 236.743, | |
| "eval_steps_per_second": 14.9, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.888432823215432e-05, | |
| "loss": 5.8285, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.885416515851299e-05, | |
| "loss": 5.8282, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 5.834588050842285, | |
| "eval_runtime": 4.2534, | |
| "eval_samples_per_second": 235.344, | |
| "eval_steps_per_second": 14.812, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.882400208487165e-05, | |
| "loss": 5.8305, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.879383901123032e-05, | |
| "loss": 5.8159, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 5.825201034545898, | |
| "eval_runtime": 4.2051, | |
| "eval_samples_per_second": 238.046, | |
| "eval_steps_per_second": 14.982, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.876367593758898e-05, | |
| "loss": 5.8109, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.873357319009493e-05, | |
| "loss": 5.8206, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 5.839576244354248, | |
| "eval_runtime": 4.2748, | |
| "eval_samples_per_second": 234.162, | |
| "eval_steps_per_second": 14.737, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.87034101164536e-05, | |
| "loss": 5.8187, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8673247042812266e-05, | |
| "loss": 5.826, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 5.854990482330322, | |
| "eval_runtime": 6.3825, | |
| "eval_samples_per_second": 156.835, | |
| "eval_steps_per_second": 9.871, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8643083969170926e-05, | |
| "loss": 5.8221, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.861292089552959e-05, | |
| "loss": 5.8109, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 5.85267448425293, | |
| "eval_runtime": 4.2815, | |
| "eval_samples_per_second": 233.795, | |
| "eval_steps_per_second": 14.714, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.858275782188826e-05, | |
| "loss": 5.8124, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.855259474824693e-05, | |
| "loss": 5.8002, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 5.857957363128662, | |
| "eval_runtime": 4.2472, | |
| "eval_samples_per_second": 235.683, | |
| "eval_steps_per_second": 14.833, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.852243167460559e-05, | |
| "loss": 5.7933, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.849232892711154e-05, | |
| "loss": 5.7957, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 5.843862533569336, | |
| "eval_runtime": 4.2251, | |
| "eval_samples_per_second": 236.92, | |
| "eval_steps_per_second": 14.911, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8462165853470204e-05, | |
| "loss": 5.7919, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8432002779828864e-05, | |
| "loss": 5.8001, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 5.8175740242004395, | |
| "eval_runtime": 4.5898, | |
| "eval_samples_per_second": 218.094, | |
| "eval_steps_per_second": 13.726, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.840183970618754e-05, | |
| "loss": 5.7874, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.837173695869348e-05, | |
| "loss": 5.7836, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 5.7963480949401855, | |
| "eval_runtime": 4.2794, | |
| "eval_samples_per_second": 233.909, | |
| "eval_steps_per_second": 14.722, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.834157388505215e-05, | |
| "loss": 5.7915, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.8311410811410814e-05, | |
| "loss": 5.7797, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 5.796699047088623, | |
| "eval_runtime": 4.2933, | |
| "eval_samples_per_second": 233.155, | |
| "eval_steps_per_second": 14.674, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.828124773776948e-05, | |
| "loss": 5.7768, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.8251144990275424e-05, | |
| "loss": 5.7876, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 5.799530506134033, | |
| "eval_runtime": 4.2207, | |
| "eval_samples_per_second": 237.163, | |
| "eval_steps_per_second": 14.926, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.82209819166341e-05, | |
| "loss": 5.7904, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.819081884299276e-05, | |
| "loss": 5.7837, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 5.798836708068848, | |
| "eval_runtime": 4.2831, | |
| "eval_samples_per_second": 233.71, | |
| "eval_steps_per_second": 14.709, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.8160655769351425e-05, | |
| "loss": 5.778, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.813049269571009e-05, | |
| "loss": 5.7681, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 5.811764240264893, | |
| "eval_runtime": 4.3287, | |
| "eval_samples_per_second": 231.246, | |
| "eval_steps_per_second": 14.554, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.810032962206876e-05, | |
| "loss": 5.7695, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.80702268745747e-05, | |
| "loss": 5.7698, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 5.799587726593018, | |
| "eval_runtime": 6.2437, | |
| "eval_samples_per_second": 160.322, | |
| "eval_steps_per_second": 10.09, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.804006380093337e-05, | |
| "loss": 5.7613, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.8009900727292036e-05, | |
| "loss": 5.7875, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 5.817694664001465, | |
| "eval_runtime": 4.2624, | |
| "eval_samples_per_second": 234.843, | |
| "eval_steps_per_second": 14.78, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.7979737653650696e-05, | |
| "loss": 5.7868, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.794957458000936e-05, | |
| "loss": 5.7672, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 5.817095756530762, | |
| "eval_runtime": 4.3001, | |
| "eval_samples_per_second": 232.788, | |
| "eval_steps_per_second": 14.651, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.791947183251531e-05, | |
| "loss": 5.7585, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.788930875887398e-05, | |
| "loss": 5.77, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 5.829194068908691, | |
| "eval_runtime": 4.4257, | |
| "eval_samples_per_second": 226.177, | |
| "eval_steps_per_second": 14.235, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.785914568523264e-05, | |
| "loss": 5.7525, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.782898261159131e-05, | |
| "loss": 5.7534, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 5.81154203414917, | |
| "eval_runtime": 4.3328, | |
| "eval_samples_per_second": 231.028, | |
| "eval_steps_per_second": 14.54, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.7798819537949973e-05, | |
| "loss": 5.7679, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.776871679045592e-05, | |
| "loss": 5.7461, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 5.76007604598999, | |
| "eval_runtime": 4.2778, | |
| "eval_samples_per_second": 233.997, | |
| "eval_steps_per_second": 14.727, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.773855371681459e-05, | |
| "loss": 5.7546, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.770839064317326e-05, | |
| "loss": 5.7542, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 5.81342077255249, | |
| "eval_runtime": 4.3112, | |
| "eval_samples_per_second": 232.186, | |
| "eval_steps_per_second": 14.613, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.767822756953192e-05, | |
| "loss": 5.7467, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.764806449589059e-05, | |
| "loss": 5.7487, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 5.810147762298584, | |
| "eval_runtime": 4.2762, | |
| "eval_samples_per_second": 234.084, | |
| "eval_steps_per_second": 14.733, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.7617961748396534e-05, | |
| "loss": 5.7516, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.7587798674755194e-05, | |
| "loss": 5.7464, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 5.790091514587402, | |
| "eval_runtime": 6.3564, | |
| "eval_samples_per_second": 157.479, | |
| "eval_steps_per_second": 9.911, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.755763560111387e-05, | |
| "loss": 5.7518, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.752747252747253e-05, | |
| "loss": 5.7573, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 5.804274082183838, | |
| "eval_runtime": 4.355, | |
| "eval_samples_per_second": 229.852, | |
| "eval_steps_per_second": 14.466, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.7497309453831195e-05, | |
| "loss": 5.7512, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.746714638018986e-05, | |
| "loss": 5.7431, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 5.761765480041504, | |
| "eval_runtime": 4.3203, | |
| "eval_samples_per_second": 231.698, | |
| "eval_steps_per_second": 14.582, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.743704363269581e-05, | |
| "loss": 5.7573, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.740688055905447e-05, | |
| "loss": 5.7202, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 5.7786478996276855, | |
| "eval_runtime": 4.3352, | |
| "eval_samples_per_second": 230.9, | |
| "eval_steps_per_second": 14.532, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.737671748541314e-05, | |
| "loss": 5.7353, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7346554411771805e-05, | |
| "loss": 5.7476, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 5.780131816864014, | |
| "eval_runtime": 4.4034, | |
| "eval_samples_per_second": 227.326, | |
| "eval_steps_per_second": 14.307, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.731639133813047e-05, | |
| "loss": 5.7345, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7286288590636415e-05, | |
| "loss": 5.7416, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 5.7368245124816895, | |
| "eval_runtime": 4.2102, | |
| "eval_samples_per_second": 237.757, | |
| "eval_steps_per_second": 14.964, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.725612551699509e-05, | |
| "loss": 5.7451, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.722596244335375e-05, | |
| "loss": 5.7401, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 5.775325298309326, | |
| "eval_runtime": 4.2649, | |
| "eval_samples_per_second": 234.709, | |
| "eval_steps_per_second": 14.772, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.7195799369712416e-05, | |
| "loss": 5.7308, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.716563629607108e-05, | |
| "loss": 5.7401, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 5.7712297439575195, | |
| "eval_runtime": 4.3345, | |
| "eval_samples_per_second": 230.935, | |
| "eval_steps_per_second": 14.534, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.7135533548577026e-05, | |
| "loss": 5.7317, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.710537047493569e-05, | |
| "loss": 5.7336, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 5.742641925811768, | |
| "eval_runtime": 4.2969, | |
| "eval_samples_per_second": 232.958, | |
| "eval_steps_per_second": 14.662, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.707520740129436e-05, | |
| "loss": 5.7449, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.704510465380031e-05, | |
| "loss": 5.7297, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 5.769224643707275, | |
| "eval_runtime": 4.3211, | |
| "eval_samples_per_second": 231.651, | |
| "eval_steps_per_second": 14.579, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.701494158015897e-05, | |
| "loss": 5.7413, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.698477850651764e-05, | |
| "loss": 5.7347, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 5.765679359436035, | |
| "eval_runtime": 4.2691, | |
| "eval_samples_per_second": 234.477, | |
| "eval_steps_per_second": 14.757, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.69546154328763e-05, | |
| "loss": 5.7256, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.692445235923497e-05, | |
| "loss": 5.7183, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 5.7880048751831055, | |
| "eval_runtime": 8.1705, | |
| "eval_samples_per_second": 122.514, | |
| "eval_steps_per_second": 7.711, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.689428928559364e-05, | |
| "loss": 5.7377, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.6864126211952304e-05, | |
| "loss": 5.7239, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 5.784894943237305, | |
| "eval_runtime": 4.3979, | |
| "eval_samples_per_second": 227.609, | |
| "eval_steps_per_second": 14.325, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.6833963138310964e-05, | |
| "loss": 5.7332, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.680380006466963e-05, | |
| "loss": 5.7316, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 5.74093770980835, | |
| "eval_runtime": 4.3725, | |
| "eval_samples_per_second": 228.931, | |
| "eval_steps_per_second": 14.408, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.67736369910283e-05, | |
| "loss": 5.7227, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6743473917386965e-05, | |
| "loss": 5.7202, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 5.766174793243408, | |
| "eval_runtime": 4.2835, | |
| "eval_samples_per_second": 233.689, | |
| "eval_steps_per_second": 14.708, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.671337116989291e-05, | |
| "loss": 5.7194, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.668326842239886e-05, | |
| "loss": 5.7073, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 5.740816593170166, | |
| "eval_runtime": 4.2663, | |
| "eval_samples_per_second": 234.632, | |
| "eval_steps_per_second": 14.767, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6653105348757525e-05, | |
| "loss": 5.7176, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.662294227511619e-05, | |
| "loss": 5.7113, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 5.764217376708984, | |
| "eval_runtime": 4.4652, | |
| "eval_samples_per_second": 224.178, | |
| "eval_steps_per_second": 14.109, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.659277920147486e-05, | |
| "loss": 5.7094, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.656261612783352e-05, | |
| "loss": 5.722, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 5.7554473876953125, | |
| "eval_runtime": 4.3539, | |
| "eval_samples_per_second": 229.907, | |
| "eval_steps_per_second": 14.47, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.6532453054192186e-05, | |
| "loss": 5.7145, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.650228998055085e-05, | |
| "loss": 5.7077, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 5.74335241317749, | |
| "eval_runtime": 4.3356, | |
| "eval_samples_per_second": 230.882, | |
| "eval_steps_per_second": 14.531, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.64721872330568e-05, | |
| "loss": 5.7123, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.644202415941546e-05, | |
| "loss": 5.7163, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 5.77748441696167, | |
| "eval_runtime": 4.4579, | |
| "eval_samples_per_second": 224.543, | |
| "eval_steps_per_second": 14.132, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6411861085774136e-05, | |
| "loss": 5.6978, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6381698012132796e-05, | |
| "loss": 5.7185, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 5.755308151245117, | |
| "eval_runtime": 4.4657, | |
| "eval_samples_per_second": 224.155, | |
| "eval_steps_per_second": 14.108, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.635153493849146e-05, | |
| "loss": 5.7133, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.632137186485013e-05, | |
| "loss": 5.7126, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 5.742791175842285, | |
| "eval_runtime": 4.4874, | |
| "eval_samples_per_second": 223.069, | |
| "eval_steps_per_second": 14.039, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.62912087912088e-05, | |
| "loss": 5.7105, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.626104571756746e-05, | |
| "loss": 5.6955, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 5.750290870666504, | |
| "eval_runtime": 4.4288, | |
| "eval_samples_per_second": 226.023, | |
| "eval_steps_per_second": 14.225, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.6230882643926124e-05, | |
| "loss": 5.7056, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.6200779896432074e-05, | |
| "loss": 5.7177, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 5.7632975578308105, | |
| "eval_runtime": 4.4407, | |
| "eval_samples_per_second": 225.416, | |
| "eval_steps_per_second": 14.187, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.6170616822790734e-05, | |
| "loss": 5.6985, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.61404537491494e-05, | |
| "loss": 5.7103, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 5.735149383544922, | |
| "eval_runtime": 4.3259, | |
| "eval_samples_per_second": 231.399, | |
| "eval_steps_per_second": 14.564, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.611029067550807e-05, | |
| "loss": 5.7056, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.6080127601866735e-05, | |
| "loss": 5.7036, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 5.733882427215576, | |
| "eval_runtime": 4.2423, | |
| "eval_samples_per_second": 235.959, | |
| "eval_steps_per_second": 14.851, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.605002485437268e-05, | |
| "loss": 5.7037, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.601986178073135e-05, | |
| "loss": 5.7035, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 5.746898651123047, | |
| "eval_runtime": 4.2969, | |
| "eval_samples_per_second": 232.956, | |
| "eval_steps_per_second": 14.662, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.598969870709001e-05, | |
| "loss": 5.6979, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.595953563344868e-05, | |
| "loss": 5.6953, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 5.743001461029053, | |
| "eval_runtime": 6.5732, | |
| "eval_samples_per_second": 152.285, | |
| "eval_steps_per_second": 9.584, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.592943288595463e-05, | |
| "loss": 5.7201, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.5899269812313295e-05, | |
| "loss": 5.704, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 5.756634712219238, | |
| "eval_runtime": 4.4285, | |
| "eval_samples_per_second": 226.037, | |
| "eval_steps_per_second": 14.226, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.5869106738671955e-05, | |
| "loss": 5.7095, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.583894366503063e-05, | |
| "loss": 5.712, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 5.764980316162109, | |
| "eval_runtime": 4.3235, | |
| "eval_samples_per_second": 231.523, | |
| "eval_steps_per_second": 14.571, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.580884091753657e-05, | |
| "loss": 5.6976, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.577867784389523e-05, | |
| "loss": 5.7046, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 5.744942665100098, | |
| "eval_runtime": 4.3426, | |
| "eval_samples_per_second": 230.505, | |
| "eval_steps_per_second": 14.507, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.5748514770253906e-05, | |
| "loss": 5.7025, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.5718351696612566e-05, | |
| "loss": 5.7031, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 5.732196807861328, | |
| "eval_runtime": 4.4018, | |
| "eval_samples_per_second": 227.407, | |
| "eval_steps_per_second": 14.312, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.568818862297123e-05, | |
| "loss": 5.6871, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.56580255493299e-05, | |
| "loss": 5.6842, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 5.773156642913818, | |
| "eval_runtime": 4.3306, | |
| "eval_samples_per_second": 231.146, | |
| "eval_steps_per_second": 14.548, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.562786247568857e-05, | |
| "loss": 5.6853, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.559769940204723e-05, | |
| "loss": 5.7022, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 5.724014759063721, | |
| "eval_runtime": 4.268, | |
| "eval_samples_per_second": 234.536, | |
| "eval_steps_per_second": 14.761, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.5567536328405894e-05, | |
| "loss": 5.7029, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.553737325476456e-05, | |
| "loss": 5.707, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 5.71505880355835, | |
| "eval_runtime": 4.2511, | |
| "eval_samples_per_second": 235.471, | |
| "eval_steps_per_second": 14.82, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.550727050727051e-05, | |
| "loss": 5.7014, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.547710743362917e-05, | |
| "loss": 5.7068, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 5.703161239624023, | |
| "eval_runtime": 4.3019, | |
| "eval_samples_per_second": 232.687, | |
| "eval_steps_per_second": 14.645, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.5446944359987844e-05, | |
| "loss": 5.6946, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.5416781286346505e-05, | |
| "loss": 5.6892, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 5.7333149909973145, | |
| "eval_runtime": 4.2526, | |
| "eval_samples_per_second": 235.387, | |
| "eval_steps_per_second": 14.815, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.5386678538852454e-05, | |
| "loss": 5.6814, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.535651546521112e-05, | |
| "loss": 5.6979, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 5.712403297424316, | |
| "eval_runtime": 4.3234, | |
| "eval_samples_per_second": 231.532, | |
| "eval_steps_per_second": 14.572, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.532635239156979e-05, | |
| "loss": 5.6959, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.529618931792845e-05, | |
| "loss": 5.6791, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 5.754906177520752, | |
| "eval_runtime": 4.3238, | |
| "eval_samples_per_second": 231.508, | |
| "eval_steps_per_second": 14.57, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.5266026244287115e-05, | |
| "loss": 5.6984, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.5235923496793065e-05, | |
| "loss": 5.6953, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 5.720048427581787, | |
| "eval_runtime": 4.3352, | |
| "eval_samples_per_second": 230.899, | |
| "eval_steps_per_second": 14.532, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.5205760423151725e-05, | |
| "loss": 5.6924, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.51755973495104e-05, | |
| "loss": 5.6845, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 5.744686126708984, | |
| "eval_runtime": 4.3839, | |
| "eval_samples_per_second": 228.335, | |
| "eval_steps_per_second": 14.371, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.514543427586906e-05, | |
| "loss": 5.695, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.511533152837501e-05, | |
| "loss": 5.6872, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 5.723191738128662, | |
| "eval_runtime": 4.2942, | |
| "eval_samples_per_second": 233.107, | |
| "eval_steps_per_second": 14.671, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.5085168454733675e-05, | |
| "loss": 5.6841, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.505500538109234e-05, | |
| "loss": 5.687, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 5.738052845001221, | |
| "eval_runtime": 4.282, | |
| "eval_samples_per_second": 233.769, | |
| "eval_steps_per_second": 14.713, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.5024842307451e-05, | |
| "loss": 5.6913, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.499467923380967e-05, | |
| "loss": 5.69, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 5.709909915924072, | |
| "eval_runtime": 4.3445, | |
| "eval_samples_per_second": 230.406, | |
| "eval_steps_per_second": 14.501, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.496457648631562e-05, | |
| "loss": 5.6785, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.4934413412674286e-05, | |
| "loss": 5.6831, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 5.698389053344727, | |
| "eval_runtime": 6.3376, | |
| "eval_samples_per_second": 157.947, | |
| "eval_steps_per_second": 9.941, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.4904250339032946e-05, | |
| "loss": 5.6893, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.4874147591538896e-05, | |
| "loss": 5.682, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 5.747517108917236, | |
| "eval_runtime": 4.4117, | |
| "eval_samples_per_second": 226.897, | |
| "eval_steps_per_second": 14.28, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.484398451789756e-05, | |
| "loss": 5.6907, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.481382144425623e-05, | |
| "loss": 5.6771, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 5.721287727355957, | |
| "eval_runtime": 4.3352, | |
| "eval_samples_per_second": 230.902, | |
| "eval_steps_per_second": 14.532, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.47836583706149e-05, | |
| "loss": 5.6743, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.475349529697356e-05, | |
| "loss": 5.6818, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 5.736617088317871, | |
| "eval_runtime": 4.3397, | |
| "eval_samples_per_second": 230.66, | |
| "eval_steps_per_second": 14.517, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.4723332223332224e-05, | |
| "loss": 5.6836, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.469316914969089e-05, | |
| "loss": 5.6862, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 5.706295490264893, | |
| "eval_runtime": 4.3399, | |
| "eval_samples_per_second": 230.65, | |
| "eval_steps_per_second": 14.516, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.466300607604956e-05, | |
| "loss": 5.6792, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.46329033285555e-05, | |
| "loss": 5.6706, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 5.7102370262146, | |
| "eval_runtime": 4.2947, | |
| "eval_samples_per_second": 233.076, | |
| "eval_steps_per_second": 14.669, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.4602740254914174e-05, | |
| "loss": 5.6775, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.4572577181272834e-05, | |
| "loss": 5.6662, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 5.69236421585083, | |
| "eval_runtime": 6.3959, | |
| "eval_samples_per_second": 156.506, | |
| "eval_steps_per_second": 9.85, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.45424141076315e-05, | |
| "loss": 5.6691, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.4512371686284734e-05, | |
| "loss": 5.6839, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 5.711584091186523, | |
| "eval_runtime": 4.2918, | |
| "eval_samples_per_second": 233.234, | |
| "eval_steps_per_second": 14.679, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.44822086126434e-05, | |
| "loss": 5.6725, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.445204553900206e-05, | |
| "loss": 5.6789, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 5.663390159606934, | |
| "eval_runtime": 4.3322, | |
| "eval_samples_per_second": 231.063, | |
| "eval_steps_per_second": 14.542, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.442188246536073e-05, | |
| "loss": 5.6765, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.4391719391719395e-05, | |
| "loss": 5.6618, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 5.73824405670166, | |
| "eval_runtime": 4.2539, | |
| "eval_samples_per_second": 235.311, | |
| "eval_steps_per_second": 14.81, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.4361556318078055e-05, | |
| "loss": 5.6636, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.433139324443673e-05, | |
| "loss": 5.6733, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 5.712129592895508, | |
| "eval_runtime": 4.3264, | |
| "eval_samples_per_second": 231.369, | |
| "eval_steps_per_second": 14.562, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.430123017079539e-05, | |
| "loss": 5.6787, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.427112742330134e-05, | |
| "loss": 5.6709, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 5.736870288848877, | |
| "eval_runtime": 4.381, | |
| "eval_samples_per_second": 228.487, | |
| "eval_steps_per_second": 14.38, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.4240964349660005e-05, | |
| "loss": 5.6618, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.421080127601867e-05, | |
| "loss": 5.6627, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 5.6889142990112305, | |
| "eval_runtime": 4.2821, | |
| "eval_samples_per_second": 233.762, | |
| "eval_steps_per_second": 14.712, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.418063820237733e-05, | |
| "loss": 5.6751, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.415053545488328e-05, | |
| "loss": 5.655, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 5.685154438018799, | |
| "eval_runtime": 6.9191, | |
| "eval_samples_per_second": 144.671, | |
| "eval_steps_per_second": 9.105, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.412037238124195e-05, | |
| "loss": 5.6734, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.4090209307600616e-05, | |
| "loss": 5.6649, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 5.713215351104736, | |
| "eval_runtime": 4.2937, | |
| "eval_samples_per_second": 233.132, | |
| "eval_steps_per_second": 14.673, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.4060046233959276e-05, | |
| "loss": 5.6724, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.4029943486465226e-05, | |
| "loss": 5.6634, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 5.674860000610352, | |
| "eval_runtime": 4.3043, | |
| "eval_samples_per_second": 232.557, | |
| "eval_steps_per_second": 14.636, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.399978041282389e-05, | |
| "loss": 5.6674, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.396961733918255e-05, | |
| "loss": 5.6625, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 5.694820880889893, | |
| "eval_runtime": 4.396, | |
| "eval_samples_per_second": 227.709, | |
| "eval_steps_per_second": 14.331, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.393951459168851e-05, | |
| "loss": 5.6711, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.390935151804717e-05, | |
| "loss": 5.6721, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 5.711126804351807, | |
| "eval_runtime": 6.4814, | |
| "eval_samples_per_second": 154.443, | |
| "eval_steps_per_second": 9.72, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.3879188444405836e-05, | |
| "loss": 5.6574, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.38490253707645e-05, | |
| "loss": 5.6608, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 5.73061990737915, | |
| "eval_runtime": 4.2517, | |
| "eval_samples_per_second": 235.437, | |
| "eval_steps_per_second": 14.818, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.381886229712317e-05, | |
| "loss": 5.6663, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.378869922348183e-05, | |
| "loss": 5.6685, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 5.769214630126953, | |
| "eval_runtime": 4.3149, | |
| "eval_samples_per_second": 231.988, | |
| "eval_steps_per_second": 14.601, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.3758536149840504e-05, | |
| "loss": 5.6631, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.3728373076199164e-05, | |
| "loss": 5.6557, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 5.712480545043945, | |
| "eval_runtime": 4.3273, | |
| "eval_samples_per_second": 231.325, | |
| "eval_steps_per_second": 14.559, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.3698270328705114e-05, | |
| "loss": 5.6767, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.3668167581211063e-05, | |
| "loss": 5.6665, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 5.739169120788574, | |
| "eval_runtime": 4.2992, | |
| "eval_samples_per_second": 232.836, | |
| "eval_steps_per_second": 14.654, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.363800450756973e-05, | |
| "loss": 5.6699, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.360784143392839e-05, | |
| "loss": 5.6603, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 5.6816325187683105, | |
| "eval_runtime": 4.353, | |
| "eval_samples_per_second": 229.954, | |
| "eval_steps_per_second": 14.473, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.357767836028706e-05, | |
| "loss": 5.6717, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.3547515286645725e-05, | |
| "loss": 5.6712, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 5.7074737548828125, | |
| "eval_runtime": 4.3743, | |
| "eval_samples_per_second": 228.834, | |
| "eval_steps_per_second": 14.402, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.3517352213004385e-05, | |
| "loss": 5.6676, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.348718913936305e-05, | |
| "loss": 5.6547, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 5.6991777420043945, | |
| "eval_runtime": 4.4989, | |
| "eval_samples_per_second": 222.5, | |
| "eval_steps_per_second": 14.004, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.3457086391869e-05, | |
| "loss": 5.6638, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.342692331822767e-05, | |
| "loss": 5.6511, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 5.679354190826416, | |
| "eval_runtime": 4.2833, | |
| "eval_samples_per_second": 233.696, | |
| "eval_steps_per_second": 14.708, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.3396760244586335e-05, | |
| "loss": 5.6673, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.3366597170945e-05, | |
| "loss": 5.6663, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 5.680385589599609, | |
| "eval_runtime": 4.3563, | |
| "eval_samples_per_second": 229.783, | |
| "eval_steps_per_second": 14.462, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.333643409730366e-05, | |
| "loss": 5.6682, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.330627102366233e-05, | |
| "loss": 5.6562, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 5.730945587158203, | |
| "eval_runtime": 6.374, | |
| "eval_samples_per_second": 157.044, | |
| "eval_steps_per_second": 9.884, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.3276107950020996e-05, | |
| "loss": 5.6656, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.3246005202526946e-05, | |
| "loss": 5.6546, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 5.708312034606934, | |
| "eval_runtime": 4.2353, | |
| "eval_samples_per_second": 236.345, | |
| "eval_steps_per_second": 14.875, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.3215842128885606e-05, | |
| "loss": 5.6529, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.318567905524428e-05, | |
| "loss": 5.656, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 5.711429119110107, | |
| "eval_runtime": 4.3481, | |
| "eval_samples_per_second": 230.216, | |
| "eval_steps_per_second": 14.489, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.315551598160294e-05, | |
| "loss": 5.6731, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.312535290796161e-05, | |
| "loss": 5.6712, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 5.6710896492004395, | |
| "eval_runtime": 4.2998, | |
| "eval_samples_per_second": 232.804, | |
| "eval_steps_per_second": 14.652, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.3095189834320274e-05, | |
| "loss": 5.6619, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.306502676067894e-05, | |
| "loss": 5.6473, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 5.6910600662231445, | |
| "eval_runtime": 4.3442, | |
| "eval_samples_per_second": 230.421, | |
| "eval_steps_per_second": 14.502, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.3034924013184884e-05, | |
| "loss": 5.6577, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.300476093954355e-05, | |
| "loss": 5.6352, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 5.7348408699035645, | |
| "eval_runtime": 4.3322, | |
| "eval_samples_per_second": 231.062, | |
| "eval_steps_per_second": 14.542, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.297459786590222e-05, | |
| "loss": 5.647, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.294443479226088e-05, | |
| "loss": 5.6602, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 5.7037835121154785, | |
| "eval_runtime": 6.3915, | |
| "eval_samples_per_second": 156.614, | |
| "eval_steps_per_second": 9.857, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.2914271718619545e-05, | |
| "loss": 5.6598, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.288410864497821e-05, | |
| "loss": 5.645, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 5.670388698577881, | |
| "eval_runtime": 4.2976, | |
| "eval_samples_per_second": 232.922, | |
| "eval_steps_per_second": 14.659, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.285394557133688e-05, | |
| "loss": 5.637, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.282378249769554e-05, | |
| "loss": 5.6611, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 5.681214332580566, | |
| "eval_runtime": 4.3365, | |
| "eval_samples_per_second": 230.833, | |
| "eval_steps_per_second": 14.528, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.2793679750201495e-05, | |
| "loss": 5.6413, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.276357700270744e-05, | |
| "loss": 5.6442, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 5.678561687469482, | |
| "eval_runtime": 4.2838, | |
| "eval_samples_per_second": 233.671, | |
| "eval_steps_per_second": 14.707, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.2733413929066105e-05, | |
| "loss": 5.6429, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.270325085542477e-05, | |
| "loss": 5.6572, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 5.70313024520874, | |
| "eval_runtime": 4.2374, | |
| "eval_samples_per_second": 236.231, | |
| "eval_steps_per_second": 14.868, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.267308778178344e-05, | |
| "loss": 5.6563, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.26429247081421e-05, | |
| "loss": 5.6631, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 5.692766189575195, | |
| "eval_runtime": 4.2623, | |
| "eval_samples_per_second": 234.85, | |
| "eval_steps_per_second": 14.781, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.261276163450077e-05, | |
| "loss": 5.6386, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.258259856085943e-05, | |
| "loss": 5.6553, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 5.708261013031006, | |
| "eval_runtime": 4.2737, | |
| "eval_samples_per_second": 234.224, | |
| "eval_steps_per_second": 14.741, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.2552495813365376e-05, | |
| "loss": 5.6524, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.252233273972405e-05, | |
| "loss": 5.6521, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 5.687132358551025, | |
| "eval_runtime": 4.4286, | |
| "eval_samples_per_second": 226.029, | |
| "eval_steps_per_second": 14.226, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.249216966608271e-05, | |
| "loss": 5.6559, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.2462006592441377e-05, | |
| "loss": 5.6644, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 5.712847709655762, | |
| "eval_runtime": 4.3174, | |
| "eval_samples_per_second": 231.852, | |
| "eval_steps_per_second": 14.592, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.2431843518800044e-05, | |
| "loss": 5.6407, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.240174077130599e-05, | |
| "loss": 5.6421, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 5.716492652893066, | |
| "eval_runtime": 4.2976, | |
| "eval_samples_per_second": 232.92, | |
| "eval_steps_per_second": 14.659, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.237157769766465e-05, | |
| "loss": 5.6653, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.234141462402332e-05, | |
| "loss": 5.6465, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 5.711600303649902, | |
| "eval_runtime": 4.3593, | |
| "eval_samples_per_second": 229.622, | |
| "eval_steps_per_second": 14.452, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.231125155038199e-05, | |
| "loss": 5.6545, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.2281088476740654e-05, | |
| "loss": 5.653, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 5.694251537322998, | |
| "eval_runtime": 6.4453, | |
| "eval_samples_per_second": 155.307, | |
| "eval_steps_per_second": 9.775, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.2250925403099314e-05, | |
| "loss": 5.6472, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.222076232945799e-05, | |
| "loss": 5.6546, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 5.6814446449279785, | |
| "eval_runtime": 4.3371, | |
| "eval_samples_per_second": 230.802, | |
| "eval_steps_per_second": 14.526, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.219059925581665e-05, | |
| "loss": 5.6483, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.216055683446988e-05, | |
| "loss": 5.654, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 5.7155609130859375, | |
| "eval_runtime": 4.3569, | |
| "eval_samples_per_second": 229.748, | |
| "eval_steps_per_second": 14.46, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.213039376082855e-05, | |
| "loss": 5.6427, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.210023068718721e-05, | |
| "loss": 5.6526, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 5.657435417175293, | |
| "eval_runtime": 4.288, | |
| "eval_samples_per_second": 233.441, | |
| "eval_steps_per_second": 14.692, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.2070067613545875e-05, | |
| "loss": 5.6495, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.203990453990454e-05, | |
| "loss": 5.649, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 5.6852569580078125, | |
| "eval_runtime": 4.3096, | |
| "eval_samples_per_second": 232.275, | |
| "eval_steps_per_second": 14.619, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.200980179241049e-05, | |
| "loss": 5.6591, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.197963871876915e-05, | |
| "loss": 5.6427, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 5.6808366775512695, | |
| "eval_runtime": 4.2828, | |
| "eval_samples_per_second": 233.726, | |
| "eval_steps_per_second": 14.71, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.1949475645127825e-05, | |
| "loss": 5.6409, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.1919312571486485e-05, | |
| "loss": 5.6436, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 5.664061546325684, | |
| "eval_runtime": 4.2839, | |
| "eval_samples_per_second": 233.663, | |
| "eval_steps_per_second": 14.706, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.188914949784515e-05, | |
| "loss": 5.6421, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.185898642420382e-05, | |
| "loss": 5.6319, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 5.68691349029541, | |
| "eval_runtime": 4.3423, | |
| "eval_samples_per_second": 230.522, | |
| "eval_steps_per_second": 14.508, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.1828823350562486e-05, | |
| "loss": 5.6542, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.1798660276921146e-05, | |
| "loss": 5.6393, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 5.684676647186279, | |
| "eval_runtime": 4.3763, | |
| "eval_samples_per_second": 228.73, | |
| "eval_steps_per_second": 14.396, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.176849720327981e-05, | |
| "loss": 5.6442, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.173839445578576e-05, | |
| "loss": 5.6363, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 5.680596828460693, | |
| "eval_runtime": 4.349, | |
| "eval_samples_per_second": 230.166, | |
| "eval_steps_per_second": 14.486, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.170823138214443e-05, | |
| "loss": 5.6416, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.167812863465038e-05, | |
| "loss": 5.648, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 5.648463249206543, | |
| "eval_runtime": 4.3014, | |
| "eval_samples_per_second": 232.713, | |
| "eval_steps_per_second": 14.646, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.164796556100904e-05, | |
| "loss": 5.6414, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.1617802487367706e-05, | |
| "loss": 5.6297, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 5.679803371429443, | |
| "eval_runtime": 4.2827, | |
| "eval_samples_per_second": 233.729, | |
| "eval_steps_per_second": 14.71, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.1587639413726373e-05, | |
| "loss": 5.6411, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.155747634008504e-05, | |
| "loss": 5.6442, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 5.673394203186035, | |
| "eval_runtime": 4.3412, | |
| "eval_samples_per_second": 230.582, | |
| "eval_steps_per_second": 14.512, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.15273132664437e-05, | |
| "loss": 5.6313, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.149715019280237e-05, | |
| "loss": 5.6546, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 5.6783528327941895, | |
| "eval_runtime": 4.4144, | |
| "eval_samples_per_second": 226.756, | |
| "eval_steps_per_second": 14.271, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.146704744530832e-05, | |
| "loss": 5.6374, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.1436884371666984e-05, | |
| "loss": 5.6325, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 5.645352840423584, | |
| "eval_runtime": 4.3033, | |
| "eval_samples_per_second": 232.612, | |
| "eval_steps_per_second": 14.64, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.1406721298025644e-05, | |
| "loss": 5.643, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.137655822438432e-05, | |
| "loss": 5.6386, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 5.695677757263184, | |
| "eval_runtime": 4.2949, | |
| "eval_samples_per_second": 233.065, | |
| "eval_steps_per_second": 14.668, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.134639515074298e-05, | |
| "loss": 5.6337, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.131629240324893e-05, | |
| "loss": 5.6236, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 5.678653240203857, | |
| "eval_runtime": 4.4357, | |
| "eval_samples_per_second": 225.669, | |
| "eval_steps_per_second": 14.203, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.1286129329607595e-05, | |
| "loss": 5.639, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.1255966255966255e-05, | |
| "loss": 5.6269, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 5.681842803955078, | |
| "eval_runtime": 4.3725, | |
| "eval_samples_per_second": 228.929, | |
| "eval_steps_per_second": 14.408, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.122580318232492e-05, | |
| "loss": 5.635, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.119564010868359e-05, | |
| "loss": 5.6285, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 5.673871040344238, | |
| "eval_runtime": 4.3771, | |
| "eval_samples_per_second": 228.689, | |
| "eval_steps_per_second": 14.393, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.1165477035042256e-05, | |
| "loss": 5.6383, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.11353742875482e-05, | |
| "loss": 5.65, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 5.630629539489746, | |
| "eval_runtime": 4.41, | |
| "eval_samples_per_second": 226.983, | |
| "eval_steps_per_second": 14.286, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.110521121390687e-05, | |
| "loss": 5.6381, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.107504814026553e-05, | |
| "loss": 5.6313, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 5.6462812423706055, | |
| "eval_runtime": 4.3445, | |
| "eval_samples_per_second": 230.407, | |
| "eval_steps_per_second": 14.501, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.10448850666242e-05, | |
| "loss": 5.6347, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.1014721992982866e-05, | |
| "loss": 5.6412, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 5.668566703796387, | |
| "eval_runtime": 4.3418, | |
| "eval_samples_per_second": 230.551, | |
| "eval_steps_per_second": 14.51, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.098455891934153e-05, | |
| "loss": 5.639, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.0954456171847476e-05, | |
| "loss": 5.6278, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 5.6881489753723145, | |
| "eval_runtime": 4.455, | |
| "eval_samples_per_second": 224.692, | |
| "eval_steps_per_second": 14.141, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.092429309820614e-05, | |
| "loss": 5.6408, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.089413002456481e-05, | |
| "loss": 5.637, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 5.688764572143555, | |
| "eval_runtime": 6.2867, | |
| "eval_samples_per_second": 159.224, | |
| "eval_steps_per_second": 10.021, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.086396695092348e-05, | |
| "loss": 5.646, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.083380387728214e-05, | |
| "loss": 5.626, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 5.671611785888672, | |
| "eval_runtime": 4.3616, | |
| "eval_samples_per_second": 229.503, | |
| "eval_steps_per_second": 14.444, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.080364080364081e-05, | |
| "loss": 5.6378, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.0773538056146754e-05, | |
| "loss": 5.6338, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 5.616012096405029, | |
| "eval_runtime": 4.4085, | |
| "eval_samples_per_second": 227.06, | |
| "eval_steps_per_second": 14.29, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.0743374982505414e-05, | |
| "loss": 5.6318, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.071321190886409e-05, | |
| "loss": 5.6361, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 5.667599201202393, | |
| "eval_runtime": 6.2583, | |
| "eval_samples_per_second": 159.947, | |
| "eval_steps_per_second": 10.067, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.068304883522275e-05, | |
| "loss": 5.625, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.0652885761581415e-05, | |
| "loss": 5.6336, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 5.684675216674805, | |
| "eval_runtime": 4.3154, | |
| "eval_samples_per_second": 231.962, | |
| "eval_steps_per_second": 14.599, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.062272268794008e-05, | |
| "loss": 5.6388, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.059255961429875e-05, | |
| "loss": 5.6351, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 5.675138473510742, | |
| "eval_runtime": 4.3055, | |
| "eval_samples_per_second": 232.494, | |
| "eval_steps_per_second": 14.632, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.056239654065741e-05, | |
| "loss": 5.6266, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.053229379316336e-05, | |
| "loss": 5.6408, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 5.615994453430176, | |
| "eval_runtime": 4.3074, | |
| "eval_samples_per_second": 232.39, | |
| "eval_steps_per_second": 14.626, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.0502130719522025e-05, | |
| "loss": 5.6399, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.047196764588069e-05, | |
| "loss": 5.6232, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 5.652904033660889, | |
| "eval_runtime": 4.3343, | |
| "eval_samples_per_second": 230.949, | |
| "eval_steps_per_second": 14.535, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.044186489838664e-05, | |
| "loss": 5.6249, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.041170182474531e-05, | |
| "loss": 5.6319, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 5.64531946182251, | |
| "eval_runtime": 5.6252, | |
| "eval_samples_per_second": 177.948, | |
| "eval_steps_per_second": 11.2, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.038153875110397e-05, | |
| "loss": 5.6244, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.0351375677462636e-05, | |
| "loss": 5.6204, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 5.661260604858398, | |
| "eval_runtime": 4.3573, | |
| "eval_samples_per_second": 229.732, | |
| "eval_steps_per_second": 14.459, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.03212126038213e-05, | |
| "loss": 5.6353, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.0291109856327246e-05, | |
| "loss": 5.6231, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 5.666103363037109, | |
| "eval_runtime": 4.5226, | |
| "eval_samples_per_second": 221.333, | |
| "eval_steps_per_second": 13.93, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.026094678268591e-05, | |
| "loss": 5.6318, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.023078370904458e-05, | |
| "loss": 5.6322, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 5.640702247619629, | |
| "eval_runtime": 4.3357, | |
| "eval_samples_per_second": 230.872, | |
| "eval_steps_per_second": 14.53, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.020062063540325e-05, | |
| "loss": 5.6135, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.017045756176191e-05, | |
| "loss": 5.6369, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 5.658245086669922, | |
| "eval_runtime": 4.353, | |
| "eval_samples_per_second": 229.957, | |
| "eval_steps_per_second": 14.473, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.014029448812058e-05, | |
| "loss": 5.6445, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.0110191740626523e-05, | |
| "loss": 5.6337, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 5.672937393188477, | |
| "eval_runtime": 4.4799, | |
| "eval_samples_per_second": 223.441, | |
| "eval_steps_per_second": 14.063, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.008002866698519e-05, | |
| "loss": 5.6349, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.004986559334386e-05, | |
| "loss": 5.6278, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 5.6635026931762695, | |
| "eval_runtime": 6.1168, | |
| "eval_samples_per_second": 163.647, | |
| "eval_steps_per_second": 10.299, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.0019702519702524e-05, | |
| "loss": 5.6318, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.9989539446061184e-05, | |
| "loss": 5.6371, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 5.643805503845215, | |
| "eval_runtime": 4.2716, | |
| "eval_samples_per_second": 234.336, | |
| "eval_steps_per_second": 14.748, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.995943669856714e-05, | |
| "loss": 5.6145, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.99292736249258e-05, | |
| "loss": 5.624, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 5.633095741271973, | |
| "eval_runtime": 4.3138, | |
| "eval_samples_per_second": 232.048, | |
| "eval_steps_per_second": 14.604, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.989911055128447e-05, | |
| "loss": 5.619, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.9868947477643135e-05, | |
| "loss": 5.6198, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 5.6540656089782715, | |
| "eval_runtime": 4.3595, | |
| "eval_samples_per_second": 229.615, | |
| "eval_steps_per_second": 14.451, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.98387844040018e-05, | |
| "loss": 5.624, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.9808681656507745e-05, | |
| "loss": 5.6243, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 5.651320457458496, | |
| "eval_runtime": 4.3133, | |
| "eval_samples_per_second": 232.072, | |
| "eval_steps_per_second": 14.606, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.977851858286641e-05, | |
| "loss": 5.6133, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.974835550922508e-05, | |
| "loss": 5.6118, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 5.682806491851807, | |
| "eval_runtime": 4.4555, | |
| "eval_samples_per_second": 224.668, | |
| "eval_steps_per_second": 14.14, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.971819243558374e-05, | |
| "loss": 5.6085, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.9688029361942406e-05, | |
| "loss": 5.6315, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 5.685708045959473, | |
| "eval_runtime": 4.3306, | |
| "eval_samples_per_second": 231.143, | |
| "eval_steps_per_second": 14.547, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.965786628830107e-05, | |
| "loss": 5.6271, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.962770321465974e-05, | |
| "loss": 5.6208, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 5.64992618560791, | |
| "eval_runtime": 4.409, | |
| "eval_samples_per_second": 227.033, | |
| "eval_steps_per_second": 14.289, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.95975401410184e-05, | |
| "loss": 5.6218, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.9567437393524356e-05, | |
| "loss": 5.6261, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 5.64516544342041, | |
| "eval_runtime": 4.4391, | |
| "eval_samples_per_second": 225.497, | |
| "eval_steps_per_second": 14.192, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.9537274319883016e-05, | |
| "loss": 5.6255, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.950711124624168e-05, | |
| "loss": 5.6247, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 5.677004814147949, | |
| "eval_runtime": 4.3652, | |
| "eval_samples_per_second": 229.316, | |
| "eval_steps_per_second": 14.432, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.947700849874763e-05, | |
| "loss": 5.6099, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.94468454251063e-05, | |
| "loss": 5.6204, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 5.616661548614502, | |
| "eval_runtime": 4.3551, | |
| "eval_samples_per_second": 229.845, | |
| "eval_steps_per_second": 14.466, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.941668235146496e-05, | |
| "loss": 5.6196, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.938651927782363e-05, | |
| "loss": 5.6166, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 5.683280944824219, | |
| "eval_runtime": 4.3154, | |
| "eval_samples_per_second": 231.959, | |
| "eval_steps_per_second": 14.599, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.9356356204182294e-05, | |
| "loss": 5.6303, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.932625345668824e-05, | |
| "loss": 5.6145, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 5.708868980407715, | |
| "eval_runtime": 4.3953, | |
| "eval_samples_per_second": 227.744, | |
| "eval_steps_per_second": 14.334, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.929609038304691e-05, | |
| "loss": 5.6208, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.926592730940557e-05, | |
| "loss": 5.6155, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 5.643332481384277, | |
| "eval_runtime": 4.3751, | |
| "eval_samples_per_second": 228.794, | |
| "eval_steps_per_second": 14.4, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.923576423576424e-05, | |
| "loss": 5.6361, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.9205601162122905e-05, | |
| "loss": 5.6162, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 5.648618221282959, | |
| "eval_runtime": 4.3904, | |
| "eval_samples_per_second": 227.999, | |
| "eval_steps_per_second": 14.35, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.917543808848157e-05, | |
| "loss": 5.6344, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.914527501484023e-05, | |
| "loss": 5.6144, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 5.633224964141846, | |
| "eval_runtime": 4.3929, | |
| "eval_samples_per_second": 227.865, | |
| "eval_steps_per_second": 14.341, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.911517226734618e-05, | |
| "loss": 5.6285, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.908500919370485e-05, | |
| "loss": 5.6198, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 5.645481109619141, | |
| "eval_runtime": 4.3967, | |
| "eval_samples_per_second": 227.672, | |
| "eval_steps_per_second": 14.329, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.9054846120063515e-05, | |
| "loss": 5.6095, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.9024683046422175e-05, | |
| "loss": 5.6231, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 5.6638264656066895, | |
| "eval_runtime": 4.4238, | |
| "eval_samples_per_second": 226.274, | |
| "eval_steps_per_second": 14.241, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.899451997278085e-05, | |
| "loss": 5.6158, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.896441722528679e-05, | |
| "loss": 5.61, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 5.614964962005615, | |
| "eval_runtime": 4.3378, | |
| "eval_samples_per_second": 230.76, | |
| "eval_steps_per_second": 14.523, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.893425415164545e-05, | |
| "loss": 5.5975, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.8904091078004126e-05, | |
| "loss": 5.614, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 5.670050621032715, | |
| "eval_runtime": 4.3122, | |
| "eval_samples_per_second": 232.134, | |
| "eval_steps_per_second": 14.61, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.8873928004362786e-05, | |
| "loss": 5.6029, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.8843825256868736e-05, | |
| "loss": 5.6158, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 5.641917705535889, | |
| "eval_runtime": 4.3145, | |
| "eval_samples_per_second": 232.008, | |
| "eval_steps_per_second": 14.602, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.88136621832274e-05, | |
| "loss": 5.6351, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.878349910958607e-05, | |
| "loss": 5.6163, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 5.651737213134766, | |
| "eval_runtime": 4.3373, | |
| "eval_samples_per_second": 230.79, | |
| "eval_steps_per_second": 14.525, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.875333603594473e-05, | |
| "loss": 5.5979, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.8723172962303403e-05, | |
| "loss": 5.6151, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 5.646933078765869, | |
| "eval_runtime": 4.2964, | |
| "eval_samples_per_second": 232.987, | |
| "eval_steps_per_second": 14.664, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.8693070214809346e-05, | |
| "loss": 5.6236, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.866290714116801e-05, | |
| "loss": 5.6251, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 5.671980381011963, | |
| "eval_runtime": 4.4739, | |
| "eval_samples_per_second": 223.743, | |
| "eval_steps_per_second": 14.082, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.863274406752668e-05, | |
| "loss": 5.6018, | |
| "step": 188500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.860258099388535e-05, | |
| "loss": 5.6272, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 5.603824138641357, | |
| "eval_runtime": 4.3496, | |
| "eval_samples_per_second": 230.135, | |
| "eval_steps_per_second": 14.484, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.857247824639129e-05, | |
| "loss": 5.6282, | |
| "step": 189500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.854231517274996e-05, | |
| "loss": 5.6291, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 5.6158552169799805, | |
| "eval_runtime": 6.4339, | |
| "eval_samples_per_second": 155.582, | |
| "eval_steps_per_second": 9.792, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.8512152099108624e-05, | |
| "loss": 5.6017, | |
| "step": 190500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.8481989025467284e-05, | |
| "loss": 5.6114, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 5.6429595947265625, | |
| "eval_runtime": 4.3858, | |
| "eval_samples_per_second": 228.235, | |
| "eval_steps_per_second": 14.364, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.845182595182595e-05, | |
| "loss": 5.6194, | |
| "step": 191500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.842166287818462e-05, | |
| "loss": 5.6128, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 5.634527683258057, | |
| "eval_runtime": 4.3652, | |
| "eval_samples_per_second": 229.313, | |
| "eval_steps_per_second": 14.432, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.8391499804543285e-05, | |
| "loss": 5.62, | |
| "step": 192500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.836139705704923e-05, | |
| "loss": 5.6213, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 5.641001224517822, | |
| "eval_runtime": 4.355, | |
| "eval_samples_per_second": 229.851, | |
| "eval_steps_per_second": 14.466, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.83312339834079e-05, | |
| "loss": 5.6182, | |
| "step": 193500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.830107090976656e-05, | |
| "loss": 5.6104, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 5.6409525871276855, | |
| "eval_runtime": 4.3644, | |
| "eval_samples_per_second": 229.353, | |
| "eval_steps_per_second": 14.435, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.827090783612523e-05, | |
| "loss": 5.6061, | |
| "step": 194500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.8240744762483896e-05, | |
| "loss": 5.6081, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 5.624050617218018, | |
| "eval_runtime": 4.463, | |
| "eval_samples_per_second": 224.291, | |
| "eval_steps_per_second": 14.116, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.821058168884256e-05, | |
| "loss": 5.6234, | |
| "step": 195500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.8180478941348505e-05, | |
| "loss": 5.6288, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 5.689996242523193, | |
| "eval_runtime": 6.3147, | |
| "eval_samples_per_second": 158.518, | |
| "eval_steps_per_second": 9.977, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.815031586770718e-05, | |
| "loss": 5.6253, | |
| "step": 196500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.812015279406584e-05, | |
| "loss": 5.607, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 5.656425952911377, | |
| "eval_runtime": 4.3871, | |
| "eval_samples_per_second": 228.167, | |
| "eval_steps_per_second": 14.36, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.8089989720424506e-05, | |
| "loss": 5.6259, | |
| "step": 197500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.805982664678317e-05, | |
| "loss": 5.605, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 5.651924133300781, | |
| "eval_runtime": 4.362, | |
| "eval_samples_per_second": 229.484, | |
| "eval_steps_per_second": 14.443, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.8029723899289116e-05, | |
| "loss": 5.6153, | |
| "step": 198500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.799956082564778e-05, | |
| "loss": 5.6109, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 5.639188766479492, | |
| "eval_runtime": 4.301, | |
| "eval_samples_per_second": 232.739, | |
| "eval_steps_per_second": 14.648, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.796939775200645e-05, | |
| "loss": 5.6064, | |
| "step": 199500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.793923467836512e-05, | |
| "loss": 5.619, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 5.662364959716797, | |
| "eval_runtime": 4.3023, | |
| "eval_samples_per_second": 232.664, | |
| "eval_steps_per_second": 14.643, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.790913193087106e-05, | |
| "loss": 5.6079, | |
| "step": 200500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.7878968857229727e-05, | |
| "loss": 5.6019, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 5.653491973876953, | |
| "eval_runtime": 4.2771, | |
| "eval_samples_per_second": 234.036, | |
| "eval_steps_per_second": 14.73, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.7848805783588394e-05, | |
| "loss": 5.6022, | |
| "step": 201500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.781864270994706e-05, | |
| "loss": 5.6133, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 5.676525115966797, | |
| "eval_runtime": 4.3425, | |
| "eval_samples_per_second": 230.512, | |
| "eval_steps_per_second": 14.508, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.778847963630572e-05, | |
| "loss": 5.6117, | |
| "step": 202500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.775837688881168e-05, | |
| "loss": 5.5927, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 5.636429786682129, | |
| "eval_runtime": 4.3367, | |
| "eval_samples_per_second": 230.822, | |
| "eval_steps_per_second": 14.527, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.772821381517034e-05, | |
| "loss": 5.6198, | |
| "step": 203500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.7698050741529004e-05, | |
| "loss": 5.6119, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 5.666501045227051, | |
| "eval_runtime": 4.3287, | |
| "eval_samples_per_second": 231.246, | |
| "eval_steps_per_second": 14.554, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.766788766788767e-05, | |
| "loss": 5.6199, | |
| "step": 204500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.763778492039362e-05, | |
| "loss": 5.602, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 5.631441116333008, | |
| "eval_runtime": 4.3578, | |
| "eval_samples_per_second": 229.703, | |
| "eval_steps_per_second": 14.457, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.760762184675228e-05, | |
| "loss": 5.5997, | |
| "step": 205500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.757745877311095e-05, | |
| "loss": 5.605, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 5.630640983581543, | |
| "eval_runtime": 4.2859, | |
| "eval_samples_per_second": 233.558, | |
| "eval_steps_per_second": 14.699, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.7547295699469615e-05, | |
| "loss": 5.6155, | |
| "step": 206500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.7517132625828275e-05, | |
| "loss": 5.612, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 5.597905158996582, | |
| "eval_runtime": 4.3535, | |
| "eval_samples_per_second": 229.93, | |
| "eval_steps_per_second": 14.471, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.748696955218695e-05, | |
| "loss": 5.6189, | |
| "step": 207500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.745680647854561e-05, | |
| "loss": 5.6184, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 5.636325359344482, | |
| "eval_runtime": 4.3413, | |
| "eval_samples_per_second": 230.575, | |
| "eval_steps_per_second": 14.512, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.742670373105156e-05, | |
| "loss": 5.6078, | |
| "step": 208500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.7396540657410225e-05, | |
| "loss": 5.6131, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 5.635697364807129, | |
| "eval_runtime": 4.3624, | |
| "eval_samples_per_second": 229.461, | |
| "eval_steps_per_second": 14.442, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.736637758376889e-05, | |
| "loss": 5.6102, | |
| "step": 209500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.733621451012755e-05, | |
| "loss": 5.6063, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 5.6277570724487305, | |
| "eval_runtime": 4.4064, | |
| "eval_samples_per_second": 227.169, | |
| "eval_steps_per_second": 14.297, | |
| "step": 210000 | |
| } | |
| ], | |
| "max_steps": 828828, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.574739225286738e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |