| { | |
| "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": 2.6543, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.05133992343294669, | |
| "eval_loss": 2.611328125, | |
| "eval_runtime": 3.8997, | |
| "eval_samples_per_second": 22.053, | |
| "eval_steps_per_second": 1.539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6077, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.05133992343294669, | |
| "eval_loss": 2.611328125, | |
| "eval_runtime": 3.9386, | |
| "eval_samples_per_second": 21.835, | |
| "eval_steps_per_second": 1.523, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.9990221430845156e-05, | |
| "loss": 2.5964, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.05192560425118565, | |
| "eval_loss": 2.560546875, | |
| "eval_runtime": 3.8896, | |
| "eval_samples_per_second": 22.11, | |
| "eval_steps_per_second": 1.543, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.996089847276925e-05, | |
| "loss": 2.7302, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.052582709559453746, | |
| "eval_loss": 2.5234375, | |
| "eval_runtime": 4.1976, | |
| "eval_samples_per_second": 20.488, | |
| "eval_steps_per_second": 1.429, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.9912069357315394e-05, | |
| "loss": 2.7004, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.05293983200959945, | |
| "eval_loss": 2.5078125, | |
| "eval_runtime": 4.2482, | |
| "eval_samples_per_second": 20.244, | |
| "eval_steps_per_second": 1.412, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.9843797748334563e-05, | |
| "loss": 2.5681, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.05318267527569853, | |
| "eval_loss": 2.494140625, | |
| "eval_runtime": 4.2937, | |
| "eval_samples_per_second": 20.029, | |
| "eval_steps_per_second": 1.397, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.975617265898004e-05, | |
| "loss": 2.6404, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.05342551854179761, | |
| "eval_loss": 2.48828125, | |
| "eval_runtime": 4.3127, | |
| "eval_samples_per_second": 19.941, | |
| "eval_steps_per_second": 1.391, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.96493083356513e-05, | |
| "loss": 2.5325, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.053554082623850065, | |
| "eval_loss": 2.48046875, | |
| "eval_runtime": 4.2885, | |
| "eval_samples_per_second": 20.053, | |
| "eval_steps_per_second": 1.399, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.952334410903845e-05, | |
| "loss": 2.7205, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.053554082623850065, | |
| "eval_loss": 2.474609375, | |
| "eval_runtime": 3.8974, | |
| "eval_samples_per_second": 22.066, | |
| "eval_steps_per_second": 1.539, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.937844421246162e-05, | |
| "loss": 2.5149, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.05329695445974516, | |
| "eval_loss": 2.46484375, | |
| "eval_runtime": 4.2968, | |
| "eval_samples_per_second": 20.015, | |
| "eval_steps_per_second": 1.396, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.9214797567742036e-05, | |
| "loss": 2.5017, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.05345408833780927, | |
| "eval_loss": 2.451171875, | |
| "eval_runtime": 4.2885, | |
| "eval_samples_per_second": 20.054, | |
| "eval_steps_per_second": 1.399, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9032617538884018e-05, | |
| "loss": 2.7026, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.053896920175989946, | |
| "eval_loss": 2.439453125, | |
| "eval_runtime": 4.2979, | |
| "eval_samples_per_second": 20.01, | |
| "eval_steps_per_second": 1.396, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.8832141653888998e-05, | |
| "loss": 2.5259, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.05425404262613565, | |
| "eval_loss": 2.431640625, | |
| "eval_runtime": 4.2986, | |
| "eval_samples_per_second": 20.007, | |
| "eval_steps_per_second": 1.396, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.861363129506436e-05, | |
| "loss": 2.563, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.05455402548425804, | |
| "eval_loss": 2.421875, | |
| "eval_runtime": 4.2879, | |
| "eval_samples_per_second": 20.056, | |
| "eval_steps_per_second": 1.399, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.8377371358230733e-05, | |
| "loss": 2.5679, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.055011142220444544, | |
| "eval_loss": 2.4140625, | |
| "eval_runtime": 3.9042, | |
| "eval_samples_per_second": 22.027, | |
| "eval_steps_per_second": 1.537, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.8123669881272247e-05, | |
| "loss": 2.3701, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.05512542140449117, | |
| "eval_loss": 2.408203125, | |
| "eval_runtime": 3.9081, | |
| "eval_samples_per_second": 22.006, | |
| "eval_steps_per_second": 1.535, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.8123669881272247e-05, | |
| "loss": 2.4739, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.05512542140449117, | |
| "eval_loss": 2.408203125, | |
| "eval_runtime": 4.3256, | |
| "eval_samples_per_second": 19.882, | |
| "eval_steps_per_second": 1.387, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.7852857642513838e-05, | |
| "loss": 2.481, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.054839723444374606, | |
| "eval_loss": 2.40234375, | |
| "eval_runtime": 3.8988, | |
| "eval_samples_per_second": 22.058, | |
| "eval_steps_per_second": 1.539, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.7565287729449473e-05, | |
| "loss": 2.5795, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_accuracy": 0.054896863036397923, | |
| "eval_loss": 2.39453125, | |
| "eval_runtime": 4.2984, | |
| "eval_samples_per_second": 20.007, | |
| "eval_steps_per_second": 1.396, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.7261335078383377e-05, | |
| "loss": 2.4902, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.05491114793440375, | |
| "eval_loss": 2.38671875, | |
| "eval_runtime": 4.3044, | |
| "eval_samples_per_second": 19.98, | |
| "eval_steps_per_second": 1.394, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.6941395985584656e-05, | |
| "loss": 2.4509, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.055139706302497, | |
| "eval_loss": 2.380859375, | |
| "eval_runtime": 4.2949, | |
| "eval_samples_per_second": 20.024, | |
| "eval_steps_per_second": 1.397, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.6605887590592547e-05, | |
| "loss": 2.6052, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.055325409976572766, | |
| "eval_loss": 2.373046875, | |
| "eval_runtime": 4.2966, | |
| "eval_samples_per_second": 20.016, | |
| "eval_steps_per_second": 1.396, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.6255247332346036e-05, | |
| "loss": 2.3323, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.05552539854865436, | |
| "eval_loss": 2.36328125, | |
| "eval_runtime": 3.5753, | |
| "eval_samples_per_second": 24.054, | |
| "eval_steps_per_second": 1.678, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2.5889932378846963e-05, | |
| "loss": 2.5994, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.05563967773270099, | |
| "eval_loss": 2.35546875, | |
| "eval_runtime": 4.2029, | |
| "eval_samples_per_second": 20.462, | |
| "eval_steps_per_second": 1.428, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.5510419031100137e-05, | |
| "loss": 2.3347, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.05558253814067768, | |
| "eval_loss": 2.34765625, | |
| "eval_runtime": 4.4126, | |
| "eval_samples_per_second": 19.49, | |
| "eval_steps_per_second": 1.36, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.5117202102107707e-05, | |
| "loss": 2.421, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.05586823610079424, | |
| "eval_loss": 2.33984375, | |
| "eval_runtime": 4.3, | |
| "eval_samples_per_second": 20.0, | |
| "eval_steps_per_second": 1.395, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.4710794271727415e-05, | |
| "loss": 2.5337, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.05603965487686418, | |
| "eval_loss": 2.3359375, | |
| "eval_runtime": 3.2828, | |
| "eval_samples_per_second": 26.197, | |
| "eval_steps_per_second": 1.828, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.4291725418235848e-05, | |
| "loss": 2.4102, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.0562539283469516, | |
| "eval_loss": 2.33203125, | |
| "eval_runtime": 4.3038, | |
| "eval_samples_per_second": 19.982, | |
| "eval_steps_per_second": 1.394, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.3860541927468265e-05, | |
| "loss": 2.4309, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.05643963202102737, | |
| "eval_loss": 2.326171875, | |
| "eval_runtime": 4.2875, | |
| "eval_samples_per_second": 20.058, | |
| "eval_steps_per_second": 1.399, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.341780598043574e-05, | |
| "loss": 1.9305, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_accuracy": 0.0563539226329924, | |
| "eval_loss": 2.322265625, | |
| "eval_runtime": 4.2962, | |
| "eval_samples_per_second": 20.017, | |
| "eval_steps_per_second": 1.397, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.2964094820348302e-05, | |
| "loss": 1.8601, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_accuracy": 0.056696760185132276, | |
| "eval_loss": 2.3203125, | |
| "eval_runtime": 4.32, | |
| "eval_samples_per_second": 19.907, | |
| "eval_steps_per_second": 1.389, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.25e-05, | |
| "loss": 1.8682, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_accuracy": 0.056425347123021545, | |
| "eval_loss": 2.328125, | |
| "eval_runtime": 4.3035, | |
| "eval_samples_per_second": 19.984, | |
| "eval_steps_per_second": 1.394, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.2026126610496852e-05, | |
| "loss": 1.8657, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_accuracy": 0.056382492429004054, | |
| "eval_loss": 2.353515625, | |
| "eval_runtime": 4.2925, | |
| "eval_samples_per_second": 20.035, | |
| "eval_steps_per_second": 1.398, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.154309249233351e-05, | |
| "loss": 2.063, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_accuracy": 0.056696760185132276, | |
| "eval_loss": 2.33984375, | |
| "eval_runtime": 3.2879, | |
| "eval_samples_per_second": 26.157, | |
| "eval_steps_per_second": 1.825, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.105152742984713e-05, | |
| "loss": 1.6443, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_accuracy": 0.05683960916519056, | |
| "eval_loss": 2.32421875, | |
| "eval_runtime": 4.3025, | |
| "eval_samples_per_second": 19.988, | |
| "eval_steps_per_second": 1.395, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.055207233009872e-05, | |
| "loss": 1.7592, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_accuracy": 0.056882463859208046, | |
| "eval_loss": 2.31640625, | |
| "eval_runtime": 4.2776, | |
| "eval_samples_per_second": 20.105, | |
| "eval_steps_per_second": 1.403, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.0045378387252624e-05, | |
| "loss": 1.8981, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_accuracy": 0.05686817896120222, | |
| "eval_loss": 2.310546875, | |
| "eval_runtime": 3.5855, | |
| "eval_samples_per_second": 23.986, | |
| "eval_steps_per_second": 1.673, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.953210623354359e-05, | |
| "loss": 1.9379, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.05728244100337124, | |
| "eval_loss": 2.3046875, | |
| "eval_runtime": 4.2888, | |
| "eval_samples_per_second": 20.052, | |
| "eval_steps_per_second": 1.399, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.9012925077938318e-05, | |
| "loss": 1.6008, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_accuracy": 0.057368150391406206, | |
| "eval_loss": 2.302734375, | |
| "eval_runtime": 4.1858, | |
| "eval_samples_per_second": 20.546, | |
| "eval_steps_per_second": 1.433, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.848851183361466e-05, | |
| "loss": 1.595, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_accuracy": 0.057453859779441174, | |
| "eval_loss": 2.302734375, | |
| "eval_runtime": 4.3045, | |
| "eval_samples_per_second": 19.979, | |
| "eval_steps_per_second": 1.394, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.7959550235396002e-05, | |
| "loss": 1.7096, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_accuracy": 0.05752528426947032, | |
| "eval_loss": 2.302734375, | |
| "eval_runtime": 4.3092, | |
| "eval_samples_per_second": 19.957, | |
| "eval_steps_per_second": 1.392, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.7426729948291474e-05, | |
| "loss": 1.7245, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_accuracy": 0.0575681389634878, | |
| "eval_loss": 2.302734375, | |
| "eval_runtime": 3.5821, | |
| "eval_samples_per_second": 24.008, | |
| "eval_steps_per_second": 1.675, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.689074566830434e-05, | |
| "loss": 1.795, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_accuracy": 0.05768241814753443, | |
| "eval_loss": 2.30078125, | |
| "eval_runtime": 4.2953, | |
| "eval_samples_per_second": 20.022, | |
| "eval_steps_per_second": 1.397, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.635229621668098e-05, | |
| "loss": 1.7241, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_accuracy": 0.057610993657505286, | |
| "eval_loss": 2.30078125, | |
| "eval_runtime": 4.3019, | |
| "eval_samples_per_second": 19.991, | |
| "eval_steps_per_second": 1.395, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.5812083628781265e-05, | |
| "loss": 1.6356, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_accuracy": 0.057639563453516944, | |
| "eval_loss": 2.298828125, | |
| "eval_runtime": 4.2961, | |
| "eval_samples_per_second": 20.018, | |
| "eval_steps_per_second": 1.397, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.5270812238758407e-05, | |
| "loss": 1.77, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_accuracy": 0.057553854065481976, | |
| "eval_loss": 2.296875, | |
| "eval_runtime": 4.3142, | |
| "eval_samples_per_second": 19.934, | |
| "eval_steps_per_second": 1.391, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.4729187761241592e-05, | |
| "loss": 1.6675, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_accuracy": 0.057668133249528596, | |
| "eval_loss": 2.29296875, | |
| "eval_runtime": 4.2943, | |
| "eval_samples_per_second": 20.026, | |
| "eval_steps_per_second": 1.397, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1.4187916371218739e-05, | |
| "loss": 1.6929, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_accuracy": 0.05771098794354608, | |
| "eval_loss": 2.291015625, | |
| "eval_runtime": 3.8871, | |
| "eval_samples_per_second": 22.124, | |
| "eval_steps_per_second": 1.544, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.3647703783319022e-05, | |
| "loss": 1.6635, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_accuracy": 0.05762527855551111, | |
| "eval_loss": 2.291015625, | |
| "eval_runtime": 4.3038, | |
| "eval_samples_per_second": 19.982, | |
| "eval_steps_per_second": 1.394, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.310925433169566e-05, | |
| "loss": 1.6093, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_accuracy": 0.05781098222958688, | |
| "eval_loss": 2.291015625, | |
| "eval_runtime": 3.8811, | |
| "eval_samples_per_second": 22.159, | |
| "eval_steps_per_second": 1.546, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.2573270051708529e-05, | |
| "loss": 1.7362, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_accuracy": 0.05796811610765099, | |
| "eval_loss": 2.2890625, | |
| "eval_runtime": 4.3003, | |
| "eval_samples_per_second": 19.998, | |
| "eval_steps_per_second": 1.395, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.2040449764604002e-05, | |
| "loss": 1.7015, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_accuracy": 0.05805382549568596, | |
| "eval_loss": 2.28515625, | |
| "eval_runtime": 4.2877, | |
| "eval_samples_per_second": 20.057, | |
| "eval_steps_per_second": 1.399, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.1511488166385349e-05, | |
| "loss": 1.9515, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_accuracy": 0.05816810467973259, | |
| "eval_loss": 2.28125, | |
| "eval_runtime": 4.3062, | |
| "eval_samples_per_second": 19.971, | |
| "eval_steps_per_second": 1.393, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.098707492206169e-05, | |
| "loss": 1.6494, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_accuracy": 0.05801097080166848, | |
| "eval_loss": 2.27734375, | |
| "eval_runtime": 3.8918, | |
| "eval_samples_per_second": 22.098, | |
| "eval_steps_per_second": 1.542, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.0467893766456408e-05, | |
| "loss": 1.7522, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_accuracy": 0.05798240100565682, | |
| "eval_loss": 2.2734375, | |
| "eval_runtime": 4.1919, | |
| "eval_samples_per_second": 20.516, | |
| "eval_steps_per_second": 1.431, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 9.954621612747371e-06, | |
| "loss": 1.7369, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_accuracy": 0.05806811039369179, | |
| "eval_loss": 2.267578125, | |
| "eval_runtime": 4.3092, | |
| "eval_samples_per_second": 19.957, | |
| "eval_steps_per_second": 1.392, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 9.447927669901284e-06, | |
| "loss": 1.6528, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.058125249985715104, | |
| "eval_loss": 2.263671875, | |
| "eval_runtime": 3.8882, | |
| "eval_samples_per_second": 22.118, | |
| "eval_steps_per_second": 1.543, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.948472570152874e-06, | |
| "loss": 1.51, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.05826809896577338, | |
| "eval_loss": 2.26171875, | |
| "eval_runtime": 4.2958, | |
| "eval_samples_per_second": 20.019, | |
| "eval_steps_per_second": 1.397, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 8.456907507666488e-06, | |
| "loss": 1.4579, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_accuracy": 0.05845380263984915, | |
| "eval_loss": 2.263671875, | |
| "eval_runtime": 4.2959, | |
| "eval_samples_per_second": 20.019, | |
| "eval_steps_per_second": 1.397, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 7.97387338950315e-06, | |
| "loss": 1.2645, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_accuracy": 0.05851094223187246, | |
| "eval_loss": 2.26953125, | |
| "eval_runtime": 4.2999, | |
| "eval_samples_per_second": 20.0, | |
| "eval_steps_per_second": 1.395, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 7.500000000000004e-06, | |
| "loss": 1.2424, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_accuracy": 0.05839666304782584, | |
| "eval_loss": 2.27734375, | |
| "eval_runtime": 4.1932, | |
| "eval_samples_per_second": 20.51, | |
| "eval_steps_per_second": 1.431, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 7.035905179651701e-06, | |
| "loss": 1.2117, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_accuracy": 0.058425232843837493, | |
| "eval_loss": 2.2890625, | |
| "eval_runtime": 4.3132, | |
| "eval_samples_per_second": 19.939, | |
| "eval_steps_per_second": 1.391, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 6.582194019564266e-06, | |
| "loss": 1.4059, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_accuracy": 0.058039540597680135, | |
| "eval_loss": 2.30078125, | |
| "eval_runtime": 3.5756, | |
| "eval_samples_per_second": 24.052, | |
| "eval_steps_per_second": 1.678, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 6.1394580725317366e-06, | |
| "loss": 1.328, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_accuracy": 0.05811096508770927, | |
| "eval_loss": 2.314453125, | |
| "eval_runtime": 4.2869, | |
| "eval_samples_per_second": 20.061, | |
| "eval_steps_per_second": 1.4, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.708274581764155e-06, | |
| "loss": 1.3436, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.05795383120964517, | |
| "eval_loss": 2.328125, | |
| "eval_runtime": 3.8909, | |
| "eval_samples_per_second": 22.103, | |
| "eval_steps_per_second": 1.542, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 5.289205728272587e-06, | |
| "loss": 1.389, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_accuracy": 0.058039540597680135, | |
| "eval_loss": 2.337890625, | |
| "eval_runtime": 4.3156, | |
| "eval_samples_per_second": 19.928, | |
| "eval_steps_per_second": 1.39, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.882797897892293e-06, | |
| "loss": 1.2127, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_accuracy": 0.0580252556996743, | |
| "eval_loss": 2.33984375, | |
| "eval_runtime": 4.3, | |
| "eval_samples_per_second": 20.0, | |
| "eval_steps_per_second": 1.395, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.4895809688998655e-06, | |
| "loss": 1.3645, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_accuracy": 0.058096680189703445, | |
| "eval_loss": 2.341796875, | |
| "eval_runtime": 4.216, | |
| "eval_samples_per_second": 20.398, | |
| "eval_steps_per_second": 1.423, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.110067621153041e-06, | |
| "loss": 1.3389, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_accuracy": 0.05805382549568596, | |
| "eval_loss": 2.337890625, | |
| "eval_runtime": 3.9033, | |
| "eval_samples_per_second": 22.032, | |
| "eval_steps_per_second": 1.537, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.744752667653965e-06, | |
| "loss": 1.2549, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_accuracy": 0.05808239529169762, | |
| "eval_loss": 2.33203125, | |
| "eval_runtime": 3.5918, | |
| "eval_samples_per_second": 23.943, | |
| "eval_steps_per_second": 1.67, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 3.394112409407455e-06, | |
| "loss": 1.2193, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_accuracy": 0.05816810467973259, | |
| "eval_loss": 2.328125, | |
| "eval_runtime": 4.2985, | |
| "eval_samples_per_second": 20.007, | |
| "eval_steps_per_second": 1.396, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.0586040144153436e-06, | |
| "loss": 1.3617, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_accuracy": 0.0583252385577967, | |
| "eval_loss": 2.322265625, | |
| "eval_runtime": 3.2953, | |
| "eval_samples_per_second": 26.097, | |
| "eval_steps_per_second": 1.821, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 2.7386649216166233e-06, | |
| "loss": 1.2336, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_accuracy": 0.058253814067767556, | |
| "eval_loss": 2.318359375, | |
| "eval_runtime": 4.1807, | |
| "eval_samples_per_second": 20.571, | |
| "eval_steps_per_second": 1.435, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2.4347122705505303e-06, | |
| "loss": 1.179, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_accuracy": 0.05829666876178504, | |
| "eval_loss": 2.314453125, | |
| "eval_runtime": 3.5945, | |
| "eval_samples_per_second": 23.926, | |
| "eval_steps_per_second": 1.669, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.1471423574861643e-06, | |
| "loss": 1.2468, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_accuracy": 0.058282383863779215, | |
| "eval_loss": 2.3125, | |
| "eval_runtime": 3.5979, | |
| "eval_samples_per_second": 23.903, | |
| "eval_steps_per_second": 1.668, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 1.8763301187277554e-06, | |
| "loss": 1.3325, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_accuracy": 0.05829666876178504, | |
| "eval_loss": 2.30859375, | |
| "eval_runtime": 3.9093, | |
| "eval_samples_per_second": 21.999, | |
| "eval_steps_per_second": 1.535, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 1.6226286417692666e-06, | |
| "loss": 1.1471, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_accuracy": 0.058339523455802525, | |
| "eval_loss": 2.306640625, | |
| "eval_runtime": 4.2929, | |
| "eval_samples_per_second": 20.033, | |
| "eval_steps_per_second": 1.398, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 1.3863687049356465e-06, | |
| "loss": 1.3123, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_accuracy": 0.0583252385577967, | |
| "eval_loss": 2.306640625, | |
| "eval_runtime": 4.3098, | |
| "eval_samples_per_second": 19.955, | |
| "eval_steps_per_second": 1.392, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 1.1678583461110026e-06, | |
| "loss": 1.3285, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_accuracy": 0.05845380263984915, | |
| "eval_loss": 2.3046875, | |
| "eval_runtime": 4.3011, | |
| "eval_samples_per_second": 19.995, | |
| "eval_steps_per_second": 1.395, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 9.67382461115986e-07, | |
| "loss": 1.3232, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_accuracy": 0.05836809325181418, | |
| "eval_loss": 2.302734375, | |
| "eval_runtime": 4.2978, | |
| "eval_samples_per_second": 20.01, | |
| "eval_steps_per_second": 1.396, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 7.852024322579649e-07, | |
| "loss": 1.1228, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_accuracy": 0.05835380835380835, | |
| "eval_loss": 2.302734375, | |
| "eval_runtime": 3.6063, | |
| "eval_samples_per_second": 23.847, | |
| "eval_steps_per_second": 1.664, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 6.215557875383804e-07, | |
| "loss": 1.3524, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_accuracy": 0.05839666304782584, | |
| "eval_loss": 2.302734375, | |
| "eval_runtime": 4.1961, | |
| "eval_samples_per_second": 20.495, | |
| "eval_steps_per_second": 1.43, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 4.766558909615504e-07, | |
| "loss": 1.2042, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.058339523455802525, | |
| "eval_loss": 2.302734375, | |
| "eval_runtime": 4.3056, | |
| "eval_samples_per_second": 19.974, | |
| "eval_steps_per_second": 1.394, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.5069166434870014e-07, | |
| "loss": 1.3588, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_accuracy": 0.058339523455802525, | |
| "eval_loss": 2.30078125, | |
| "eval_runtime": 4.1957, | |
| "eval_samples_per_second": 20.497, | |
| "eval_steps_per_second": 1.43, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 2.438273410199598e-07, | |
| "loss": 1.2982, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_accuracy": 0.058425232843837493, | |
| "eval_loss": 2.30078125, | |
| "eval_runtime": 3.898, | |
| "eval_samples_per_second": 22.062, | |
| "eval_steps_per_second": 1.539, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.5620225166544155e-07, | |
| "loss": 1.4373, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_accuracy": 0.05845380263984915, | |
| "eval_loss": 2.30078125, | |
| "eval_runtime": 4.3019, | |
| "eval_samples_per_second": 19.991, | |
| "eval_steps_per_second": 1.395, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.793064268460605e-08, | |
| "loss": 1.3562, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.05841094794583167, | |
| "eval_loss": 2.30078125, | |
| "eval_runtime": 4.2946, | |
| "eval_samples_per_second": 20.025, | |
| "eval_steps_per_second": 1.397, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 87, | |
| "total_flos": 4783591391232.0, | |
| "train_loss": 1.8617539679867097, | |
| "train_runtime": 1017.4729, | |
| "train_samples_per_second": 1.353, | |
| "train_steps_per_second": 0.086 | |
| } | |
| ], | |
| "max_steps": 87, | |
| "num_train_epochs": 3, | |
| "total_flos": 4783591391232.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |