| { | |
| "best_metric": 0.8274506330490112, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.0, | |
| "eval_steps": 50, | |
| "global_step": 114, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 36.11992263793945, | |
| "learning_rate": 1e-05, | |
| "loss": 5.5742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "eval_loss": 1.6754724979400635, | |
| "eval_runtime": 4.6364, | |
| "eval_samples_per_second": 13.804, | |
| "eval_steps_per_second": 3.451, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 45.496089935302734, | |
| "learning_rate": 2e-05, | |
| "loss": 6.0369, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 46.79734802246094, | |
| "learning_rate": 3e-05, | |
| "loss": 6.0623, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 52.48137283325195, | |
| "learning_rate": 4e-05, | |
| "loss": 5.5416, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 39.756309509277344, | |
| "learning_rate": 5e-05, | |
| "loss": 5.173, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 41.609867095947266, | |
| "learning_rate": 6e-05, | |
| "loss": 4.7899, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18421052631578946, | |
| "grad_norm": 27.226150512695312, | |
| "learning_rate": 7e-05, | |
| "loss": 3.9422, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 33.287879943847656, | |
| "learning_rate": 8e-05, | |
| "loss": 3.9925, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23684210526315788, | |
| "grad_norm": 39.3206672668457, | |
| "learning_rate": 9e-05, | |
| "loss": 4.7715, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 41.02152633666992, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7116, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2894736842105263, | |
| "grad_norm": 17.27116584777832, | |
| "learning_rate": 9.997718922447667e-05, | |
| "loss": 3.7028, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 15.264183044433594, | |
| "learning_rate": 9.990877771116589e-05, | |
| "loss": 4.0017, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.34210526315789475, | |
| "grad_norm": 15.61949348449707, | |
| "learning_rate": 9.979482788085454e-05, | |
| "loss": 3.2975, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 18.417621612548828, | |
| "learning_rate": 9.96354437049027e-05, | |
| "loss": 3.4839, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 17.082714080810547, | |
| "learning_rate": 9.943077061037671e-05, | |
| "loss": 3.2736, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 21.343236923217773, | |
| "learning_rate": 9.918099534735718e-05, | |
| "loss": 3.5313, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4473684210526316, | |
| "grad_norm": 17.40627670288086, | |
| "learning_rate": 9.888634581854234e-05, | |
| "loss": 3.2103, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 26.427959442138672, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 3.6983, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 26.003570556640625, | |
| "learning_rate": 9.816354005237583e-05, | |
| "loss": 3.3593, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 13.644905090332031, | |
| "learning_rate": 9.773604332542729e-05, | |
| "loss": 3.8264, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5526315789473685, | |
| "grad_norm": 12.819908142089844, | |
| "learning_rate": 9.726499075173201e-05, | |
| "loss": 3.4524, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 14.334078788757324, | |
| "learning_rate": 9.675081213427076e-05, | |
| "loss": 3.6683, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6052631578947368, | |
| "grad_norm": 14.417925834655762, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.7619, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 14.206096649169922, | |
| "learning_rate": 9.559499229960451e-05, | |
| "loss": 3.2873, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": 14.678654670715332, | |
| "learning_rate": 9.495440568827129e-05, | |
| "loss": 3.3115, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 16.141925811767578, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 3.4907, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7105263157894737, | |
| "grad_norm": 21.366544723510742, | |
| "learning_rate": 9.355080099977578e-05, | |
| "loss": 4.1801, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 10.775222778320312, | |
| "learning_rate": 9.278906361507238e-05, | |
| "loss": 3.3955, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7631578947368421, | |
| "grad_norm": 10.973443984985352, | |
| "learning_rate": 9.19882841613699e-05, | |
| "loss": 3.2433, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 16.16126251220703, | |
| "learning_rate": 9.114919329468282e-05, | |
| "loss": 3.5706, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8157894736842105, | |
| "grad_norm": 12.188801765441895, | |
| "learning_rate": 9.02725566275473e-05, | |
| "loss": 3.3048, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 14.286109924316406, | |
| "learning_rate": 8.935917403045251e-05, | |
| "loss": 3.5666, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.868421052631579, | |
| "grad_norm": 14.997357368469238, | |
| "learning_rate": 8.840987890201403e-05, | |
| "loss": 3.8015, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 13.553812026977539, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 3.2431, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": 13.112909317016602, | |
| "learning_rate": 8.640704769378942e-05, | |
| "loss": 3.4528, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 16.17171287536621, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.7627, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9736842105263158, | |
| "grad_norm": 12.972054481506348, | |
| "learning_rate": 8.427137111675199e-05, | |
| "loss": 3.5154, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 17.756343841552734, | |
| "learning_rate": 8.315613291203976e-05, | |
| "loss": 3.4056, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0263157894736843, | |
| "grad_norm": 8.132559776306152, | |
| "learning_rate": 8.201064202312441e-05, | |
| "loss": 2.9234, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 7.704466819763184, | |
| "learning_rate": 8.083594363142717e-05, | |
| "loss": 1.9351, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0789473684210527, | |
| "grad_norm": 8.56411075592041, | |
| "learning_rate": 7.963310956820085e-05, | |
| "loss": 1.8873, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 7.822863578796387, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 1.6994, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.131578947368421, | |
| "grad_norm": 11.918898582458496, | |
| "learning_rate": 7.714744911007394e-05, | |
| "loss": 1.6854, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 10.359103202819824, | |
| "learning_rate": 7.586689070888284e-05, | |
| "loss": 1.4273, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.1842105263157894, | |
| "grad_norm": 13.726045608520508, | |
| "learning_rate": 7.456273055419388e-05, | |
| "loss": 1.1155, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 11.406822204589844, | |
| "learning_rate": 7.323615860218843e-05, | |
| "loss": 1.0255, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.236842105263158, | |
| "grad_norm": 18.803253173828125, | |
| "learning_rate": 7.188838525826702e-05, | |
| "loss": 1.3298, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 13.75057601928711, | |
| "learning_rate": 7.052064027263786e-05, | |
| "loss": 2.3476, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.2894736842105263, | |
| "grad_norm": 11.206314086914062, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.597, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 10.493936538696289, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 1.637, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "eval_loss": 0.8274506330490112, | |
| "eval_runtime": 4.7798, | |
| "eval_samples_per_second": 13.39, | |
| "eval_steps_per_second": 3.347, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3421052631578947, | |
| "grad_norm": 9.546468734741211, | |
| "learning_rate": 6.631013946104347e-05, | |
| "loss": 1.7558, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 9.4080228805542, | |
| "learning_rate": 6.487515269276016e-05, | |
| "loss": 1.4641, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.3947368421052633, | |
| "grad_norm": 7.666134834289551, | |
| "learning_rate": 6.342659337371885e-05, | |
| "loss": 1.0689, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.4210526315789473, | |
| "grad_norm": 9.010215759277344, | |
| "learning_rate": 6.19657832143779e-05, | |
| "loss": 1.2617, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.4473684210526316, | |
| "grad_norm": 11.879247665405273, | |
| "learning_rate": 6.049405510324238e-05, | |
| "loss": 1.1061, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 15.107841491699219, | |
| "learning_rate": 5.90127518906953e-05, | |
| "loss": 1.5306, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 9.882277488708496, | |
| "learning_rate": 5.752322516373916e-05, | |
| "loss": 2.4832, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.526315789473684, | |
| "grad_norm": 8.323047637939453, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 1.656, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.5526315789473686, | |
| "grad_norm": 9.123269081115723, | |
| "learning_rate": 5.45249437914819e-05, | |
| "loss": 1.592, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 10.40864086151123, | |
| "learning_rate": 5.3018924871114305e-05, | |
| "loss": 1.4905, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.6052631578947367, | |
| "grad_norm": 9.093459129333496, | |
| "learning_rate": 5.151015139004445e-05, | |
| "loss": 1.2591, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": 10.694282531738281, | |
| "learning_rate": 5e-05, | |
| "loss": 1.351, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.6578947368421053, | |
| "grad_norm": 12.236539840698242, | |
| "learning_rate": 4.848984860995557e-05, | |
| "loss": 1.1828, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 10.095430374145508, | |
| "learning_rate": 4.6981075128885693e-05, | |
| "loss": 1.1513, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.7105263157894737, | |
| "grad_norm": 12.897542953491211, | |
| "learning_rate": 4.547505620851811e-05, | |
| "loss": 1.0376, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 10.298996925354004, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 2.2939, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.763157894736842, | |
| "grad_norm": 8.406174659729004, | |
| "learning_rate": 4.2476774836260845e-05, | |
| "loss": 1.4841, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 8.802860260009766, | |
| "learning_rate": 4.0987248109304714e-05, | |
| "loss": 1.567, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.8157894736842106, | |
| "grad_norm": 10.089945793151855, | |
| "learning_rate": 3.950594489675763e-05, | |
| "loss": 1.2052, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 11.97966194152832, | |
| "learning_rate": 3.803421678562213e-05, | |
| "loss": 1.4612, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.868421052631579, | |
| "grad_norm": 11.531331062316895, | |
| "learning_rate": 3.657340662628116e-05, | |
| "loss": 1.2934, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 8.967305183410645, | |
| "learning_rate": 3.512484730723986e-05, | |
| "loss": 1.1132, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.9210526315789473, | |
| "grad_norm": 22.837160110473633, | |
| "learning_rate": 3.368986053895655e-05, | |
| "loss": 1.2606, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.9473684210526314, | |
| "grad_norm": 14.750879287719727, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 1.2884, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.973684210526316, | |
| "grad_norm": 10.757916450500488, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8587, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 15.325807571411133, | |
| "learning_rate": 2.9479359727362173e-05, | |
| "loss": 1.2197, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.026315789473684, | |
| "grad_norm": 5.313655853271484, | |
| "learning_rate": 2.811161474173297e-05, | |
| "loss": 1.1478, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 5.582791328430176, | |
| "learning_rate": 2.6763841397811573e-05, | |
| "loss": 0.6872, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.0789473684210527, | |
| "grad_norm": 4.926303863525391, | |
| "learning_rate": 2.5437269445806145e-05, | |
| "loss": 0.5424, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 7.606872081756592, | |
| "learning_rate": 2.4133109291117156e-05, | |
| "loss": 0.5015, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.1315789473684212, | |
| "grad_norm": 5.713882923126221, | |
| "learning_rate": 2.2852550889926067e-05, | |
| "loss": 0.4867, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.1578947368421053, | |
| "grad_norm": 8.591730117797852, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 0.4267, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.1842105263157894, | |
| "grad_norm": 12.103515625, | |
| "learning_rate": 2.0366890431799167e-05, | |
| "loss": 0.2807, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 8.517769813537598, | |
| "learning_rate": 1.9164056368572846e-05, | |
| "loss": 0.3038, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.236842105263158, | |
| "grad_norm": 6.122335433959961, | |
| "learning_rate": 1.7989357976875603e-05, | |
| "loss": 0.3068, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.263157894736842, | |
| "grad_norm": 9.968849182128906, | |
| "learning_rate": 1.684386708796025e-05, | |
| "loss": 1.396, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.2894736842105265, | |
| "grad_norm": 10.96872615814209, | |
| "learning_rate": 1.5728628883248007e-05, | |
| "loss": 0.5336, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 7.527137279510498, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5198, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.3421052631578947, | |
| "grad_norm": 6.584356784820557, | |
| "learning_rate": 1.3592952306210588e-05, | |
| "loss": 0.3041, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 7.736539363861084, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 0.4027, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.3947368421052633, | |
| "grad_norm": 5.754791259765625, | |
| "learning_rate": 1.159012109798598e-05, | |
| "loss": 0.2305, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 6.632175922393799, | |
| "learning_rate": 1.0640825969547496e-05, | |
| "loss": 0.2377, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.4473684210526314, | |
| "grad_norm": 12.447802543640137, | |
| "learning_rate": 9.7274433724527e-06, | |
| "loss": 0.3519, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 2.473684210526316, | |
| "grad_norm": 7.3365702629089355, | |
| "learning_rate": 8.850806705317183e-06, | |
| "loss": 0.2841, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 8.352860450744629, | |
| "learning_rate": 8.011715838630107e-06, | |
| "loss": 0.9615, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 7.111477851867676, | |
| "learning_rate": 7.21093638492763e-06, | |
| "loss": 0.4884, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.5526315789473686, | |
| "grad_norm": 7.582794189453125, | |
| "learning_rate": 6.449199000224221e-06, | |
| "loss": 0.5061, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 2.5789473684210527, | |
| "grad_norm": 8.334342002868652, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 0.5218, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.6052631578947367, | |
| "grad_norm": 15.341864585876465, | |
| "learning_rate": 5.045594311728707e-06, | |
| "loss": 0.3552, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 8.251885414123535, | |
| "learning_rate": 4.405007700395497e-06, | |
| "loss": 0.3264, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "eval_loss": 0.9560651779174805, | |
| "eval_runtime": 4.7813, | |
| "eval_samples_per_second": 13.385, | |
| "eval_steps_per_second": 3.346, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.6578947368421053, | |
| "grad_norm": 7.54060697555542, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2268, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 2.6842105263157894, | |
| "grad_norm": 9.745018005371094, | |
| "learning_rate": 3.249187865729264e-06, | |
| "loss": 0.5083, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.7105263157894735, | |
| "grad_norm": 6.40946102142334, | |
| "learning_rate": 2.7350092482679836e-06, | |
| "loss": 0.202, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 7.4240217208862305, | |
| "learning_rate": 2.2639566745727205e-06, | |
| "loss": 0.9122, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.763157894736842, | |
| "grad_norm": 6.273193836212158, | |
| "learning_rate": 1.8364599476241862e-06, | |
| "loss": 0.4703, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.7894736842105265, | |
| "grad_norm": 7.9733967781066895, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 0.4487, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.8157894736842106, | |
| "grad_norm": 7.2762579917907715, | |
| "learning_rate": 1.1136541814576573e-06, | |
| "loss": 0.3321, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 6.559560298919678, | |
| "learning_rate": 8.190046526428242e-07, | |
| "loss": 0.3086, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.8684210526315788, | |
| "grad_norm": 7.2038397789001465, | |
| "learning_rate": 5.692293896232936e-07, | |
| "loss": 0.2334, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 8.095062255859375, | |
| "learning_rate": 3.6455629509730136e-07, | |
| "loss": 0.3355, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.9210526315789473, | |
| "grad_norm": 8.475146293640137, | |
| "learning_rate": 2.0517211914545254e-07, | |
| "loss": 0.2103, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 8.619668960571289, | |
| "learning_rate": 9.12222888341252e-08, | |
| "loss": 0.2427, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.973684210526316, | |
| "grad_norm": 5.392899036407471, | |
| "learning_rate": 2.2810775523329773e-08, | |
| "loss": 0.3473, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 12.812440872192383, | |
| "learning_rate": 0.0, | |
| "loss": 0.3174, | |
| "step": 114 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 114, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.6219486313408102e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |