| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.6107081324472627, | |
| "global_step": 445000, | |
| "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 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.730605143648622e-05, | |
| "loss": 5.6061, | |
| "step": 210500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.727594868899217e-05, | |
| "loss": 5.5978, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 5.661520004272461, | |
| "eval_runtime": 4.3347, | |
| "eval_samples_per_second": 230.925, | |
| "eval_steps_per_second": 14.534, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.7245785615350836e-05, | |
| "loss": 5.6161, | |
| "step": 211500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.7215622541709496e-05, | |
| "loss": 5.6034, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 5.591000080108643, | |
| "eval_runtime": 4.3807, | |
| "eval_samples_per_second": 228.503, | |
| "eval_steps_per_second": 14.381, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.718545946806817e-05, | |
| "loss": 5.6148, | |
| "step": 212500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.715535672057411e-05, | |
| "loss": 5.6112, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 5.652878284454346, | |
| "eval_runtime": 6.5244, | |
| "eval_samples_per_second": 153.423, | |
| "eval_steps_per_second": 9.656, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.712519364693278e-05, | |
| "loss": 5.6086, | |
| "step": 213500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.709503057329145e-05, | |
| "loss": 5.5992, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 5.627796173095703, | |
| "eval_runtime": 4.3064, | |
| "eval_samples_per_second": 232.446, | |
| "eval_steps_per_second": 14.629, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.706486749965011e-05, | |
| "loss": 5.6003, | |
| "step": 214500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.7034764752156056e-05, | |
| "loss": 5.6099, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 5.642346382141113, | |
| "eval_runtime": 4.4977, | |
| "eval_samples_per_second": 222.559, | |
| "eval_steps_per_second": 14.007, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.700460167851472e-05, | |
| "loss": 5.5956, | |
| "step": 215500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.697443860487339e-05, | |
| "loss": 5.6031, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 5.631239891052246, | |
| "eval_runtime": 5.8594, | |
| "eval_samples_per_second": 170.837, | |
| "eval_steps_per_second": 10.752, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.694427553123205e-05, | |
| "loss": 5.604, | |
| "step": 216500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.6914112457590724e-05, | |
| "loss": 5.6015, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 5.639444351196289, | |
| "eval_runtime": 4.3658, | |
| "eval_samples_per_second": 229.284, | |
| "eval_steps_per_second": 14.43, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.688400971009667e-05, | |
| "loss": 5.6062, | |
| "step": 217500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.6853846636455334e-05, | |
| "loss": 5.6041, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 5.653528690338135, | |
| "eval_runtime": 4.4108, | |
| "eval_samples_per_second": 226.943, | |
| "eval_steps_per_second": 14.283, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.6823683562814e-05, | |
| "loss": 5.6039, | |
| "step": 218500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.679352048917267e-05, | |
| "loss": 5.6027, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 5.654060363769531, | |
| "eval_runtime": 4.3047, | |
| "eval_samples_per_second": 232.538, | |
| "eval_steps_per_second": 14.635, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.676341774167861e-05, | |
| "loss": 5.5953, | |
| "step": 219500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.673325466803728e-05, | |
| "loss": 5.6065, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 5.660271167755127, | |
| "eval_runtime": 4.4687, | |
| "eval_samples_per_second": 224.002, | |
| "eval_steps_per_second": 14.098, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.6703091594395945e-05, | |
| "loss": 5.6137, | |
| "step": 220500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.6672928520754605e-05, | |
| "loss": 5.601, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 5.656097888946533, | |
| "eval_runtime": 4.2208, | |
| "eval_samples_per_second": 237.157, | |
| "eval_steps_per_second": 14.926, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.664282577326056e-05, | |
| "loss": 5.6, | |
| "step": 221500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.661266269961922e-05, | |
| "loss": 5.6075, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 5.628451824188232, | |
| "eval_runtime": 4.3448, | |
| "eval_samples_per_second": 230.39, | |
| "eval_steps_per_second": 14.5, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.658249962597789e-05, | |
| "loss": 5.5945, | |
| "step": 222500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.6552336552336555e-05, | |
| "loss": 5.608, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 5.617640018463135, | |
| "eval_runtime": 4.3432, | |
| "eval_samples_per_second": 230.475, | |
| "eval_steps_per_second": 14.505, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.652217347869522e-05, | |
| "loss": 5.5962, | |
| "step": 223500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.6492070731201165e-05, | |
| "loss": 5.5969, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 5.676702976226807, | |
| "eval_runtime": 4.3353, | |
| "eval_samples_per_second": 230.893, | |
| "eval_steps_per_second": 14.532, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.646190765755983e-05, | |
| "loss": 5.6165, | |
| "step": 224500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.64317445839185e-05, | |
| "loss": 5.6145, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 5.627898693084717, | |
| "eval_runtime": 4.3201, | |
| "eval_samples_per_second": 231.706, | |
| "eval_steps_per_second": 14.583, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.6401581510277166e-05, | |
| "loss": 5.6048, | |
| "step": 225500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.6371418436635826e-05, | |
| "loss": 5.6053, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 5.602691650390625, | |
| "eval_runtime": 6.0129, | |
| "eval_samples_per_second": 166.476, | |
| "eval_steps_per_second": 10.478, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.63412553629945e-05, | |
| "loss": 5.6042, | |
| "step": 226500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.631109228935316e-05, | |
| "loss": 5.5962, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 5.625843048095703, | |
| "eval_runtime": 4.3278, | |
| "eval_samples_per_second": 231.293, | |
| "eval_steps_per_second": 14.557, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.62809895418591e-05, | |
| "loss": 5.6113, | |
| "step": 227500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.6250826468217777e-05, | |
| "loss": 5.6022, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 5.665659427642822, | |
| "eval_runtime": 4.359, | |
| "eval_samples_per_second": 229.642, | |
| "eval_steps_per_second": 14.453, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.622066339457644e-05, | |
| "loss": 5.6051, | |
| "step": 228500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.6190500320935104e-05, | |
| "loss": 5.6086, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 5.674694538116455, | |
| "eval_runtime": 4.2969, | |
| "eval_samples_per_second": 232.959, | |
| "eval_steps_per_second": 14.662, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.616033724729377e-05, | |
| "loss": 5.5967, | |
| "step": 229500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.613023449979972e-05, | |
| "loss": 5.6055, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 5.6704535484313965, | |
| "eval_runtime": 4.3875, | |
| "eval_samples_per_second": 228.15, | |
| "eval_steps_per_second": 14.359, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.610007142615838e-05, | |
| "loss": 5.5994, | |
| "step": 230500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.6069908352517054e-05, | |
| "loss": 5.6073, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 5.617954730987549, | |
| "eval_runtime": 4.3854, | |
| "eval_samples_per_second": 228.258, | |
| "eval_steps_per_second": 14.366, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.6039745278875714e-05, | |
| "loss": 5.5921, | |
| "step": 231500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.600958220523438e-05, | |
| "loss": 5.6037, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 5.635035991668701, | |
| "eval_runtime": 4.3159, | |
| "eval_samples_per_second": 231.935, | |
| "eval_steps_per_second": 14.597, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.597941913159305e-05, | |
| "loss": 5.6059, | |
| "step": 232500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.5949316384099e-05, | |
| "loss": 5.6097, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 5.596395015716553, | |
| "eval_runtime": 4.4067, | |
| "eval_samples_per_second": 227.157, | |
| "eval_steps_per_second": 14.297, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.591915331045766e-05, | |
| "loss": 5.5941, | |
| "step": 233500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.5888990236816325e-05, | |
| "loss": 5.5931, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 5.672845840454102, | |
| "eval_runtime": 4.3691, | |
| "eval_samples_per_second": 229.106, | |
| "eval_steps_per_second": 14.419, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.585882716317499e-05, | |
| "loss": 5.6034, | |
| "step": 234500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.582866408953366e-05, | |
| "loss": 5.6017, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 5.563544273376465, | |
| "eval_runtime": 4.2928, | |
| "eval_samples_per_second": 233.179, | |
| "eval_steps_per_second": 14.676, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.57985613420396e-05, | |
| "loss": 5.6184, | |
| "step": 235500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.576839826839827e-05, | |
| "loss": 5.5987, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 5.619165420532227, | |
| "eval_runtime": 4.4266, | |
| "eval_samples_per_second": 226.133, | |
| "eval_steps_per_second": 14.232, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.5738235194756936e-05, | |
| "loss": 5.6069, | |
| "step": 236500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.5708072121115596e-05, | |
| "loss": 5.6052, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 5.640077114105225, | |
| "eval_runtime": 4.304, | |
| "eval_samples_per_second": 232.574, | |
| "eval_steps_per_second": 14.638, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.567790904747427e-05, | |
| "loss": 5.6022, | |
| "step": 237500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.564780629998021e-05, | |
| "loss": 5.5994, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 5.631266117095947, | |
| "eval_runtime": 4.339, | |
| "eval_samples_per_second": 230.698, | |
| "eval_steps_per_second": 14.519, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.561764322633888e-05, | |
| "loss": 5.6028, | |
| "step": 238500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.5587480152697546e-05, | |
| "loss": 5.6057, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 5.639108180999756, | |
| "eval_runtime": 4.3269, | |
| "eval_samples_per_second": 231.343, | |
| "eval_steps_per_second": 14.56, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.555731707905621e-05, | |
| "loss": 5.6019, | |
| "step": 239500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.552715400541487e-05, | |
| "loss": 5.6002, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 5.599489212036133, | |
| "eval_runtime": 4.2746, | |
| "eval_samples_per_second": 234.176, | |
| "eval_steps_per_second": 14.738, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.549705125792083e-05, | |
| "loss": 5.604, | |
| "step": 240500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.546688818427949e-05, | |
| "loss": 5.6023, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 5.6258158683776855, | |
| "eval_runtime": 4.3904, | |
| "eval_samples_per_second": 227.997, | |
| "eval_steps_per_second": 14.349, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.543672511063816e-05, | |
| "loss": 5.5952, | |
| "step": 241500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.5406562036996824e-05, | |
| "loss": 5.5972, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 5.620538711547852, | |
| "eval_runtime": 4.4432, | |
| "eval_samples_per_second": 225.29, | |
| "eval_steps_per_second": 14.179, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.537639896335549e-05, | |
| "loss": 5.5949, | |
| "step": 242500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.5346296215861434e-05, | |
| "loss": 5.5929, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 5.622025489807129, | |
| "eval_runtime": 6.0726, | |
| "eval_samples_per_second": 164.839, | |
| "eval_steps_per_second": 10.374, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.53161331422201e-05, | |
| "loss": 5.6055, | |
| "step": 243500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.528597006857877e-05, | |
| "loss": 5.6057, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 5.636081218719482, | |
| "eval_runtime": 4.3951, | |
| "eval_samples_per_second": 227.752, | |
| "eval_steps_per_second": 14.334, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.525580699493743e-05, | |
| "loss": 5.592, | |
| "step": 244500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.5225704247443384e-05, | |
| "loss": 5.5927, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 5.613470554351807, | |
| "eval_runtime": 4.2808, | |
| "eval_samples_per_second": 233.836, | |
| "eval_steps_per_second": 14.717, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.5195541173802044e-05, | |
| "loss": 5.5995, | |
| "step": 245500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.516537810016071e-05, | |
| "loss": 5.5932, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 5.671243667602539, | |
| "eval_runtime": 4.3622, | |
| "eval_samples_per_second": 229.469, | |
| "eval_steps_per_second": 14.442, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.513521502651937e-05, | |
| "loss": 5.5976, | |
| "step": 246500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.510511227902533e-05, | |
| "loss": 5.5954, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 5.645402431488037, | |
| "eval_runtime": 4.3336, | |
| "eval_samples_per_second": 230.987, | |
| "eval_steps_per_second": 14.538, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.507494920538399e-05, | |
| "loss": 5.5893, | |
| "step": 247500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.5044786131742655e-05, | |
| "loss": 5.6012, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 5.6515679359436035, | |
| "eval_runtime": 4.3246, | |
| "eval_samples_per_second": 231.466, | |
| "eval_steps_per_second": 14.568, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.501462305810132e-05, | |
| "loss": 5.6031, | |
| "step": 248500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.498445998445999e-05, | |
| "loss": 5.5963, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 5.553864479064941, | |
| "eval_runtime": 4.4624, | |
| "eval_samples_per_second": 224.32, | |
| "eval_steps_per_second": 14.118, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.495435723696593e-05, | |
| "loss": 5.5976, | |
| "step": 249500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.492425448947188e-05, | |
| "loss": 5.5912, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 5.589954853057861, | |
| "eval_runtime": 4.401, | |
| "eval_samples_per_second": 227.45, | |
| "eval_steps_per_second": 14.315, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.489409141583055e-05, | |
| "loss": 5.6036, | |
| "step": 250500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.486392834218921e-05, | |
| "loss": 5.5945, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 5.610245227813721, | |
| "eval_runtime": 4.3039, | |
| "eval_samples_per_second": 232.58, | |
| "eval_steps_per_second": 14.638, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.483376526854788e-05, | |
| "loss": 5.6045, | |
| "step": 251500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.480360219490654e-05, | |
| "loss": 5.5801, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 5.662520885467529, | |
| "eval_runtime": 4.4164, | |
| "eval_samples_per_second": 226.657, | |
| "eval_steps_per_second": 14.265, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.477343912126521e-05, | |
| "loss": 5.5911, | |
| "step": 252500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.4743276047623876e-05, | |
| "loss": 5.5971, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 5.606277942657471, | |
| "eval_runtime": 4.2933, | |
| "eval_samples_per_second": 233.156, | |
| "eval_steps_per_second": 14.674, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.471311297398254e-05, | |
| "loss": 5.5897, | |
| "step": 253500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.4683010226488486e-05, | |
| "loss": 5.5806, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 5.616698741912842, | |
| "eval_runtime": 4.358, | |
| "eval_samples_per_second": 229.693, | |
| "eval_steps_per_second": 14.456, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.465284715284716e-05, | |
| "loss": 5.5886, | |
| "step": 254500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.462268407920582e-05, | |
| "loss": 5.6036, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 5.618276119232178, | |
| "eval_runtime": 4.391, | |
| "eval_samples_per_second": 227.965, | |
| "eval_steps_per_second": 14.347, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.459252100556449e-05, | |
| "loss": 5.5938, | |
| "step": 255500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.4562357931923154e-05, | |
| "loss": 5.6139, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 5.62522554397583, | |
| "eval_runtime": 4.3609, | |
| "eval_samples_per_second": 229.539, | |
| "eval_steps_per_second": 14.447, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.453231551057638e-05, | |
| "loss": 5.5998, | |
| "step": 256500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.4502152436935046e-05, | |
| "loss": 5.5781, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 5.601036548614502, | |
| "eval_runtime": 4.3881, | |
| "eval_samples_per_second": 228.114, | |
| "eval_steps_per_second": 14.357, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.447198936329371e-05, | |
| "loss": 5.5866, | |
| "step": 257500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.444182628965238e-05, | |
| "loss": 5.5866, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 5.622751235961914, | |
| "eval_runtime": 4.361, | |
| "eval_samples_per_second": 229.534, | |
| "eval_steps_per_second": 14.446, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.441166321601104e-05, | |
| "loss": 5.5846, | |
| "step": 258500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.438150014236971e-05, | |
| "loss": 5.5912, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 5.602281093597412, | |
| "eval_runtime": 4.3383, | |
| "eval_samples_per_second": 230.736, | |
| "eval_steps_per_second": 14.522, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.4351337068728374e-05, | |
| "loss": 5.584, | |
| "step": 259500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.432117399508704e-05, | |
| "loss": 5.5935, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 5.619230270385742, | |
| "eval_runtime": 4.4126, | |
| "eval_samples_per_second": 226.848, | |
| "eval_steps_per_second": 14.277, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.429107124759299e-05, | |
| "loss": 5.5939, | |
| "step": 260500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.426090817395166e-05, | |
| "loss": 5.5879, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 5.617980480194092, | |
| "eval_runtime": 4.483, | |
| "eval_samples_per_second": 223.286, | |
| "eval_steps_per_second": 14.053, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.423074510031032e-05, | |
| "loss": 5.5785, | |
| "step": 261500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.4200582026668985e-05, | |
| "loss": 5.5968, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 5.606536865234375, | |
| "eval_runtime": 4.3562, | |
| "eval_samples_per_second": 229.79, | |
| "eval_steps_per_second": 14.462, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.417041895302765e-05, | |
| "loss": 5.5833, | |
| "step": 262500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.41403162055336e-05, | |
| "loss": 5.5899, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 5.632786750793457, | |
| "eval_runtime": 4.4039, | |
| "eval_samples_per_second": 227.3, | |
| "eval_steps_per_second": 14.306, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.411015313189226e-05, | |
| "loss": 5.6022, | |
| "step": 263500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.407999005825093e-05, | |
| "loss": 5.5924, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 5.664926528930664, | |
| "eval_runtime": 4.3562, | |
| "eval_samples_per_second": 229.789, | |
| "eval_steps_per_second": 14.462, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.4049826984609595e-05, | |
| "loss": 5.5992, | |
| "step": 264500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.4019663910968256e-05, | |
| "loss": 5.594, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 5.613445281982422, | |
| "eval_runtime": 4.3529, | |
| "eval_samples_per_second": 229.961, | |
| "eval_steps_per_second": 14.473, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.398956116347421e-05, | |
| "loss": 5.595, | |
| "step": 265500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.395939808983287e-05, | |
| "loss": 5.5779, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 5.641766548156738, | |
| "eval_runtime": 4.3867, | |
| "eval_samples_per_second": 228.188, | |
| "eval_steps_per_second": 14.361, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.392923501619154e-05, | |
| "loss": 5.5935, | |
| "step": 266500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.3899071942550206e-05, | |
| "loss": 5.5857, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 5.578934669494629, | |
| "eval_runtime": 4.3746, | |
| "eval_samples_per_second": 228.819, | |
| "eval_steps_per_second": 14.401, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.386890886890887e-05, | |
| "loss": 5.5911, | |
| "step": 267500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.383874579526753e-05, | |
| "loss": 5.5854, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 5.591177463531494, | |
| "eval_runtime": 4.3359, | |
| "eval_samples_per_second": 230.861, | |
| "eval_steps_per_second": 14.53, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.38085827216262e-05, | |
| "loss": 5.5984, | |
| "step": 268500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.377847997413215e-05, | |
| "loss": 5.5851, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 5.609918117523193, | |
| "eval_runtime": 6.2577, | |
| "eval_samples_per_second": 159.962, | |
| "eval_steps_per_second": 10.068, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.374831690049082e-05, | |
| "loss": 5.5783, | |
| "step": 269500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.371815382684948e-05, | |
| "loss": 5.5891, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 5.6276116371154785, | |
| "eval_runtime": 4.3901, | |
| "eval_samples_per_second": 228.014, | |
| "eval_steps_per_second": 14.351, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.368799075320815e-05, | |
| "loss": 5.5805, | |
| "step": 270500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.365788800571409e-05, | |
| "loss": 5.5853, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 5.602240562438965, | |
| "eval_runtime": 4.2864, | |
| "eval_samples_per_second": 233.528, | |
| "eval_steps_per_second": 14.698, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.362772493207276e-05, | |
| "loss": 5.5979, | |
| "step": 271500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.359756185843143e-05, | |
| "loss": 5.5948, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 5.630936145782471, | |
| "eval_runtime": 4.2788, | |
| "eval_samples_per_second": 233.942, | |
| "eval_steps_per_second": 14.724, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.356739878479009e-05, | |
| "loss": 5.5974, | |
| "step": 272500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.3537235711148754e-05, | |
| "loss": 5.5825, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 5.636594772338867, | |
| "eval_runtime": 4.3052, | |
| "eval_samples_per_second": 232.51, | |
| "eval_steps_per_second": 14.634, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.3507132963654704e-05, | |
| "loss": 5.5782, | |
| "step": 273500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.347696989001337e-05, | |
| "loss": 5.5843, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 5.65947151184082, | |
| "eval_runtime": 4.3453, | |
| "eval_samples_per_second": 230.365, | |
| "eval_steps_per_second": 14.498, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.344680681637203e-05, | |
| "loss": 5.5752, | |
| "step": 274500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.341670406887799e-05, | |
| "loss": 5.5732, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 5.613409519195557, | |
| "eval_runtime": 4.3105, | |
| "eval_samples_per_second": 232.225, | |
| "eval_steps_per_second": 14.616, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.338654099523665e-05, | |
| "loss": 5.5945, | |
| "step": 275500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.3356377921595315e-05, | |
| "loss": 5.5779, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 5.653366565704346, | |
| "eval_runtime": 4.3619, | |
| "eval_samples_per_second": 229.489, | |
| "eval_steps_per_second": 14.443, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.332621484795398e-05, | |
| "loss": 5.592, | |
| "step": 276500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.329605177431265e-05, | |
| "loss": 5.5827, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 5.661462783813477, | |
| "eval_runtime": 4.2952, | |
| "eval_samples_per_second": 233.05, | |
| "eval_steps_per_second": 14.668, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.326588870067131e-05, | |
| "loss": 5.5852, | |
| "step": 277500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.3235725627029976e-05, | |
| "loss": 5.5721, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 5.621175289154053, | |
| "eval_runtime": 4.3045, | |
| "eval_samples_per_second": 232.548, | |
| "eval_steps_per_second": 14.636, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.320556255338864e-05, | |
| "loss": 5.5806, | |
| "step": 278500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.317539947974731e-05, | |
| "loss": 5.5851, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 5.6257219314575195, | |
| "eval_runtime": 4.3249, | |
| "eval_samples_per_second": 231.453, | |
| "eval_steps_per_second": 14.567, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.314529673225326e-05, | |
| "loss": 5.5875, | |
| "step": 279500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.311513365861192e-05, | |
| "loss": 5.5788, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 5.616583347320557, | |
| "eval_runtime": 4.3483, | |
| "eval_samples_per_second": 230.203, | |
| "eval_steps_per_second": 14.488, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.3084970584970586e-05, | |
| "loss": 5.5866, | |
| "step": 280500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.305480751132925e-05, | |
| "loss": 5.5697, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 5.639812469482422, | |
| "eval_runtime": 4.4373, | |
| "eval_samples_per_second": 225.589, | |
| "eval_steps_per_second": 14.198, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.30247047638352e-05, | |
| "loss": 5.5711, | |
| "step": 281500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.299454169019386e-05, | |
| "loss": 5.5933, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 5.632999897003174, | |
| "eval_runtime": 4.4375, | |
| "eval_samples_per_second": 225.578, | |
| "eval_steps_per_second": 14.197, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.296437861655253e-05, | |
| "loss": 5.5914, | |
| "step": 282500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.29342155429112e-05, | |
| "loss": 5.5818, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 5.581757068634033, | |
| "eval_runtime": 4.3378, | |
| "eval_samples_per_second": 230.763, | |
| "eval_steps_per_second": 14.524, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.2904052469269864e-05, | |
| "loss": 5.5744, | |
| "step": 283500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.2873889395628524e-05, | |
| "loss": 5.577, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 5.626399040222168, | |
| "eval_runtime": 4.3623, | |
| "eval_samples_per_second": 229.464, | |
| "eval_steps_per_second": 14.442, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.284378664813448e-05, | |
| "loss": 5.5862, | |
| "step": 284500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.281362357449314e-05, | |
| "loss": 5.57, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 5.625292778015137, | |
| "eval_runtime": 6.6232, | |
| "eval_samples_per_second": 151.136, | |
| "eval_steps_per_second": 9.512, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.278346050085181e-05, | |
| "loss": 5.5883, | |
| "step": 285500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.2753297427210475e-05, | |
| "loss": 5.583, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 5.616182804107666, | |
| "eval_runtime": 4.3373, | |
| "eval_samples_per_second": 230.789, | |
| "eval_steps_per_second": 14.525, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.272313435356914e-05, | |
| "loss": 5.5543, | |
| "step": 286500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.26929712799278e-05, | |
| "loss": 5.5804, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 5.654087066650391, | |
| "eval_runtime": 5.9497, | |
| "eval_samples_per_second": 168.245, | |
| "eval_steps_per_second": 10.589, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.266280820628647e-05, | |
| "loss": 5.5752, | |
| "step": 287500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.2632645132645136e-05, | |
| "loss": 5.5813, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 5.568077564239502, | |
| "eval_runtime": 4.304, | |
| "eval_samples_per_second": 232.575, | |
| "eval_steps_per_second": 14.638, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.2602482059003796e-05, | |
| "loss": 5.5821, | |
| "step": 288500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.257231898536246e-05, | |
| "loss": 5.5683, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 5.624704837799072, | |
| "eval_runtime": 4.2307, | |
| "eval_samples_per_second": 236.604, | |
| "eval_steps_per_second": 14.891, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.254221623786841e-05, | |
| "loss": 5.5683, | |
| "step": 289500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.251205316422708e-05, | |
| "loss": 5.5807, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 5.592767238616943, | |
| "eval_runtime": 4.2406, | |
| "eval_samples_per_second": 236.051, | |
| "eval_steps_per_second": 14.856, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.248189009058574e-05, | |
| "loss": 5.5905, | |
| "step": 290500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.2451787343091696e-05, | |
| "loss": 5.5783, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 5.550808906555176, | |
| "eval_runtime": 6.3243, | |
| "eval_samples_per_second": 158.277, | |
| "eval_steps_per_second": 9.962, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.2421624269450356e-05, | |
| "loss": 5.5827, | |
| "step": 291500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.239146119580902e-05, | |
| "loss": 5.5793, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 5.641295433044434, | |
| "eval_runtime": 4.2972, | |
| "eval_samples_per_second": 232.941, | |
| "eval_steps_per_second": 14.661, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.236129812216769e-05, | |
| "loss": 5.5852, | |
| "step": 292500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.233113504852636e-05, | |
| "loss": 5.5576, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 5.595691680908203, | |
| "eval_runtime": 4.2537, | |
| "eval_samples_per_second": 235.322, | |
| "eval_steps_per_second": 14.81, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.230097197488502e-05, | |
| "loss": 5.5686, | |
| "step": 293500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.227080890124369e-05, | |
| "loss": 5.575, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 5.610649108886719, | |
| "eval_runtime": 4.3768, | |
| "eval_samples_per_second": 228.704, | |
| "eval_steps_per_second": 14.394, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.224064582760235e-05, | |
| "loss": 5.5757, | |
| "step": 294500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.221048275396102e-05, | |
| "loss": 5.5751, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 5.616249084472656, | |
| "eval_runtime": 4.2765, | |
| "eval_samples_per_second": 234.069, | |
| "eval_steps_per_second": 14.732, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.218038000646697e-05, | |
| "loss": 5.5724, | |
| "step": 295500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.215021693282563e-05, | |
| "loss": 5.5678, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 5.58726167678833, | |
| "eval_runtime": 4.3531, | |
| "eval_samples_per_second": 229.953, | |
| "eval_steps_per_second": 14.473, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.2120053859184295e-05, | |
| "loss": 5.5696, | |
| "step": 296500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.208989078554296e-05, | |
| "loss": 5.5762, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 5.5941548347473145, | |
| "eval_runtime": 4.1805, | |
| "eval_samples_per_second": 239.445, | |
| "eval_steps_per_second": 15.07, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.205978803804891e-05, | |
| "loss": 5.5715, | |
| "step": 297500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.202962496440757e-05, | |
| "loss": 5.5698, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 5.603238582611084, | |
| "eval_runtime": 4.2335, | |
| "eval_samples_per_second": 236.45, | |
| "eval_steps_per_second": 14.881, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.199946189076624e-05, | |
| "loss": 5.5834, | |
| "step": 298500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.1969298817124905e-05, | |
| "loss": 5.5719, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 5.640628814697266, | |
| "eval_runtime": 4.2976, | |
| "eval_samples_per_second": 232.922, | |
| "eval_steps_per_second": 14.659, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.193913574348357e-05, | |
| "loss": 5.5841, | |
| "step": 299500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.190903299598952e-05, | |
| "loss": 5.5852, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 5.6316609382629395, | |
| "eval_runtime": 6.6588, | |
| "eval_samples_per_second": 150.328, | |
| "eval_steps_per_second": 9.461, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.187886992234819e-05, | |
| "loss": 5.5728, | |
| "step": 300500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.184870684870685e-05, | |
| "loss": 5.5794, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 5.637535095214844, | |
| "eval_runtime": 4.2729, | |
| "eval_samples_per_second": 234.266, | |
| "eval_steps_per_second": 14.744, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.1818543775065516e-05, | |
| "loss": 5.5692, | |
| "step": 301500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.1788441027571465e-05, | |
| "loss": 5.5912, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 5.601639747619629, | |
| "eval_runtime": 4.2748, | |
| "eval_samples_per_second": 234.165, | |
| "eval_steps_per_second": 14.738, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.175833828007741e-05, | |
| "loss": 5.577, | |
| "step": 302500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.1728175206436075e-05, | |
| "loss": 5.5698, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 5.601426124572754, | |
| "eval_runtime": 4.2879, | |
| "eval_samples_per_second": 233.449, | |
| "eval_steps_per_second": 14.693, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.169801213279474e-05, | |
| "loss": 5.5745, | |
| "step": 303500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.166784905915341e-05, | |
| "loss": 5.5658, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 5.584649562835693, | |
| "eval_runtime": 4.2401, | |
| "eval_samples_per_second": 236.077, | |
| "eval_steps_per_second": 14.858, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.163774631165936e-05, | |
| "loss": 5.5632, | |
| "step": 304500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.1607583238018026e-05, | |
| "loss": 5.5701, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 5.594232082366943, | |
| "eval_runtime": 6.4608, | |
| "eval_samples_per_second": 154.934, | |
| "eval_steps_per_second": 9.751, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.1577420164376686e-05, | |
| "loss": 5.5869, | |
| "step": 305500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.154725709073535e-05, | |
| "loss": 5.5681, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 5.6190314292907715, | |
| "eval_runtime": 4.2645, | |
| "eval_samples_per_second": 234.731, | |
| "eval_steps_per_second": 14.773, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.151709401709402e-05, | |
| "loss": 5.5742, | |
| "step": 306500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.148693094345269e-05, | |
| "loss": 5.5584, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 5.601367950439453, | |
| "eval_runtime": 6.1261, | |
| "eval_samples_per_second": 163.4, | |
| "eval_steps_per_second": 10.284, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.145682819595863e-05, | |
| "loss": 5.5774, | |
| "step": 307500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.14266651223173e-05, | |
| "loss": 5.5788, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 5.602400302886963, | |
| "eval_runtime": 4.2475, | |
| "eval_samples_per_second": 235.665, | |
| "eval_steps_per_second": 14.832, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.1396502048675963e-05, | |
| "loss": 5.5696, | |
| "step": 308500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.136633897503463e-05, | |
| "loss": 5.5806, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 5.596291542053223, | |
| "eval_runtime": 4.3852, | |
| "eval_samples_per_second": 228.268, | |
| "eval_steps_per_second": 14.366, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.13361759013933e-05, | |
| "loss": 5.5689, | |
| "step": 309500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.130601282775196e-05, | |
| "loss": 5.555, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 5.634425163269043, | |
| "eval_runtime": 4.2821, | |
| "eval_samples_per_second": 233.764, | |
| "eval_steps_per_second": 14.712, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.1275849754110625e-05, | |
| "loss": 5.5582, | |
| "step": 310500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.124568668046929e-05, | |
| "loss": 5.5638, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 5.537110328674316, | |
| "eval_runtime": 4.2827, | |
| "eval_samples_per_second": 233.729, | |
| "eval_steps_per_second": 14.71, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.121558393297524e-05, | |
| "loss": 5.559, | |
| "step": 311500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.11854208593339e-05, | |
| "loss": 5.5625, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 5.598823070526123, | |
| "eval_runtime": 4.1935, | |
| "eval_samples_per_second": 238.704, | |
| "eval_steps_per_second": 15.023, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.115525778569257e-05, | |
| "loss": 5.5682, | |
| "step": 312500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.1125094712051235e-05, | |
| "loss": 5.5701, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 5.606781005859375, | |
| "eval_runtime": 4.1581, | |
| "eval_samples_per_second": 240.735, | |
| "eval_steps_per_second": 15.151, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.1094991964557185e-05, | |
| "loss": 5.5559, | |
| "step": 313500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.1064889217063134e-05, | |
| "loss": 5.5611, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 5.584975242614746, | |
| "eval_runtime": 4.1497, | |
| "eval_samples_per_second": 241.223, | |
| "eval_steps_per_second": 15.182, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.10347261434218e-05, | |
| "loss": 5.5758, | |
| "step": 314500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.100456306978046e-05, | |
| "loss": 5.5857, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 5.614663600921631, | |
| "eval_runtime": 4.0061, | |
| "eval_samples_per_second": 249.869, | |
| "eval_steps_per_second": 15.726, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.097439999613913e-05, | |
| "loss": 5.5646, | |
| "step": 315500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.0944236922497795e-05, | |
| "loss": 5.5609, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 5.600166320800781, | |
| "eval_runtime": 3.7879, | |
| "eval_samples_per_second": 264.264, | |
| "eval_steps_per_second": 16.632, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.0914073848856456e-05, | |
| "loss": 5.5657, | |
| "step": 316500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.088391077521512e-05, | |
| "loss": 5.5646, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 5.617602825164795, | |
| "eval_runtime": 3.9864, | |
| "eval_samples_per_second": 251.102, | |
| "eval_steps_per_second": 15.804, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.085374770157379e-05, | |
| "loss": 5.567, | |
| "step": 317500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.082364495407974e-05, | |
| "loss": 5.5691, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 5.588697910308838, | |
| "eval_runtime": 4.0872, | |
| "eval_samples_per_second": 244.913, | |
| "eval_steps_per_second": 15.414, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.07934818804384e-05, | |
| "loss": 5.5731, | |
| "step": 318500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.076331880679707e-05, | |
| "loss": 5.5518, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 5.6083807945251465, | |
| "eval_runtime": 4.1744, | |
| "eval_samples_per_second": 239.797, | |
| "eval_steps_per_second": 15.092, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.073315573315573e-05, | |
| "loss": 5.5795, | |
| "step": 319500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.070305298566168e-05, | |
| "loss": 5.5704, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 5.620527744293213, | |
| "eval_runtime": 4.2147, | |
| "eval_samples_per_second": 237.505, | |
| "eval_steps_per_second": 14.948, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.067295023816763e-05, | |
| "loss": 5.5635, | |
| "step": 320500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.06427871645263e-05, | |
| "loss": 5.5752, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 5.60969877243042, | |
| "eval_runtime": 4.206, | |
| "eval_samples_per_second": 237.991, | |
| "eval_steps_per_second": 14.978, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.061262409088496e-05, | |
| "loss": 5.5772, | |
| "step": 321500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.058246101724363e-05, | |
| "loss": 5.5723, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 5.585223197937012, | |
| "eval_runtime": 4.1426, | |
| "eval_samples_per_second": 241.634, | |
| "eval_steps_per_second": 15.208, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.055229794360229e-05, | |
| "loss": 5.5594, | |
| "step": 322500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.052213486996096e-05, | |
| "loss": 5.5613, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 5.594601631164551, | |
| "eval_runtime": 4.029, | |
| "eval_samples_per_second": 248.45, | |
| "eval_steps_per_second": 15.637, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.0491971796319624e-05, | |
| "loss": 5.5452, | |
| "step": 323500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.0461808722678287e-05, | |
| "loss": 5.5723, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 5.622194290161133, | |
| "eval_runtime": 4.1571, | |
| "eval_samples_per_second": 240.791, | |
| "eval_steps_per_second": 15.155, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.0431705975184237e-05, | |
| "loss": 5.5765, | |
| "step": 324500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.04015429015429e-05, | |
| "loss": 5.5653, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 5.609323024749756, | |
| "eval_runtime": 4.2445, | |
| "eval_samples_per_second": 235.834, | |
| "eval_steps_per_second": 14.843, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.037137982790157e-05, | |
| "loss": 5.56, | |
| "step": 325500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.034121675426023e-05, | |
| "loss": 5.5604, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 5.608053207397461, | |
| "eval_runtime": 4.2784, | |
| "eval_samples_per_second": 233.968, | |
| "eval_steps_per_second": 14.725, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.03110536806189e-05, | |
| "loss": 5.5698, | |
| "step": 326500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.0280950933124848e-05, | |
| "loss": 5.5602, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 5.6086883544921875, | |
| "eval_runtime": 4.2993, | |
| "eval_samples_per_second": 232.828, | |
| "eval_steps_per_second": 14.654, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.0250787859483515e-05, | |
| "loss": 5.5624, | |
| "step": 327500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.0220624785842178e-05, | |
| "loss": 5.577, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 5.620945453643799, | |
| "eval_runtime": 4.2859, | |
| "eval_samples_per_second": 233.559, | |
| "eval_steps_per_second": 14.699, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.0190461712200845e-05, | |
| "loss": 5.5651, | |
| "step": 328500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.0160419290854074e-05, | |
| "loss": 5.56, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 5.617950439453125, | |
| "eval_runtime": 4.181, | |
| "eval_samples_per_second": 239.419, | |
| "eval_steps_per_second": 15.068, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.0130256217212737e-05, | |
| "loss": 5.5633, | |
| "step": 329500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.0100093143571408e-05, | |
| "loss": 5.567, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 5.581989288330078, | |
| "eval_runtime": 4.1844, | |
| "eval_samples_per_second": 239.221, | |
| "eval_steps_per_second": 15.056, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.0069930069930068e-05, | |
| "loss": 5.5607, | |
| "step": 330500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.003976699628874e-05, | |
| "loss": 5.5698, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 5.626122951507568, | |
| "eval_runtime": 4.2366, | |
| "eval_samples_per_second": 236.277, | |
| "eval_steps_per_second": 14.871, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.00096039226474e-05, | |
| "loss": 5.5686, | |
| "step": 331500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.997944084900607e-05, | |
| "loss": 5.5682, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 5.587873458862305, | |
| "eval_runtime": 4.2898, | |
| "eval_samples_per_second": 233.342, | |
| "eval_steps_per_second": 14.686, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.9949277775364732e-05, | |
| "loss": 5.5734, | |
| "step": 332500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.99191147017234e-05, | |
| "loss": 5.5789, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 5.579086780548096, | |
| "eval_runtime": 4.247, | |
| "eval_samples_per_second": 235.697, | |
| "eval_steps_per_second": 14.834, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9889011954229346e-05, | |
| "loss": 5.5631, | |
| "step": 333500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9858848880588013e-05, | |
| "loss": 5.5566, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 5.596020221710205, | |
| "eval_runtime": 3.9959, | |
| "eval_samples_per_second": 250.505, | |
| "eval_steps_per_second": 15.766, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9828685806946676e-05, | |
| "loss": 5.5698, | |
| "step": 334500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9798522733305346e-05, | |
| "loss": 5.566, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 5.61091947555542, | |
| "eval_runtime": 4.2033, | |
| "eval_samples_per_second": 238.144, | |
| "eval_steps_per_second": 14.988, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9768419985811293e-05, | |
| "loss": 5.5673, | |
| "step": 335500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.973825691216996e-05, | |
| "loss": 5.5628, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 5.610008239746094, | |
| "eval_runtime": 4.2081, | |
| "eval_samples_per_second": 237.875, | |
| "eval_steps_per_second": 14.971, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9708093838528623e-05, | |
| "loss": 5.5706, | |
| "step": 336500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.967793076488729e-05, | |
| "loss": 5.5726, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 5.600627422332764, | |
| "eval_runtime": 4.3279, | |
| "eval_samples_per_second": 231.29, | |
| "eval_steps_per_second": 14.557, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9647767691245954e-05, | |
| "loss": 5.5503, | |
| "step": 337500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.96176649437519e-05, | |
| "loss": 5.5895, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 5.598173141479492, | |
| "eval_runtime": 4.1467, | |
| "eval_samples_per_second": 241.398, | |
| "eval_steps_per_second": 15.193, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9587501870110567e-05, | |
| "loss": 5.5667, | |
| "step": 338500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9557399122616513e-05, | |
| "loss": 5.5607, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 5.594642162322998, | |
| "eval_runtime": 4.1122, | |
| "eval_samples_per_second": 243.425, | |
| "eval_steps_per_second": 15.32, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9527236048975183e-05, | |
| "loss": 5.5682, | |
| "step": 339500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9497072975333844e-05, | |
| "loss": 5.5516, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 5.622577667236328, | |
| "eval_runtime": 3.8072, | |
| "eval_samples_per_second": 262.92, | |
| "eval_steps_per_second": 16.547, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9466909901692514e-05, | |
| "loss": 5.5667, | |
| "step": 340500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9436746828051178e-05, | |
| "loss": 5.5565, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 5.5851006507873535, | |
| "eval_runtime": 3.8861, | |
| "eval_samples_per_second": 257.585, | |
| "eval_steps_per_second": 16.212, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9406583754409844e-05, | |
| "loss": 5.5713, | |
| "step": 341500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9376420680768508e-05, | |
| "loss": 5.5666, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 5.600591659545898, | |
| "eval_runtime": 5.223, | |
| "eval_samples_per_second": 191.654, | |
| "eval_steps_per_second": 12.062, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9346257607127175e-05, | |
| "loss": 5.552, | |
| "step": 342500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.931615485963312e-05, | |
| "loss": 5.5644, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 5.608797550201416, | |
| "eval_runtime": 4.1399, | |
| "eval_samples_per_second": 241.796, | |
| "eval_steps_per_second": 15.218, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.928599178599179e-05, | |
| "loss": 5.5612, | |
| "step": 343500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.9255828712350452e-05, | |
| "loss": 5.5712, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 5.611100673675537, | |
| "eval_runtime": 4.0817, | |
| "eval_samples_per_second": 245.242, | |
| "eval_steps_per_second": 15.435, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.9225665638709122e-05, | |
| "loss": 5.5511, | |
| "step": 344500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.9195562891215068e-05, | |
| "loss": 5.5501, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 5.617428302764893, | |
| "eval_runtime": 4.2409, | |
| "eval_samples_per_second": 236.035, | |
| "eval_steps_per_second": 14.855, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.916539981757373e-05, | |
| "loss": 5.5677, | |
| "step": 345500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.91352367439324e-05, | |
| "loss": 5.5761, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 5.5843377113342285, | |
| "eval_runtime": 4.3583, | |
| "eval_samples_per_second": 229.679, | |
| "eval_steps_per_second": 14.455, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.9105073670291062e-05, | |
| "loss": 5.5865, | |
| "step": 346500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.907491059664973e-05, | |
| "loss": 5.5604, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 5.591548919677734, | |
| "eval_runtime": 4.2343, | |
| "eval_samples_per_second": 236.401, | |
| "eval_steps_per_second": 14.878, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.9044807849155675e-05, | |
| "loss": 5.5721, | |
| "step": 347500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.9014644775514342e-05, | |
| "loss": 5.559, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 5.568837642669678, | |
| "eval_runtime": 4.2724, | |
| "eval_samples_per_second": 234.292, | |
| "eval_steps_per_second": 14.746, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.8984481701873006e-05, | |
| "loss": 5.5726, | |
| "step": 348500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.8954318628231676e-05, | |
| "loss": 5.5715, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 5.614943504333496, | |
| "eval_runtime": 4.2628, | |
| "eval_samples_per_second": 234.823, | |
| "eval_steps_per_second": 14.779, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.8924276206884905e-05, | |
| "loss": 5.5576, | |
| "step": 349500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.8894113133243572e-05, | |
| "loss": 5.5667, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 5.581839561462402, | |
| "eval_runtime": 4.319, | |
| "eval_samples_per_second": 231.765, | |
| "eval_steps_per_second": 14.587, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.8863950059602236e-05, | |
| "loss": 5.5802, | |
| "step": 350500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.88337869859609e-05, | |
| "loss": 5.5684, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 5.611480236053467, | |
| "eval_runtime": 4.2644, | |
| "eval_samples_per_second": 234.732, | |
| "eval_steps_per_second": 14.773, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.8803623912319566e-05, | |
| "loss": 5.5583, | |
| "step": 351500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.877346083867823e-05, | |
| "loss": 5.5526, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 5.582302570343018, | |
| "eval_runtime": 4.2931, | |
| "eval_samples_per_second": 233.165, | |
| "eval_steps_per_second": 14.675, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.874335809118418e-05, | |
| "loss": 5.5705, | |
| "step": 352500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.8713195017542843e-05, | |
| "loss": 5.5763, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 5.567468643188477, | |
| "eval_runtime": 4.2538, | |
| "eval_samples_per_second": 235.319, | |
| "eval_steps_per_second": 14.81, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.8683031943901513e-05, | |
| "loss": 5.5613, | |
| "step": 353500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.8652868870260173e-05, | |
| "loss": 5.5607, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 5.62228536605835, | |
| "eval_runtime": 4.2752, | |
| "eval_samples_per_second": 234.142, | |
| "eval_steps_per_second": 14.736, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.8622705796618844e-05, | |
| "loss": 5.5693, | |
| "step": 354500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.859260304912479e-05, | |
| "loss": 5.5688, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 5.592869281768799, | |
| "eval_runtime": 4.2324, | |
| "eval_samples_per_second": 236.51, | |
| "eval_steps_per_second": 14.885, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.8562439975483457e-05, | |
| "loss": 5.5638, | |
| "step": 355500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.853227690184212e-05, | |
| "loss": 5.5509, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 5.573236465454102, | |
| "eval_runtime": 4.1603, | |
| "eval_samples_per_second": 240.606, | |
| "eval_steps_per_second": 15.143, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.8502113828200787e-05, | |
| "loss": 5.5607, | |
| "step": 356500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.847195075455945e-05, | |
| "loss": 5.5653, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 5.6225433349609375, | |
| "eval_runtime": 4.2135, | |
| "eval_samples_per_second": 237.568, | |
| "eval_steps_per_second": 14.952, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.8441787680918118e-05, | |
| "loss": 5.5625, | |
| "step": 357500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.841162460727678e-05, | |
| "loss": 5.5612, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 5.620114326477051, | |
| "eval_runtime": 4.2253, | |
| "eval_samples_per_second": 236.907, | |
| "eval_steps_per_second": 14.91, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.8381461533635452e-05, | |
| "loss": 5.5458, | |
| "step": 358500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.8351358786141398e-05, | |
| "loss": 5.5536, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 5.56666374206543, | |
| "eval_runtime": 4.1642, | |
| "eval_samples_per_second": 240.385, | |
| "eval_steps_per_second": 15.129, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.8321195712500058e-05, | |
| "loss": 5.5679, | |
| "step": 359500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.829103263885873e-05, | |
| "loss": 5.5517, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 5.610234260559082, | |
| "eval_runtime": 4.1981, | |
| "eval_samples_per_second": 238.442, | |
| "eval_steps_per_second": 15.007, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.826086956521739e-05, | |
| "loss": 5.5577, | |
| "step": 360500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.823070649157606e-05, | |
| "loss": 5.5618, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 5.579962730407715, | |
| "eval_runtime": 4.2993, | |
| "eval_samples_per_second": 232.831, | |
| "eval_steps_per_second": 14.654, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8200603744082005e-05, | |
| "loss": 5.5503, | |
| "step": 361500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8170500996587955e-05, | |
| "loss": 5.5654, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 5.613447666168213, | |
| "eval_runtime": 4.2494, | |
| "eval_samples_per_second": 235.562, | |
| "eval_steps_per_second": 14.826, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.814033792294662e-05, | |
| "loss": 5.56, | |
| "step": 362500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.811017484930529e-05, | |
| "loss": 5.547, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 5.580785274505615, | |
| "eval_runtime": 4.2913, | |
| "eval_samples_per_second": 233.261, | |
| "eval_steps_per_second": 14.681, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.808001177566395e-05, | |
| "loss": 5.5518, | |
| "step": 363500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.804984870202262e-05, | |
| "loss": 5.5466, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 5.616759300231934, | |
| "eval_runtime": 4.2299, | |
| "eval_samples_per_second": 236.648, | |
| "eval_steps_per_second": 14.894, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.8019685628381283e-05, | |
| "loss": 5.5547, | |
| "step": 364500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.798952255473995e-05, | |
| "loss": 5.5541, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 5.554247856140137, | |
| "eval_runtime": 4.201, | |
| "eval_samples_per_second": 238.274, | |
| "eval_steps_per_second": 14.996, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7959359481098613e-05, | |
| "loss": 5.5566, | |
| "step": 365500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.792919640745728e-05, | |
| "loss": 5.5548, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 5.5636162757873535, | |
| "eval_runtime": 4.2679, | |
| "eval_samples_per_second": 234.542, | |
| "eval_steps_per_second": 14.761, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.7899093659963227e-05, | |
| "loss": 5.5579, | |
| "step": 366500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.786893058632189e-05, | |
| "loss": 5.5524, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 5.584085941314697, | |
| "eval_runtime": 4.2363, | |
| "eval_samples_per_second": 236.294, | |
| "eval_steps_per_second": 14.872, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.7838767512680557e-05, | |
| "loss": 5.5657, | |
| "step": 367500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.780860443903922e-05, | |
| "loss": 5.5628, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 5.601650238037109, | |
| "eval_runtime": 4.2707, | |
| "eval_samples_per_second": 234.387, | |
| "eval_steps_per_second": 14.752, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.7778501691545174e-05, | |
| "loss": 5.5471, | |
| "step": 368500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.7748338617903834e-05, | |
| "loss": 5.5603, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 5.596165657043457, | |
| "eval_runtime": 4.23, | |
| "eval_samples_per_second": 236.643, | |
| "eval_steps_per_second": 14.894, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.7718175544262504e-05, | |
| "loss": 5.5684, | |
| "step": 369500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.7688012470621168e-05, | |
| "loss": 5.5528, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 5.604942798614502, | |
| "eval_runtime": 4.1427, | |
| "eval_samples_per_second": 241.628, | |
| "eval_steps_per_second": 15.207, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.7657909723127117e-05, | |
| "loss": 5.5509, | |
| "step": 370500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.762774664948578e-05, | |
| "loss": 5.5528, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 5.5896897315979, | |
| "eval_runtime": 4.1957, | |
| "eval_samples_per_second": 238.578, | |
| "eval_steps_per_second": 15.015, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.759764390199173e-05, | |
| "loss": 5.5553, | |
| "step": 371500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.7567480828350394e-05, | |
| "loss": 5.5542, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 5.589568138122559, | |
| "eval_runtime": 4.162, | |
| "eval_samples_per_second": 240.512, | |
| "eval_steps_per_second": 15.137, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.7537317754709058e-05, | |
| "loss": 5.5597, | |
| "step": 372500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.7507154681067725e-05, | |
| "loss": 5.5624, | |
| "step": 373000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 5.575145244598389, | |
| "eval_runtime": 4.052, | |
| "eval_samples_per_second": 247.036, | |
| "eval_steps_per_second": 15.548, | |
| "step": 373000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.747705193357367e-05, | |
| "loss": 5.5584, | |
| "step": 373500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.744688885993234e-05, | |
| "loss": 5.5456, | |
| "step": 374000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 5.605469226837158, | |
| "eval_runtime": 4.0454, | |
| "eval_samples_per_second": 247.441, | |
| "eval_steps_per_second": 15.573, | |
| "step": 374000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.7416725786291005e-05, | |
| "loss": 5.5504, | |
| "step": 374500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.738656271264967e-05, | |
| "loss": 5.5575, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 5.579885005950928, | |
| "eval_runtime": 4.0178, | |
| "eval_samples_per_second": 249.138, | |
| "eval_steps_per_second": 15.68, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.7356399639008335e-05, | |
| "loss": 5.5487, | |
| "step": 375500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.7326236565367002e-05, | |
| "loss": 5.5439, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 5.579631328582764, | |
| "eval_runtime": 5.2771, | |
| "eval_samples_per_second": 189.686, | |
| "eval_steps_per_second": 11.938, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.729613381787295e-05, | |
| "loss": 5.5649, | |
| "step": 376500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.7265970744231615e-05, | |
| "loss": 5.5515, | |
| "step": 377000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 5.597219944000244, | |
| "eval_runtime": 4.0434, | |
| "eval_samples_per_second": 247.561, | |
| "eval_steps_per_second": 15.581, | |
| "step": 377000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.723580767059028e-05, | |
| "loss": 5.559, | |
| "step": 377500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.720564459694895e-05, | |
| "loss": 5.5702, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 5.597592353820801, | |
| "eval_runtime": 3.8939, | |
| "eval_samples_per_second": 257.067, | |
| "eval_steps_per_second": 16.179, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.717548152330761e-05, | |
| "loss": 5.561, | |
| "step": 378500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.7145378775813562e-05, | |
| "loss": 5.5536, | |
| "step": 379000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 5.638396739959717, | |
| "eval_runtime": 4.0063, | |
| "eval_samples_per_second": 249.856, | |
| "eval_steps_per_second": 15.725, | |
| "step": 379000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.7115215702172226e-05, | |
| "loss": 5.5627, | |
| "step": 379500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.708505262853089e-05, | |
| "loss": 5.555, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 5.568854808807373, | |
| "eval_runtime": 4.112, | |
| "eval_samples_per_second": 243.436, | |
| "eval_steps_per_second": 15.321, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.7054889554889556e-05, | |
| "loss": 5.5682, | |
| "step": 380500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.702472648124822e-05, | |
| "loss": 5.5562, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 5.613949298858643, | |
| "eval_runtime": 4.1925, | |
| "eval_samples_per_second": 238.759, | |
| "eval_steps_per_second": 15.027, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.6994563407606887e-05, | |
| "loss": 5.5564, | |
| "step": 381500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.696440033396555e-05, | |
| "loss": 5.5478, | |
| "step": 382000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 5.5822858810424805, | |
| "eval_runtime": 4.2141, | |
| "eval_samples_per_second": 237.533, | |
| "eval_steps_per_second": 14.95, | |
| "step": 382000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.6934237260324218e-05, | |
| "loss": 5.5597, | |
| "step": 382500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.6904134512830164e-05, | |
| "loss": 5.5682, | |
| "step": 383000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 5.5694403648376465, | |
| "eval_runtime": 4.2372, | |
| "eval_samples_per_second": 236.243, | |
| "eval_steps_per_second": 14.868, | |
| "step": 383000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.6873971439188834e-05, | |
| "loss": 5.5571, | |
| "step": 383500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.6843808365547494e-05, | |
| "loss": 5.56, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 5.621694564819336, | |
| "eval_runtime": 4.1243, | |
| "eval_samples_per_second": 242.707, | |
| "eval_steps_per_second": 15.275, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.6813645291906165e-05, | |
| "loss": 5.5608, | |
| "step": 384500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.6783482218264828e-05, | |
| "loss": 5.5455, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 5.554786205291748, | |
| "eval_runtime": 5.749, | |
| "eval_samples_per_second": 174.116, | |
| "eval_steps_per_second": 10.958, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.6753319144623495e-05, | |
| "loss": 5.5584, | |
| "step": 385500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.672315607098216e-05, | |
| "loss": 5.5682, | |
| "step": 386000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 5.536126136779785, | |
| "eval_runtime": 4.2461, | |
| "eval_samples_per_second": 235.746, | |
| "eval_steps_per_second": 14.837, | |
| "step": 386000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.6693053323488108e-05, | |
| "loss": 5.5461, | |
| "step": 386500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.6662890249846772e-05, | |
| "loss": 5.5556, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 5.569164276123047, | |
| "eval_runtime": 4.2217, | |
| "eval_samples_per_second": 237.109, | |
| "eval_steps_per_second": 14.923, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.6632727176205442e-05, | |
| "loss": 5.5503, | |
| "step": 387500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.6602564102564102e-05, | |
| "loss": 5.561, | |
| "step": 388000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 5.604675769805908, | |
| "eval_runtime": 4.2406, | |
| "eval_samples_per_second": 236.052, | |
| "eval_steps_per_second": 14.856, | |
| "step": 388000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.6572401028922773e-05, | |
| "loss": 5.5453, | |
| "step": 388500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.654229828142872e-05, | |
| "loss": 5.5681, | |
| "step": 389000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 5.55439567565918, | |
| "eval_runtime": 4.2063, | |
| "eval_samples_per_second": 237.977, | |
| "eval_steps_per_second": 14.978, | |
| "step": 389000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.651213520778738e-05, | |
| "loss": 5.5375, | |
| "step": 389500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.648197213414605e-05, | |
| "loss": 5.5561, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 5.5874738693237305, | |
| "eval_runtime": 4.1774, | |
| "eval_samples_per_second": 239.624, | |
| "eval_steps_per_second": 15.081, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.6451809060504713e-05, | |
| "loss": 5.5464, | |
| "step": 390500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.642164598686338e-05, | |
| "loss": 5.5325, | |
| "step": 391000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 5.5877885818481445, | |
| "eval_runtime": 4.0293, | |
| "eval_samples_per_second": 248.429, | |
| "eval_steps_per_second": 15.635, | |
| "step": 391000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6391543239369326e-05, | |
| "loss": 5.5384, | |
| "step": 391500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6361380165727993e-05, | |
| "loss": 5.5592, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 5.5823540687561035, | |
| "eval_runtime": 3.8746, | |
| "eval_samples_per_second": 258.349, | |
| "eval_steps_per_second": 16.26, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6331217092086657e-05, | |
| "loss": 5.5406, | |
| "step": 392500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6301054018445327e-05, | |
| "loss": 5.554, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 5.59796667098999, | |
| "eval_runtime": 3.8288, | |
| "eval_samples_per_second": 261.442, | |
| "eval_steps_per_second": 16.454, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6270890944803987e-05, | |
| "loss": 5.5465, | |
| "step": 393500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.6240727871162658e-05, | |
| "loss": 5.546, | |
| "step": 394000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 5.55270528793335, | |
| "eval_runtime": 4.0947, | |
| "eval_samples_per_second": 244.462, | |
| "eval_steps_per_second": 15.386, | |
| "step": 394000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.6210625123668604e-05, | |
| "loss": 5.5609, | |
| "step": 394500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.618046205002727e-05, | |
| "loss": 5.5515, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 5.575203895568848, | |
| "eval_runtime": 4.2143, | |
| "eval_samples_per_second": 237.525, | |
| "eval_steps_per_second": 14.949, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.6150298976385934e-05, | |
| "loss": 5.5391, | |
| "step": 395500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.6120135902744598e-05, | |
| "loss": 5.5524, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 5.595301151275635, | |
| "eval_runtime": 4.0739, | |
| "eval_samples_per_second": 245.713, | |
| "eval_steps_per_second": 15.464, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.6089972829103265e-05, | |
| "loss": 5.5546, | |
| "step": 396500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.605987008160921e-05, | |
| "loss": 5.5506, | |
| "step": 397000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 5.568810939788818, | |
| "eval_runtime": 4.1531, | |
| "eval_samples_per_second": 241.022, | |
| "eval_steps_per_second": 15.169, | |
| "step": 397000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.6029707007967878e-05, | |
| "loss": 5.5422, | |
| "step": 397500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.5999604260473824e-05, | |
| "loss": 5.5606, | |
| "step": 398000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 5.557425022125244, | |
| "eval_runtime": 4.2221, | |
| "eval_samples_per_second": 237.084, | |
| "eval_steps_per_second": 14.921, | |
| "step": 398000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.5969441186832494e-05, | |
| "loss": 5.5471, | |
| "step": 398500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.5939278113191158e-05, | |
| "loss": 5.5514, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 5.553510665893555, | |
| "eval_runtime": 4.1728, | |
| "eval_samples_per_second": 239.885, | |
| "eval_steps_per_second": 15.098, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.5909115039549825e-05, | |
| "loss": 5.5371, | |
| "step": 399500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.587895196590849e-05, | |
| "loss": 5.5452, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 5.55861759185791, | |
| "eval_runtime": 4.2253, | |
| "eval_samples_per_second": 236.905, | |
| "eval_steps_per_second": 14.91, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.5848788892267156e-05, | |
| "loss": 5.5338, | |
| "step": 400500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.581862581862582e-05, | |
| "loss": 5.5538, | |
| "step": 401000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 5.5573577880859375, | |
| "eval_runtime": 4.2195, | |
| "eval_samples_per_second": 237.233, | |
| "eval_steps_per_second": 14.931, | |
| "step": 401000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.5788462744984486e-05, | |
| "loss": 5.5498, | |
| "step": 401500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.5758359997490432e-05, | |
| "loss": 5.5545, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 5.518813133239746, | |
| "eval_runtime": 4.0734, | |
| "eval_samples_per_second": 245.741, | |
| "eval_steps_per_second": 15.466, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.5728196923849103e-05, | |
| "loss": 5.5528, | |
| "step": 402500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.5698033850207763e-05, | |
| "loss": 5.5465, | |
| "step": 403000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 5.5730109214782715, | |
| "eval_runtime": 4.2103, | |
| "eval_samples_per_second": 237.751, | |
| "eval_steps_per_second": 14.963, | |
| "step": 403000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.5667870776566426e-05, | |
| "loss": 5.554, | |
| "step": 403500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.5637707702925097e-05, | |
| "loss": 5.5516, | |
| "step": 404000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 5.568479061126709, | |
| "eval_runtime": 4.095, | |
| "eval_samples_per_second": 244.447, | |
| "eval_steps_per_second": 15.385, | |
| "step": 404000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.5607604955431043e-05, | |
| "loss": 5.5377, | |
| "step": 404500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.557744188178971e-05, | |
| "loss": 5.5422, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 5.573971748352051, | |
| "eval_runtime": 4.0905, | |
| "eval_samples_per_second": 244.713, | |
| "eval_steps_per_second": 15.401, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.5547278808148373e-05, | |
| "loss": 5.5486, | |
| "step": 405500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.551711573450704e-05, | |
| "loss": 5.5566, | |
| "step": 406000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 5.565399646759033, | |
| "eval_runtime": 4.2007, | |
| "eval_samples_per_second": 238.293, | |
| "eval_steps_per_second": 14.997, | |
| "step": 406000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.5486952660865704e-05, | |
| "loss": 5.5534, | |
| "step": 406500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.545678958722437e-05, | |
| "loss": 5.5585, | |
| "step": 407000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 5.614578723907471, | |
| "eval_runtime": 4.1661, | |
| "eval_samples_per_second": 240.272, | |
| "eval_steps_per_second": 15.122, | |
| "step": 407000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.5426686839730317e-05, | |
| "loss": 5.5461, | |
| "step": 407500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.5396523766088987e-05, | |
| "loss": 5.5577, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 5.5891923904418945, | |
| "eval_runtime": 4.1531, | |
| "eval_samples_per_second": 241.024, | |
| "eval_steps_per_second": 15.169, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.5366360692447648e-05, | |
| "loss": 5.5564, | |
| "step": 408500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.5336197618806318e-05, | |
| "loss": 5.5332, | |
| "step": 409000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 5.594736099243164, | |
| "eval_runtime": 4.1179, | |
| "eval_samples_per_second": 243.084, | |
| "eval_steps_per_second": 15.299, | |
| "step": 409000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.5306094871312264e-05, | |
| "loss": 5.562, | |
| "step": 409500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.527593179767093e-05, | |
| "loss": 5.5479, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 5.611057758331299, | |
| "eval_runtime": 3.9514, | |
| "eval_samples_per_second": 253.327, | |
| "eval_steps_per_second": 15.944, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5245768724029595e-05, | |
| "loss": 5.5425, | |
| "step": 410500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5215605650388258e-05, | |
| "loss": 5.5615, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 5.556435585021973, | |
| "eval_runtime": 3.947, | |
| "eval_samples_per_second": 253.608, | |
| "eval_steps_per_second": 15.961, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5185442576746925e-05, | |
| "loss": 5.5489, | |
| "step": 411500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.515533982925287e-05, | |
| "loss": 5.5524, | |
| "step": 412000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 5.55076265335083, | |
| "eval_runtime": 3.7148, | |
| "eval_samples_per_second": 269.464, | |
| "eval_steps_per_second": 16.959, | |
| "step": 412000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5125176755611542e-05, | |
| "loss": 5.5383, | |
| "step": 412500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5095013681970202e-05, | |
| "loss": 5.551, | |
| "step": 413000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 5.5648393630981445, | |
| "eval_runtime": 3.9, | |
| "eval_samples_per_second": 256.665, | |
| "eval_steps_per_second": 16.154, | |
| "step": 413000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.5064850608328872e-05, | |
| "loss": 5.5427, | |
| "step": 413500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.5034687534687536e-05, | |
| "loss": 5.5444, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 5.562320709228516, | |
| "eval_runtime": 4.0551, | |
| "eval_samples_per_second": 246.849, | |
| "eval_steps_per_second": 15.536, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.5004584787193485e-05, | |
| "loss": 5.549, | |
| "step": 414500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.497442171355215e-05, | |
| "loss": 5.5571, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 5.529527187347412, | |
| "eval_runtime": 3.9424, | |
| "eval_samples_per_second": 253.906, | |
| "eval_steps_per_second": 15.98, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.4944258639910813e-05, | |
| "loss": 5.537, | |
| "step": 415500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.491409556626948e-05, | |
| "loss": 5.5462, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 5.569790363311768, | |
| "eval_runtime": 4.0546, | |
| "eval_samples_per_second": 246.881, | |
| "eval_steps_per_second": 15.538, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.488399281877543e-05, | |
| "loss": 5.5532, | |
| "step": 416500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.4853829745134093e-05, | |
| "loss": 5.5461, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 5.56859827041626, | |
| "eval_runtime": 4.2053, | |
| "eval_samples_per_second": 238.032, | |
| "eval_steps_per_second": 14.981, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.482366667149276e-05, | |
| "loss": 5.5524, | |
| "step": 417500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.4793503597851427e-05, | |
| "loss": 5.5539, | |
| "step": 418000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 5.538581371307373, | |
| "eval_runtime": 4.1418, | |
| "eval_samples_per_second": 241.683, | |
| "eval_steps_per_second": 15.211, | |
| "step": 418000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.476334052421009e-05, | |
| "loss": 5.5466, | |
| "step": 418500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.473323777671604e-05, | |
| "loss": 5.5561, | |
| "step": 419000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 5.570122241973877, | |
| "eval_runtime": 4.1361, | |
| "eval_samples_per_second": 242.018, | |
| "eval_steps_per_second": 15.232, | |
| "step": 419000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.4703074703074707e-05, | |
| "loss": 5.5666, | |
| "step": 419500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.467291162943337e-05, | |
| "loss": 5.554, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 5.601891040802002, | |
| "eval_runtime": 4.2243, | |
| "eval_samples_per_second": 236.962, | |
| "eval_steps_per_second": 14.914, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.4642748555792037e-05, | |
| "loss": 5.5529, | |
| "step": 420500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.4612645808297983e-05, | |
| "loss": 5.543, | |
| "step": 421000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 5.567346096038818, | |
| "eval_runtime": 4.1937, | |
| "eval_samples_per_second": 238.694, | |
| "eval_steps_per_second": 15.023, | |
| "step": 421000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.4582482734656647e-05, | |
| "loss": 5.5413, | |
| "step": 421500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.4552319661015314e-05, | |
| "loss": 5.5391, | |
| "step": 422000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 5.597777366638184, | |
| "eval_runtime": 4.1882, | |
| "eval_samples_per_second": 239.006, | |
| "eval_steps_per_second": 15.042, | |
| "step": 422000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.4522156587373978e-05, | |
| "loss": 5.5391, | |
| "step": 422500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.4491993513732644e-05, | |
| "loss": 5.5506, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 5.593500137329102, | |
| "eval_runtime": 4.1978, | |
| "eval_samples_per_second": 238.459, | |
| "eval_steps_per_second": 15.008, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.446183044009131e-05, | |
| "loss": 5.5521, | |
| "step": 423500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.4431727692597258e-05, | |
| "loss": 5.5379, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 5.544180393218994, | |
| "eval_runtime": 4.1787, | |
| "eval_samples_per_second": 239.549, | |
| "eval_steps_per_second": 15.077, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.4401564618955925e-05, | |
| "loss": 5.5495, | |
| "step": 424500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.437140154531459e-05, | |
| "loss": 5.5417, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 5.583528995513916, | |
| "eval_runtime": 4.1305, | |
| "eval_samples_per_second": 242.344, | |
| "eval_steps_per_second": 15.252, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.4341238471673255e-05, | |
| "loss": 5.5366, | |
| "step": 425500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.4311135724179205e-05, | |
| "loss": 5.5373, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 5.552159786224365, | |
| "eval_runtime": 4.2057, | |
| "eval_samples_per_second": 238.008, | |
| "eval_steps_per_second": 14.98, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.4280972650537868e-05, | |
| "loss": 5.5466, | |
| "step": 426500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.4250809576896535e-05, | |
| "loss": 5.5248, | |
| "step": 427000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 5.536990642547607, | |
| "eval_runtime": 4.0967, | |
| "eval_samples_per_second": 244.344, | |
| "eval_steps_per_second": 15.378, | |
| "step": 427000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.4220646503255202e-05, | |
| "loss": 5.5544, | |
| "step": 427500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.4190483429613866e-05, | |
| "loss": 5.5438, | |
| "step": 428000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 5.581920146942139, | |
| "eval_runtime": 4.05, | |
| "eval_samples_per_second": 247.158, | |
| "eval_steps_per_second": 15.555, | |
| "step": 428000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.4160320355972533e-05, | |
| "loss": 5.5543, | |
| "step": 428500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.413021760847848e-05, | |
| "loss": 5.5448, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 5.557128429412842, | |
| "eval_runtime": 4.1843, | |
| "eval_samples_per_second": 239.226, | |
| "eval_steps_per_second": 15.056, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.4100054534837142e-05, | |
| "loss": 5.536, | |
| "step": 429500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.406989146119581e-05, | |
| "loss": 5.5539, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 5.58180570602417, | |
| "eval_runtime": 4.1974, | |
| "eval_samples_per_second": 238.479, | |
| "eval_steps_per_second": 15.009, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.4039728387554476e-05, | |
| "loss": 5.5363, | |
| "step": 430500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.400956531391314e-05, | |
| "loss": 5.5494, | |
| "step": 431000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 5.602090835571289, | |
| "eval_runtime": 4.0312, | |
| "eval_samples_per_second": 248.316, | |
| "eval_steps_per_second": 15.628, | |
| "step": 431000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.397946256641909e-05, | |
| "loss": 5.5326, | |
| "step": 431500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.3949299492777753e-05, | |
| "loss": 5.5442, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 5.6263041496276855, | |
| "eval_runtime": 3.9955, | |
| "eval_samples_per_second": 250.529, | |
| "eval_steps_per_second": 15.768, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.391913641913642e-05, | |
| "loss": 5.5484, | |
| "step": 432500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.3888973345495087e-05, | |
| "loss": 5.5355, | |
| "step": 433000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 5.561853885650635, | |
| "eval_runtime": 4.1484, | |
| "eval_samples_per_second": 241.296, | |
| "eval_steps_per_second": 15.186, | |
| "step": 433000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.3858870598001033e-05, | |
| "loss": 5.5404, | |
| "step": 433500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.38287075243597e-05, | |
| "loss": 5.541, | |
| "step": 434000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 5.530201435089111, | |
| "eval_runtime": 4.1149, | |
| "eval_samples_per_second": 243.262, | |
| "eval_steps_per_second": 15.31, | |
| "step": 434000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.3798544450718367e-05, | |
| "loss": 5.5463, | |
| "step": 434500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.376838137707703e-05, | |
| "loss": 5.5308, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 5.592388153076172, | |
| "eval_runtime": 4.1121, | |
| "eval_samples_per_second": 243.428, | |
| "eval_steps_per_second": 15.321, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.3738218303435698e-05, | |
| "loss": 5.5466, | |
| "step": 435500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.3708115555941644e-05, | |
| "loss": 5.5422, | |
| "step": 436000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 5.5666399002075195, | |
| "eval_runtime": 4.0817, | |
| "eval_samples_per_second": 245.244, | |
| "eval_steps_per_second": 15.435, | |
| "step": 436000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.3677952482300307e-05, | |
| "loss": 5.5384, | |
| "step": 436500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.3647789408658974e-05, | |
| "loss": 5.5429, | |
| "step": 437000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 5.560754299163818, | |
| "eval_runtime": 5.9793, | |
| "eval_samples_per_second": 167.411, | |
| "eval_steps_per_second": 10.536, | |
| "step": 437000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.361762633501764e-05, | |
| "loss": 5.5554, | |
| "step": 437500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3587463261376305e-05, | |
| "loss": 5.5484, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 5.554554462432861, | |
| "eval_runtime": 3.705, | |
| "eval_samples_per_second": 270.178, | |
| "eval_steps_per_second": 17.004, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3557300187734972e-05, | |
| "loss": 5.5452, | |
| "step": 438500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3527137114093635e-05, | |
| "loss": 5.5396, | |
| "step": 439000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 5.551665782928467, | |
| "eval_runtime": 3.5833, | |
| "eval_samples_per_second": 279.351, | |
| "eval_steps_per_second": 17.582, | |
| "step": 439000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3496974040452302e-05, | |
| "loss": 5.5407, | |
| "step": 439500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3466931619105535e-05, | |
| "loss": 5.5455, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 5.568324089050293, | |
| "eval_runtime": 3.9095, | |
| "eval_samples_per_second": 256.043, | |
| "eval_steps_per_second": 16.115, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3436768545464198e-05, | |
| "loss": 5.5508, | |
| "step": 440500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.3406605471822865e-05, | |
| "loss": 5.5582, | |
| "step": 441000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 5.559935569763184, | |
| "eval_runtime": 3.8918, | |
| "eval_samples_per_second": 257.21, | |
| "eval_steps_per_second": 16.188, | |
| "step": 441000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.3376442398181532e-05, | |
| "loss": 5.5465, | |
| "step": 441500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.3346279324540196e-05, | |
| "loss": 5.5556, | |
| "step": 442000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 5.554677963256836, | |
| "eval_runtime": 3.9336, | |
| "eval_samples_per_second": 254.477, | |
| "eval_steps_per_second": 16.016, | |
| "step": 442000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.3316116250898863e-05, | |
| "loss": 5.5417, | |
| "step": 442500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.328601350340481e-05, | |
| "loss": 5.5424, | |
| "step": 443000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 5.574638843536377, | |
| "eval_runtime": 4.029, | |
| "eval_samples_per_second": 248.45, | |
| "eval_steps_per_second": 15.637, | |
| "step": 443000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.3255850429763472e-05, | |
| "loss": 5.5643, | |
| "step": 443500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.322568735612214e-05, | |
| "loss": 5.5361, | |
| "step": 444000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 5.589256286621094, | |
| "eval_runtime": 4.176, | |
| "eval_samples_per_second": 239.704, | |
| "eval_steps_per_second": 15.086, | |
| "step": 444000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.3195524282480803e-05, | |
| "loss": 5.5349, | |
| "step": 444500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.316536120883947e-05, | |
| "loss": 5.5408, | |
| "step": 445000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 5.5889177322387695, | |
| "eval_runtime": 4.1178, | |
| "eval_samples_per_second": 243.092, | |
| "eval_steps_per_second": 15.299, | |
| "step": 445000 | |
| } | |
| ], | |
| "max_steps": 828828, | |
| "num_train_epochs": 3, | |
| "total_flos": 5.4536747264337715e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |