| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.27360850531582237, | |
| "eval_steps": 500, | |
| "global_step": 7000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003908692933083177, | |
| "grad_norm": 0.47716134786605835, | |
| "learning_rate": 4.98240400406663e-05, | |
| "loss": 1.3868, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007817385866166354, | |
| "grad_norm": 0.28900113701820374, | |
| "learning_rate": 4.9628528974739973e-05, | |
| "loss": 1.3348, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01172607879924953, | |
| "grad_norm": 0.37652796506881714, | |
| "learning_rate": 4.943301790881364e-05, | |
| "loss": 1.3298, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.015634771732332707, | |
| "grad_norm": 0.24992702901363373, | |
| "learning_rate": 4.923750684288731e-05, | |
| "loss": 1.3309, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.019543464665415886, | |
| "grad_norm": 0.3237004280090332, | |
| "learning_rate": 4.904199577696098e-05, | |
| "loss": 1.3228, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02345215759849906, | |
| "grad_norm": 0.259011447429657, | |
| "learning_rate": 4.884648471103465e-05, | |
| "loss": 1.3166, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02736085053158224, | |
| "grad_norm": 0.34121841192245483, | |
| "learning_rate": 4.8650973645108314e-05, | |
| "loss": 1.3145, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.031269543464665414, | |
| "grad_norm": 0.41398781538009644, | |
| "learning_rate": 4.845546257918198e-05, | |
| "loss": 1.3081, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.03517823639774859, | |
| "grad_norm": 0.4289904832839966, | |
| "learning_rate": 4.825995151325565e-05, | |
| "loss": 1.3073, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.03908692933083177, | |
| "grad_norm": 0.21226634085178375, | |
| "learning_rate": 4.8064440447329324e-05, | |
| "loss": 1.3057, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04299562226391495, | |
| "grad_norm": 0.2929254174232483, | |
| "learning_rate": 4.786892938140299e-05, | |
| "loss": 1.3034, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.04690431519699812, | |
| "grad_norm": 0.22025109827518463, | |
| "learning_rate": 4.767341831547666e-05, | |
| "loss": 1.3048, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.0508130081300813, | |
| "grad_norm": 0.36455097794532776, | |
| "learning_rate": 4.747790724955033e-05, | |
| "loss": 1.3028, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.05472170106316448, | |
| "grad_norm": 0.24527208507061005, | |
| "learning_rate": 4.728239618362399e-05, | |
| "loss": 1.2996, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.05863039399624766, | |
| "grad_norm": 0.33187615871429443, | |
| "learning_rate": 4.7086885117697664e-05, | |
| "loss": 1.3001, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.06253908692933083, | |
| "grad_norm": 0.502117931842804, | |
| "learning_rate": 4.689137405177133e-05, | |
| "loss": 1.2954, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.06644777986241401, | |
| "grad_norm": 0.289112389087677, | |
| "learning_rate": 4.6695862985845e-05, | |
| "loss": 1.2969, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.07035647279549719, | |
| "grad_norm": 0.24350133538246155, | |
| "learning_rate": 4.6500351919918674e-05, | |
| "loss": 1.2929, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.07426516572858036, | |
| "grad_norm": 0.2194579690694809, | |
| "learning_rate": 4.630484085399234e-05, | |
| "loss": 1.2913, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.07817385866166354, | |
| "grad_norm": 0.3578532636165619, | |
| "learning_rate": 4.6109329788066005e-05, | |
| "loss": 1.2946, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.08208255159474671, | |
| "grad_norm": 0.22988037765026093, | |
| "learning_rate": 4.591381872213967e-05, | |
| "loss": 1.2906, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.0859912445278299, | |
| "grad_norm": 0.44038262963294983, | |
| "learning_rate": 4.571830765621334e-05, | |
| "loss": 1.2941, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.08989993746091307, | |
| "grad_norm": 0.27333030104637146, | |
| "learning_rate": 4.5522796590287015e-05, | |
| "loss": 1.2903, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.09380863039399624, | |
| "grad_norm": 0.23196421563625336, | |
| "learning_rate": 4.532728552436068e-05, | |
| "loss": 1.2897, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.09771732332707943, | |
| "grad_norm": 0.25054216384887695, | |
| "learning_rate": 4.513177445843435e-05, | |
| "loss": 1.2891, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.1016260162601626, | |
| "grad_norm": 0.17129705846309662, | |
| "learning_rate": 4.493626339250802e-05, | |
| "loss": 1.2874, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.10553470919324578, | |
| "grad_norm": 0.5260087251663208, | |
| "learning_rate": 4.474075232658168e-05, | |
| "loss": 1.289, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.10944340212632896, | |
| "grad_norm": 0.2251499593257904, | |
| "learning_rate": 4.4545241260655355e-05, | |
| "loss": 1.2882, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.11335209505941213, | |
| "grad_norm": 0.24193763732910156, | |
| "learning_rate": 4.434973019472902e-05, | |
| "loss": 1.2886, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.11726078799249531, | |
| "grad_norm": 0.2361423224210739, | |
| "learning_rate": 4.415421912880269e-05, | |
| "loss": 1.2863, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.12116948092557848, | |
| "grad_norm": 0.22438161075115204, | |
| "learning_rate": 4.3958708062876365e-05, | |
| "loss": 1.2861, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.12507817385866166, | |
| "grad_norm": 0.30306315422058105, | |
| "learning_rate": 4.376319699695003e-05, | |
| "loss": 1.2838, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.12898686679174484, | |
| "grad_norm": 0.2526134252548218, | |
| "learning_rate": 4.35676859310237e-05, | |
| "loss": 1.288, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.13289555972482803, | |
| "grad_norm": 0.27540501952171326, | |
| "learning_rate": 4.337217486509736e-05, | |
| "loss": 1.2878, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.13680425265791119, | |
| "grad_norm": 0.2769360840320587, | |
| "learning_rate": 4.3176663799171034e-05, | |
| "loss": 1.2844, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.14071294559099437, | |
| "grad_norm": 0.3868384063243866, | |
| "learning_rate": 4.2981152733244706e-05, | |
| "loss": 1.2856, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.14462163852407756, | |
| "grad_norm": 0.2426549792289734, | |
| "learning_rate": 4.278564166731837e-05, | |
| "loss": 1.2843, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.1485303314571607, | |
| "grad_norm": 0.28486019372940063, | |
| "learning_rate": 4.2590130601392044e-05, | |
| "loss": 1.2812, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.1524390243902439, | |
| "grad_norm": 0.3195390999317169, | |
| "learning_rate": 4.239461953546571e-05, | |
| "loss": 1.2845, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.15634771732332708, | |
| "grad_norm": 0.3183465003967285, | |
| "learning_rate": 4.219910846953938e-05, | |
| "loss": 1.281, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.16025641025641027, | |
| "grad_norm": 0.30105575919151306, | |
| "learning_rate": 4.2003597403613047e-05, | |
| "loss": 1.2817, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.16416510318949343, | |
| "grad_norm": 0.3548736274242401, | |
| "learning_rate": 4.180808633768671e-05, | |
| "loss": 1.2805, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.1680737961225766, | |
| "grad_norm": 0.21018876135349274, | |
| "learning_rate": 4.1612575271760384e-05, | |
| "loss": 1.28, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.1719824890556598, | |
| "grad_norm": 0.2551437318325043, | |
| "learning_rate": 4.141706420583405e-05, | |
| "loss": 1.279, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.17589118198874296, | |
| "grad_norm": 0.21301493048667908, | |
| "learning_rate": 4.122155313990772e-05, | |
| "loss": 1.2802, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.17979987492182614, | |
| "grad_norm": 0.3330891728401184, | |
| "learning_rate": 4.1026042073981394e-05, | |
| "loss": 1.2784, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.18370856785490933, | |
| "grad_norm": 0.20550762116909027, | |
| "learning_rate": 4.083053100805506e-05, | |
| "loss": 1.2802, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.18761726078799248, | |
| "grad_norm": 0.2603992521762848, | |
| "learning_rate": 4.0635019942128725e-05, | |
| "loss": 1.2792, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.19152595372107567, | |
| "grad_norm": 0.17917224764823914, | |
| "learning_rate": 4.04395088762024e-05, | |
| "loss": 1.2803, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.19543464665415886, | |
| "grad_norm": 0.17226773500442505, | |
| "learning_rate": 4.024399781027606e-05, | |
| "loss": 1.2775, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.199343339587242, | |
| "grad_norm": 0.28991296887397766, | |
| "learning_rate": 4.0048486744349735e-05, | |
| "loss": 1.2801, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.2032520325203252, | |
| "grad_norm": 0.2766139805316925, | |
| "learning_rate": 3.98529756784234e-05, | |
| "loss": 1.2773, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.20716072545340838, | |
| "grad_norm": 0.3101244866847992, | |
| "learning_rate": 3.965746461249707e-05, | |
| "loss": 1.2786, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.21106941838649157, | |
| "grad_norm": 0.2537230849266052, | |
| "learning_rate": 3.946195354657074e-05, | |
| "loss": 1.2782, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.21497811131957473, | |
| "grad_norm": 0.388886958360672, | |
| "learning_rate": 3.92664424806444e-05, | |
| "loss": 1.2766, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.2188868042526579, | |
| "grad_norm": 0.3374210596084595, | |
| "learning_rate": 3.9070931414718075e-05, | |
| "loss": 1.273, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.2227954971857411, | |
| "grad_norm": 0.34907710552215576, | |
| "learning_rate": 3.887542034879174e-05, | |
| "loss": 1.2772, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.22670419011882426, | |
| "grad_norm": 0.22610360383987427, | |
| "learning_rate": 3.867990928286541e-05, | |
| "loss": 1.2744, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.23061288305190744, | |
| "grad_norm": 0.27353575825691223, | |
| "learning_rate": 3.8484398216939085e-05, | |
| "loss": 1.2755, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.23452157598499063, | |
| "grad_norm": 0.3231126368045807, | |
| "learning_rate": 3.828888715101275e-05, | |
| "loss": 1.2746, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.23843026891807378, | |
| "grad_norm": 0.3560299575328827, | |
| "learning_rate": 3.8093376085086416e-05, | |
| "loss": 1.2725, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.24233896185115697, | |
| "grad_norm": 0.2950970530509949, | |
| "learning_rate": 3.789786501916008e-05, | |
| "loss": 1.27, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.24624765478424016, | |
| "grad_norm": 0.25703492760658264, | |
| "learning_rate": 3.770235395323375e-05, | |
| "loss": 1.2705, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.2501563477173233, | |
| "grad_norm": 0.4161667227745056, | |
| "learning_rate": 3.7506842887307426e-05, | |
| "loss": 1.2725, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.2540650406504065, | |
| "grad_norm": 0.4292469322681427, | |
| "learning_rate": 3.731133182138109e-05, | |
| "loss": 1.2736, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.2579737335834897, | |
| "grad_norm": 0.28723031282424927, | |
| "learning_rate": 3.711582075545476e-05, | |
| "loss": 1.2696, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.26188242651657284, | |
| "grad_norm": 0.3981460928916931, | |
| "learning_rate": 3.692030968952843e-05, | |
| "loss": 1.2712, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.26579111944965605, | |
| "grad_norm": 0.509950578212738, | |
| "learning_rate": 3.6724798623602094e-05, | |
| "loss": 1.272, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.2696998123827392, | |
| "grad_norm": 0.2820459008216858, | |
| "learning_rate": 3.6529287557675766e-05, | |
| "loss": 1.2704, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.27360850531582237, | |
| "grad_norm": 0.2927381098270416, | |
| "learning_rate": 3.633377649174943e-05, | |
| "loss": 1.268, | |
| "step": 7000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 25584, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.957498454016e+16, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |