| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 87, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3e-05, | |
| "loss": 3.1406, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.04514027769841723, | |
| "eval_loss": 3.076171875, | |
| "eval_runtime": 2.8635, | |
| "eval_samples_per_second": 30.033, | |
| "eval_steps_per_second": 2.095, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3e-05, | |
| "loss": 3.074, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.04514027769841723, | |
| "eval_loss": 3.076171875, | |
| "eval_runtime": 2.8038, | |
| "eval_samples_per_second": 30.673, | |
| "eval_steps_per_second": 2.14, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 3e-05, | |
| "loss": 3.0557, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.04514027769841723, | |
| "eval_loss": 3.076171875, | |
| "eval_runtime": 1.812, | |
| "eval_samples_per_second": 47.46, | |
| "eval_steps_per_second": 3.311, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.9990221430845156e-05, | |
| "loss": 3.2166, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.045697388720644536, | |
| "eval_loss": 3.017578125, | |
| "eval_runtime": 1.7487, | |
| "eval_samples_per_second": 49.181, | |
| "eval_steps_per_second": 3.431, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.996089847276925e-05, | |
| "loss": 3.0989, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.04601165647677276, | |
| "eval_loss": 2.9921875, | |
| "eval_runtime": 2.7561, | |
| "eval_samples_per_second": 31.204, | |
| "eval_steps_per_second": 2.177, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.9912069357315394e-05, | |
| "loss": 3.0732, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.04635449402891263, | |
| "eval_loss": 2.974609375, | |
| "eval_runtime": 2.7568, | |
| "eval_samples_per_second": 31.196, | |
| "eval_steps_per_second": 2.176, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.9843797748334563e-05, | |
| "loss": 3.0867, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.04628306953888349, | |
| "eval_loss": 2.962890625, | |
| "eval_runtime": 1.7772, | |
| "eval_samples_per_second": 48.39, | |
| "eval_steps_per_second": 3.376, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.975617265898004e-05, | |
| "loss": 2.979, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.04668304668304668, | |
| "eval_loss": 2.951171875, | |
| "eval_runtime": 2.0751, | |
| "eval_samples_per_second": 41.444, | |
| "eval_steps_per_second": 2.891, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.96493083356513e-05, | |
| "loss": 3.1838, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.04668304668304668, | |
| "eval_loss": 2.94140625, | |
| "eval_runtime": 2.063, | |
| "eval_samples_per_second": 41.687, | |
| "eval_steps_per_second": 2.908, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.952334410903845e-05, | |
| "loss": 2.9399, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.04674018627507, | |
| "eval_loss": 2.93359375, | |
| "eval_runtime": 1.7666, | |
| "eval_samples_per_second": 48.681, | |
| "eval_steps_per_second": 3.396, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.937844421246162e-05, | |
| "loss": 2.926, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.047125878521227356, | |
| "eval_loss": 2.92578125, | |
| "eval_runtime": 2.0537, | |
| "eval_samples_per_second": 41.875, | |
| "eval_steps_per_second": 2.921, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9214797567742036e-05, | |
| "loss": 3.2144, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.047254442603279816, | |
| "eval_loss": 2.919921875, | |
| "eval_runtime": 1.7851, | |
| "eval_samples_per_second": 48.176, | |
| "eval_steps_per_second": 3.361, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.9032617538884018e-05, | |
| "loss": 2.978, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.04735443688932061, | |
| "eval_loss": 2.9140625, | |
| "eval_runtime": 2.7591, | |
| "eval_samples_per_second": 31.17, | |
| "eval_steps_per_second": 2.175, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.8832141653888998e-05, | |
| "loss": 3.0076, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.047640134849437174, | |
| "eval_loss": 2.908203125, | |
| "eval_runtime": 2.6767, | |
| "eval_samples_per_second": 32.129, | |
| "eval_steps_per_second": 2.242, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.861363129506436e-05, | |
| "loss": 2.9897, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.04772584423747214, | |
| "eval_loss": 2.90234375, | |
| "eval_runtime": 1.7524, | |
| "eval_samples_per_second": 49.075, | |
| "eval_steps_per_second": 3.424, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.8377371358230733e-05, | |
| "loss": 2.8831, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.04792583280955374, | |
| "eval_loss": 2.89453125, | |
| "eval_runtime": 2.0593, | |
| "eval_samples_per_second": 41.762, | |
| "eval_steps_per_second": 2.914, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.8123669881272247e-05, | |
| "loss": 2.9749, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.04786869321753043, | |
| "eval_loss": 2.88671875, | |
| "eval_runtime": 2.7597, | |
| "eval_samples_per_second": 31.163, | |
| "eval_steps_per_second": 2.174, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.7852857642513838e-05, | |
| "loss": 2.9431, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.04776869893148963, | |
| "eval_loss": 2.8828125, | |
| "eval_runtime": 1.7792, | |
| "eval_samples_per_second": 48.336, | |
| "eval_steps_per_second": 3.372, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.7565287729449473e-05, | |
| "loss": 3.0498, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_accuracy": 0.047882978115536254, | |
| "eval_loss": 2.876953125, | |
| "eval_runtime": 2.7592, | |
| "eval_samples_per_second": 31.168, | |
| "eval_steps_per_second": 2.175, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.7261335078383377e-05, | |
| "loss": 2.9409, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.047854408319524595, | |
| "eval_loss": 2.87109375, | |
| "eval_runtime": 1.7642, | |
| "eval_samples_per_second": 48.747, | |
| "eval_steps_per_second": 3.401, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.6941395985584656e-05, | |
| "loss": 2.96, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.04802582709559454, | |
| "eval_loss": 2.8671875, | |
| "eval_runtime": 1.7801, | |
| "eval_samples_per_second": 48.313, | |
| "eval_steps_per_second": 3.371, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.6605887590592547e-05, | |
| "loss": 3.0767, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.04784012342151877, | |
| "eval_loss": 2.86328125, | |
| "eval_runtime": 2.3678, | |
| "eval_samples_per_second": 36.32, | |
| "eval_steps_per_second": 2.534, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.6255247332346036e-05, | |
| "loss": 2.772, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.04792583280955374, | |
| "eval_loss": 2.859375, | |
| "eval_runtime": 2.7833, | |
| "eval_samples_per_second": 30.899, | |
| "eval_steps_per_second": 2.156, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2.5889932378846963e-05, | |
| "loss": 3.0574, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.04801154219758871, | |
| "eval_loss": 2.853515625, | |
| "eval_runtime": 2.7758, | |
| "eval_samples_per_second": 30.982, | |
| "eval_steps_per_second": 2.162, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.5510419031100137e-05, | |
| "loss": 2.8137, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.048040111993600365, | |
| "eval_loss": 2.849609375, | |
| "eval_runtime": 2.7701, | |
| "eval_samples_per_second": 31.046, | |
| "eval_steps_per_second": 2.166, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.5117202102107707e-05, | |
| "loss": 2.8872, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.048282955259699445, | |
| "eval_loss": 2.84375, | |
| "eval_runtime": 1.7514, | |
| "eval_samples_per_second": 49.103, | |
| "eval_steps_per_second": 3.426, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.4710794271727415e-05, | |
| "loss": 3.0085, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.0484115193417519, | |
| "eval_loss": 2.83984375, | |
| "eval_runtime": 1.7625, | |
| "eval_samples_per_second": 48.794, | |
| "eval_steps_per_second": 3.404, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.4291725418235848e-05, | |
| "loss": 2.9165, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.0485115136277927, | |
| "eval_loss": 2.8359375, | |
| "eval_runtime": 2.0562, | |
| "eval_samples_per_second": 41.824, | |
| "eval_steps_per_second": 2.918, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.3860541927468265e-05, | |
| "loss": 2.8525, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.04861150791383349, | |
| "eval_loss": 2.833984375, | |
| "eval_runtime": 2.0728, | |
| "eval_samples_per_second": 41.49, | |
| "eval_steps_per_second": 2.895, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.341780598043574e-05, | |
| "loss": 2.7759, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_accuracy": 0.04845437403576938, | |
| "eval_loss": 2.830078125, | |
| "eval_runtime": 1.7727, | |
| "eval_samples_per_second": 48.512, | |
| "eval_steps_per_second": 3.385, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.2964094820348302e-05, | |
| "loss": 2.7312, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_accuracy": 0.048497228729786866, | |
| "eval_loss": 2.828125, | |
| "eval_runtime": 1.7542, | |
| "eval_samples_per_second": 49.026, | |
| "eval_steps_per_second": 3.42, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.25e-05, | |
| "loss": 2.6641, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_accuracy": 0.04866864750585681, | |
| "eval_loss": 2.826171875, | |
| "eval_runtime": 2.6551, | |
| "eval_samples_per_second": 32.39, | |
| "eval_steps_per_second": 2.26, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.2026126610496852e-05, | |
| "loss": 2.7896, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_accuracy": 0.04855436832181018, | |
| "eval_loss": 2.82421875, | |
| "eval_runtime": 1.7664, | |
| "eval_samples_per_second": 48.686, | |
| "eval_steps_per_second": 3.397, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.154309249233351e-05, | |
| "loss": 2.7878, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_accuracy": 0.04866864750585681, | |
| "eval_loss": 2.822265625, | |
| "eval_runtime": 1.7584, | |
| "eval_samples_per_second": 48.909, | |
| "eval_steps_per_second": 3.412, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.105152742984713e-05, | |
| "loss": 2.4028, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_accuracy": 0.04869721730186846, | |
| "eval_loss": 2.8203125, | |
| "eval_runtime": 2.7671, | |
| "eval_samples_per_second": 31.08, | |
| "eval_steps_per_second": 2.168, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.055207233009872e-05, | |
| "loss": 2.5618, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_accuracy": 0.04878292668990344, | |
| "eval_loss": 2.818359375, | |
| "eval_runtime": 1.7727, | |
| "eval_samples_per_second": 48.514, | |
| "eval_steps_per_second": 3.385, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.0045378387252624e-05, | |
| "loss": 2.6697, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_accuracy": 0.04875435689389178, | |
| "eval_loss": 2.81640625, | |
| "eval_runtime": 2.7791, | |
| "eval_samples_per_second": 30.945, | |
| "eval_steps_per_second": 2.159, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.953210623354359e-05, | |
| "loss": 2.6333, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.048711502199874294, | |
| "eval_loss": 2.814453125, | |
| "eval_runtime": 2.7731, | |
| "eval_samples_per_second": 31.012, | |
| "eval_steps_per_second": 2.164, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.9012925077938318e-05, | |
| "loss": 2.4897, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_accuracy": 0.04858293811782184, | |
| "eval_loss": 2.8125, | |
| "eval_runtime": 2.7903, | |
| "eval_samples_per_second": 30.821, | |
| "eval_steps_per_second": 2.15, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.848851183361466e-05, | |
| "loss": 2.4908, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_accuracy": 0.04865436260785098, | |
| "eval_loss": 2.810546875, | |
| "eval_runtime": 2.7759, | |
| "eval_samples_per_second": 30.981, | |
| "eval_steps_per_second": 2.161, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.7959550235396002e-05, | |
| "loss": 2.6926, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_accuracy": 0.048768641791897605, | |
| "eval_loss": 2.80859375, | |
| "eval_runtime": 2.6681, | |
| "eval_samples_per_second": 32.233, | |
| "eval_steps_per_second": 2.249, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.7426729948291474e-05, | |
| "loss": 2.6602, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_accuracy": 0.048868636077938406, | |
| "eval_loss": 2.806640625, | |
| "eval_runtime": 1.7824, | |
| "eval_samples_per_second": 48.25, | |
| "eval_steps_per_second": 3.366, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.689074566830434e-05, | |
| "loss": 2.8054, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_accuracy": 0.04885435117993257, | |
| "eval_loss": 2.8046875, | |
| "eval_runtime": 2.6637, | |
| "eval_samples_per_second": 32.286, | |
| "eval_steps_per_second": 2.253, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.635229621668098e-05, | |
| "loss": 2.5532, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_accuracy": 0.048954345465973374, | |
| "eval_loss": 2.8046875, | |
| "eval_runtime": 2.7813, | |
| "eval_samples_per_second": 30.921, | |
| "eval_steps_per_second": 2.157, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.5812083628781265e-05, | |
| "loss": 2.4756, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_accuracy": 0.04906862465002, | |
| "eval_loss": 2.802734375, | |
| "eval_runtime": 2.3836, | |
| "eval_samples_per_second": 36.08, | |
| "eval_steps_per_second": 2.517, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.5270812238758407e-05, | |
| "loss": 2.6123, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_accuracy": 0.04912576424204331, | |
| "eval_loss": 2.80078125, | |
| "eval_runtime": 1.7527, | |
| "eval_samples_per_second": 49.068, | |
| "eval_steps_per_second": 3.423, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.4729187761241592e-05, | |
| "loss": 2.5117, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_accuracy": 0.04902576995600252, | |
| "eval_loss": 2.798828125, | |
| "eval_runtime": 1.7703, | |
| "eval_samples_per_second": 48.579, | |
| "eval_steps_per_second": 3.389, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1.4187916371218739e-05, | |
| "loss": 2.5552, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_accuracy": 0.04904005485400834, | |
| "eval_loss": 2.796875, | |
| "eval_runtime": 2.7807, | |
| "eval_samples_per_second": 30.928, | |
| "eval_steps_per_second": 2.158, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.3647703783319022e-05, | |
| "loss": 2.5122, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_accuracy": 0.04902576995600252, | |
| "eval_loss": 2.794921875, | |
| "eval_runtime": 1.7675, | |
| "eval_samples_per_second": 48.658, | |
| "eval_steps_per_second": 3.395, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.310925433169566e-05, | |
| "loss": 2.5593, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_accuracy": 0.04909719444603165, | |
| "eval_loss": 2.79296875, | |
| "eval_runtime": 1.7524, | |
| "eval_samples_per_second": 49.077, | |
| "eval_steps_per_second": 3.424, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.2573270051708529e-05, | |
| "loss": 2.5759, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_accuracy": 0.04909719444603165, | |
| "eval_loss": 2.791015625, | |
| "eval_runtime": 2.7672, | |
| "eval_samples_per_second": 31.079, | |
| "eval_steps_per_second": 2.168, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.2040449764604002e-05, | |
| "loss": 2.5535, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_accuracy": 0.04929718301811325, | |
| "eval_loss": 2.7890625, | |
| "eval_runtime": 2.6669, | |
| "eval_samples_per_second": 32.247, | |
| "eval_steps_per_second": 2.25, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.1511488166385349e-05, | |
| "loss": 2.6531, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_accuracy": 0.04939717730415405, | |
| "eval_loss": 2.787109375, | |
| "eval_runtime": 2.0564, | |
| "eval_samples_per_second": 41.821, | |
| "eval_steps_per_second": 2.918, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.098707492206169e-05, | |
| "loss": 2.5701, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_accuracy": 0.0495257413862065, | |
| "eval_loss": 2.78515625, | |
| "eval_runtime": 1.7609, | |
| "eval_samples_per_second": 48.84, | |
| "eval_steps_per_second": 3.407, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.0467893766456408e-05, | |
| "loss": 2.6621, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_accuracy": 0.049654305468258955, | |
| "eval_loss": 2.783203125, | |
| "eval_runtime": 2.0679, | |
| "eval_samples_per_second": 41.587, | |
| "eval_steps_per_second": 2.901, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 9.954621612747371e-06, | |
| "loss": 2.532, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_accuracy": 0.04958288097822981, | |
| "eval_loss": 2.78125, | |
| "eval_runtime": 1.7708, | |
| "eval_samples_per_second": 48.565, | |
| "eval_steps_per_second": 3.388, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 9.447927669901284e-06, | |
| "loss": 2.5928, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.049654305468258955, | |
| "eval_loss": 2.779296875, | |
| "eval_runtime": 1.752, | |
| "eval_samples_per_second": 49.086, | |
| "eval_steps_per_second": 3.425, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.948472570152874e-06, | |
| "loss": 2.5486, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.04969716016227644, | |
| "eval_loss": 2.775390625, | |
| "eval_runtime": 1.768, | |
| "eval_samples_per_second": 48.642, | |
| "eval_steps_per_second": 3.394, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 8.456907507666488e-06, | |
| "loss": 2.5009, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_accuracy": 0.0497257299582881, | |
| "eval_loss": 2.7734375, | |
| "eval_runtime": 2.6592, | |
| "eval_samples_per_second": 32.341, | |
| "eval_steps_per_second": 2.256, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 7.97387338950315e-06, | |
| "loss": 2.4346, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_accuracy": 0.049754299754299756, | |
| "eval_loss": 2.7734375, | |
| "eval_runtime": 1.77, | |
| "eval_samples_per_second": 48.588, | |
| "eval_steps_per_second": 3.39, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 7.500000000000004e-06, | |
| "loss": 2.3259, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_accuracy": 0.049740014856293924, | |
| "eval_loss": 2.771484375, | |
| "eval_runtime": 2.7629, | |
| "eval_samples_per_second": 31.127, | |
| "eval_steps_per_second": 2.172, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 7.035905179651701e-06, | |
| "loss": 2.3569, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_accuracy": 0.04978286955031141, | |
| "eval_loss": 2.76953125, | |
| "eval_runtime": 2.7575, | |
| "eval_samples_per_second": 31.187, | |
| "eval_steps_per_second": 2.176, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 6.582194019564266e-06, | |
| "loss": 2.5898, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_accuracy": 0.049811439346323066, | |
| "eval_loss": 2.76953125, | |
| "eval_runtime": 1.7477, | |
| "eval_samples_per_second": 49.209, | |
| "eval_steps_per_second": 3.433, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 6.1394580725317366e-06, | |
| "loss": 2.3657, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_accuracy": 0.04976858465230558, | |
| "eval_loss": 2.767578125, | |
| "eval_runtime": 1.7819, | |
| "eval_samples_per_second": 48.263, | |
| "eval_steps_per_second": 3.367, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.708274581764155e-06, | |
| "loss": 2.4875, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.049754299754299756, | |
| "eval_loss": 2.767578125, | |
| "eval_runtime": 2.7652, | |
| "eval_samples_per_second": 31.1, | |
| "eval_steps_per_second": 2.17, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 5.289205728272587e-06, | |
| "loss": 2.4392, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_accuracy": 0.0497257299582881, | |
| "eval_loss": 2.767578125, | |
| "eval_runtime": 2.0654, | |
| "eval_samples_per_second": 41.638, | |
| "eval_steps_per_second": 2.905, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.882797897892293e-06, | |
| "loss": 2.3595, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_accuracy": 0.0497257299582881, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.674, | |
| "eval_samples_per_second": 32.162, | |
| "eval_steps_per_second": 2.244, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.4895809688998655e-06, | |
| "loss": 2.4757, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_accuracy": 0.049811439346323066, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.7575, | |
| "eval_samples_per_second": 31.187, | |
| "eval_steps_per_second": 2.176, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.110067621153041e-06, | |
| "loss": 2.4617, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_accuracy": 0.049811439346323066, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.7642, | |
| "eval_samples_per_second": 31.112, | |
| "eval_steps_per_second": 2.171, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.744752667653965e-06, | |
| "loss": 2.3376, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_accuracy": 0.049925718530369693, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 1.7636, | |
| "eval_samples_per_second": 48.763, | |
| "eval_steps_per_second": 3.402, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 3.394112409407455e-06, | |
| "loss": 2.3129, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_accuracy": 0.04982572424432889, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.0925, | |
| "eval_samples_per_second": 41.099, | |
| "eval_steps_per_second": 2.867, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.0586040144153436e-06, | |
| "loss": 2.5703, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_accuracy": 0.04979715444831724, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 1.7604, | |
| "eval_samples_per_second": 48.851, | |
| "eval_steps_per_second": 3.408, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 2.7386649216166233e-06, | |
| "loss": 2.3491, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_accuracy": 0.049811439346323066, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.7645, | |
| "eval_samples_per_second": 31.109, | |
| "eval_steps_per_second": 2.17, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2.4347122705505303e-06, | |
| "loss": 2.3484, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_accuracy": 0.049754299754299756, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.7683, | |
| "eval_samples_per_second": 31.066, | |
| "eval_steps_per_second": 2.167, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.1471423574861643e-06, | |
| "loss": 2.3782, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_accuracy": 0.049740014856293924, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 1.7554, | |
| "eval_samples_per_second": 48.991, | |
| "eval_steps_per_second": 3.418, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 1.8763301187277554e-06, | |
| "loss": 2.4033, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_accuracy": 0.04979715444831724, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.7591, | |
| "eval_samples_per_second": 31.17, | |
| "eval_steps_per_second": 2.175, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 1.6226286417692666e-06, | |
| "loss": 2.3821, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_accuracy": 0.04976858465230558, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 1.7671, | |
| "eval_samples_per_second": 48.668, | |
| "eval_steps_per_second": 3.395, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 1.3863687049356465e-06, | |
| "loss": 2.39, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_accuracy": 0.04979715444831724, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 1.7638, | |
| "eval_samples_per_second": 48.758, | |
| "eval_steps_per_second": 3.402, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 1.1678583461110026e-06, | |
| "loss": 2.3984, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_accuracy": 0.049740014856293924, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.774, | |
| "eval_samples_per_second": 31.002, | |
| "eval_steps_per_second": 2.163, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 9.67382461115986e-07, | |
| "loss": 2.3936, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_accuracy": 0.049754299754299756, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.0608, | |
| "eval_samples_per_second": 41.732, | |
| "eval_steps_per_second": 2.912, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 7.852024322579649e-07, | |
| "loss": 2.4414, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_accuracy": 0.0497257299582881, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.3621, | |
| "eval_samples_per_second": 36.408, | |
| "eval_steps_per_second": 2.54, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 6.215557875383804e-07, | |
| "loss": 2.4727, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_accuracy": 0.04969716016227644, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.7992, | |
| "eval_samples_per_second": 30.723, | |
| "eval_steps_per_second": 2.143, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 4.766558909615504e-07, | |
| "loss": 2.3192, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.04971144506028227, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 2.0548, | |
| "eval_samples_per_second": 41.853, | |
| "eval_steps_per_second": 2.92, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.5069166434870014e-07, | |
| "loss": 2.4365, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_accuracy": 0.04966859036626479, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 1.7544, | |
| "eval_samples_per_second": 49.02, | |
| "eval_steps_per_second": 3.42, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 2.438273410199598e-07, | |
| "loss": 2.5042, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_accuracy": 0.04969716016227644, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 1.7715, | |
| "eval_samples_per_second": 48.545, | |
| "eval_steps_per_second": 3.387, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.5620225166544155e-07, | |
| "loss": 2.4746, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_accuracy": 0.04966859036626479, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 1.772, | |
| "eval_samples_per_second": 48.534, | |
| "eval_steps_per_second": 3.386, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.793064268460605e-08, | |
| "loss": 2.5383, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.049654305468258955, | |
| "eval_loss": 2.765625, | |
| "eval_runtime": 1.7578, | |
| "eval_samples_per_second": 48.924, | |
| "eval_steps_per_second": 3.413, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 87, | |
| "total_flos": 902636273664.0, | |
| "train_loss": 2.6778283831716956, | |
| "train_runtime": 390.8223, | |
| "train_samples_per_second": 3.523, | |
| "train_steps_per_second": 0.223 | |
| } | |
| ], | |
| "max_steps": 87, | |
| "num_train_epochs": 3, | |
| "total_flos": 902636273664.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |