| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1266, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023696682464454975, | |
| "grad_norm": 30.705133295132807, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5563, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04739336492890995, | |
| "grad_norm": 2.043478075324726, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4838, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07109004739336493, | |
| "grad_norm": 1.3358743818486332, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4503, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0947867298578199, | |
| "grad_norm": 0.7538335151640748, | |
| "learning_rate": 5e-06, | |
| "loss": 0.429, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11848341232227488, | |
| "grad_norm": 0.7811530617140079, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4108, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14218009478672985, | |
| "grad_norm": 0.9317427620124435, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4018, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16587677725118483, | |
| "grad_norm": 0.6243367032731518, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3908, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1895734597156398, | |
| "grad_norm": 0.6176921128719449, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3833, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2132701421800948, | |
| "grad_norm": 0.4314255330259147, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3777, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23696682464454977, | |
| "grad_norm": 0.5197854521683744, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3704, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26066350710900477, | |
| "grad_norm": 1.002573805206526, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3662, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2843601895734597, | |
| "grad_norm": 0.5881621358357682, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3658, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3080568720379147, | |
| "grad_norm": 0.5217282145946449, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3629, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33175355450236965, | |
| "grad_norm": 0.6091442268483355, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3652, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35545023696682465, | |
| "grad_norm": 0.8005863736511483, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3531, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3791469194312796, | |
| "grad_norm": 0.6150361006740718, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3498, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4028436018957346, | |
| "grad_norm": 0.6278490509821739, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3507, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4265402843601896, | |
| "grad_norm": 0.8241804964154705, | |
| "learning_rate": 5e-06, | |
| "loss": 0.348, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.45023696682464454, | |
| "grad_norm": 0.6555844743575341, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3476, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.47393364928909953, | |
| "grad_norm": 0.5422180070121905, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3427, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4976303317535545, | |
| "grad_norm": 0.5207523671441107, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3447, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5213270142180095, | |
| "grad_norm": 0.45313363674774493, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3408, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5450236966824644, | |
| "grad_norm": 0.5162603087798662, | |
| "learning_rate": 5e-06, | |
| "loss": 0.341, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5687203791469194, | |
| "grad_norm": 0.46580112576483534, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3335, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5924170616113744, | |
| "grad_norm": 0.608794869219161, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3345, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6161137440758294, | |
| "grad_norm": 0.523854370493108, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3308, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6398104265402843, | |
| "grad_norm": 0.5706943490018692, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3361, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6635071090047393, | |
| "grad_norm": 0.45300138137727003, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3326, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6872037914691943, | |
| "grad_norm": 0.45102429427517104, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3302, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7109004739336493, | |
| "grad_norm": 0.5137700452326517, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3289, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7345971563981043, | |
| "grad_norm": 0.6127249666946868, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3316, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7582938388625592, | |
| "grad_norm": 0.44932409996775663, | |
| "learning_rate": 5e-06, | |
| "loss": 0.326, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7819905213270142, | |
| "grad_norm": 0.5532587149282668, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3296, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8056872037914692, | |
| "grad_norm": 0.43366234423399613, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3292, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8293838862559242, | |
| "grad_norm": 0.6322058991355771, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3294, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8530805687203792, | |
| "grad_norm": 0.46695206519297977, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3302, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8767772511848341, | |
| "grad_norm": 0.5812611546801564, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3273, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9004739336492891, | |
| "grad_norm": 0.5621804321411954, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3192, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9241706161137441, | |
| "grad_norm": 0.4679602140385812, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3214, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9478672985781991, | |
| "grad_norm": 0.5333407829184633, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3204, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9715639810426541, | |
| "grad_norm": 0.43987965909268334, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3214, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.995260663507109, | |
| "grad_norm": 0.6709211874509404, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3182, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.3187981843948364, | |
| "eval_runtime": 41.0925, | |
| "eval_samples_per_second": 276.547, | |
| "eval_steps_per_second": 1.095, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.018957345971564, | |
| "grad_norm": 0.5760447436307622, | |
| "learning_rate": 5e-06, | |
| "loss": 0.287, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.042654028436019, | |
| "grad_norm": 0.6762165069988788, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2762, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.066350710900474, | |
| "grad_norm": 0.47402123924703626, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2734, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0900473933649288, | |
| "grad_norm": 0.5516286942729635, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2769, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.113744075829384, | |
| "grad_norm": 0.5287265469429161, | |
| "learning_rate": 5e-06, | |
| "loss": 0.273, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.1374407582938388, | |
| "grad_norm": 0.6297802215905517, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2763, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.161137440758294, | |
| "grad_norm": 0.5655517444516921, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2779, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1848341232227488, | |
| "grad_norm": 0.4960690379887489, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2745, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2085308056872037, | |
| "grad_norm": 0.4549491415898102, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2754, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2322274881516588, | |
| "grad_norm": 0.4752122430144407, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2731, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2559241706161137, | |
| "grad_norm": 0.4647993470821906, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2739, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2796208530805688, | |
| "grad_norm": 0.5109279201523487, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2714, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.3033175355450237, | |
| "grad_norm": 0.5840908685437068, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2737, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3270142180094786, | |
| "grad_norm": 0.5246063574530767, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2751, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.3507109004739337, | |
| "grad_norm": 0.44184294378239247, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2745, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3744075829383886, | |
| "grad_norm": 0.5913058737082955, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2734, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3981042654028437, | |
| "grad_norm": 0.5008265601868412, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2738, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4218009478672986, | |
| "grad_norm": 0.49995889605138555, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2744, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4454976303317535, | |
| "grad_norm": 0.45557075455533524, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2721, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4691943127962086, | |
| "grad_norm": 0.6379507686940746, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2732, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4928909952606635, | |
| "grad_norm": 0.4583258359143169, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2725, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5165876777251186, | |
| "grad_norm": 0.5749182699938892, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2665, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.5402843601895735, | |
| "grad_norm": 0.5326772009600166, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2697, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5639810426540284, | |
| "grad_norm": 0.5654654670246291, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2673, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5876777251184833, | |
| "grad_norm": 0.7750526195773435, | |
| "learning_rate": 5e-06, | |
| "loss": 0.274, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.6113744075829384, | |
| "grad_norm": 0.5315008234518865, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2702, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6350710900473935, | |
| "grad_norm": 0.5749838515161616, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2695, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.6587677725118484, | |
| "grad_norm": 0.5001274305498948, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2686, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6824644549763033, | |
| "grad_norm": 0.5123878344164223, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2707, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.7061611374407581, | |
| "grad_norm": 0.5614887710303913, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2669, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7298578199052133, | |
| "grad_norm": 0.549426396684614, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2658, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.7535545023696684, | |
| "grad_norm": 0.6106476140869552, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2687, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7772511848341233, | |
| "grad_norm": 0.44864012484374616, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2704, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.8009478672985781, | |
| "grad_norm": 0.6259517201369036, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2673, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.824644549763033, | |
| "grad_norm": 0.5150026298786189, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2693, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.8483412322274881, | |
| "grad_norm": 0.5457767160105244, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2652, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8720379146919433, | |
| "grad_norm": 0.4576520211880369, | |
| "learning_rate": 5e-06, | |
| "loss": 0.264, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8957345971563981, | |
| "grad_norm": 0.42780791505078525, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2707, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.919431279620853, | |
| "grad_norm": 0.48992225159350095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2645, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.943127962085308, | |
| "grad_norm": 0.5410708029490111, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2627, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.966824644549763, | |
| "grad_norm": 0.4336435751671359, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2663, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9905213270142181, | |
| "grad_norm": 0.43877727937635, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2676, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.30145883560180664, | |
| "eval_runtime": 41.7379, | |
| "eval_samples_per_second": 272.27, | |
| "eval_steps_per_second": 1.078, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 2.014218009478673, | |
| "grad_norm": 0.6524222083837387, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2369, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.037914691943128, | |
| "grad_norm": 0.5787525251465172, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2195, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.061611374407583, | |
| "grad_norm": 0.5756101918178816, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2199, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.085308056872038, | |
| "grad_norm": 0.6236522012957664, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2204, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.109004739336493, | |
| "grad_norm": 0.6419600675102759, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2207, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.132701421800948, | |
| "grad_norm": 0.6691668192668253, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2205, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.156398104265403, | |
| "grad_norm": 0.5662613639218179, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2202, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.1800947867298577, | |
| "grad_norm": 0.5285961633074623, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2213, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.2037914691943126, | |
| "grad_norm": 0.5182873734926402, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2237, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.227488151658768, | |
| "grad_norm": 0.455467292575364, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2196, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.251184834123223, | |
| "grad_norm": 0.5910920449175188, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2213, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.2748815165876777, | |
| "grad_norm": 0.48913238274264176, | |
| "learning_rate": 5e-06, | |
| "loss": 0.22, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.2985781990521326, | |
| "grad_norm": 0.48506465561903783, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2209, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.322274881516588, | |
| "grad_norm": 0.4777608016950058, | |
| "learning_rate": 5e-06, | |
| "loss": 0.225, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.345971563981043, | |
| "grad_norm": 0.5663901860164571, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2236, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.3696682464454977, | |
| "grad_norm": 0.5218376695680845, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2216, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3933649289099526, | |
| "grad_norm": 0.5699143314581089, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2233, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.4170616113744074, | |
| "grad_norm": 0.4742020161888442, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2228, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.4407582938388623, | |
| "grad_norm": 0.5183880143591837, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2226, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.4644549763033177, | |
| "grad_norm": 0.6480574727941906, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2211, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.4881516587677726, | |
| "grad_norm": 0.5046467998532, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2225, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.5118483412322274, | |
| "grad_norm": 0.6234765711742589, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2207, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.5355450236966823, | |
| "grad_norm": 0.5463355131695685, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2224, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.5592417061611377, | |
| "grad_norm": 0.5045207519726893, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2193, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.5829383886255926, | |
| "grad_norm": 0.5385436231173875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2215, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.6066350710900474, | |
| "grad_norm": 0.5203528739245922, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2239, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.6303317535545023, | |
| "grad_norm": 0.515758932015822, | |
| "learning_rate": 5e-06, | |
| "loss": 0.225, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.654028436018957, | |
| "grad_norm": 0.5245283280931154, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2217, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.677725118483412, | |
| "grad_norm": 0.47961811011847694, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2223, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.7014218009478674, | |
| "grad_norm": 0.532667073838913, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2202, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.7251184834123223, | |
| "grad_norm": 0.4731691182426918, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2203, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.748815165876777, | |
| "grad_norm": 0.5085530590505501, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2195, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.772511848341232, | |
| "grad_norm": 0.5212827222451933, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2201, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.7962085308056874, | |
| "grad_norm": 0.6101309650612445, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2241, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.8199052132701423, | |
| "grad_norm": 0.524976392694722, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2185, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.843601895734597, | |
| "grad_norm": 0.5268018676437338, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2218, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.867298578199052, | |
| "grad_norm": 0.4815524564659738, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2211, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.890995260663507, | |
| "grad_norm": 0.5166341199930529, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2194, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.914691943127962, | |
| "grad_norm": 0.4522595493688504, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2258, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.938388625592417, | |
| "grad_norm": 0.5232915579904739, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2218, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.962085308056872, | |
| "grad_norm": 0.5580173773855611, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2211, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.985781990521327, | |
| "grad_norm": 0.5398857489449794, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2241, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.30088362097740173, | |
| "eval_runtime": 40.2088, | |
| "eval_samples_per_second": 282.624, | |
| "eval_steps_per_second": 1.119, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1266, | |
| "total_flos": 2120597152727040.0, | |
| "train_loss": 0.2836323574444317, | |
| "train_runtime": 7986.5453, | |
| "train_samples_per_second": 81.101, | |
| "train_steps_per_second": 0.159 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1266, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2120597152727040.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |