pbe-lora
/
gcp_models
/lora-logo_fix_full_deepseek7b_ds33i_lr_0.0002_alpha_1024_r_1024
/checkpoint-624
/trainer_state.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9807692307692308, | |
| "eval_steps": 78, | |
| "global_step": 624, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.633008095015655, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 2.3642923831939697, | |
| "eval_runtime": 33.2196, | |
| "eval_samples_per_second": 47.743, | |
| "eval_steps_per_second": 0.753, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.816570811549855, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3822, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.2176314207267582, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2088, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.5639737617555216, | |
| "learning_rate": 4e-05, | |
| "loss": 1.794, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.1571102035547312, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4568, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.04828656811459, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0793, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.9089343337123418, | |
| "learning_rate": 7e-05, | |
| "loss": 0.8952, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.6414378754303298, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6966, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.7026793020995574, | |
| "learning_rate": 9e-05, | |
| "loss": 0.667, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.6114674369831836, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6263, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.34886410731590795, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 0.6368, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3792869975162224, | |
| "learning_rate": 0.00012, | |
| "loss": 0.6412, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.35972404115397844, | |
| "learning_rate": 0.00013000000000000002, | |
| "loss": 0.5548, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.24576678580898173, | |
| "learning_rate": 0.00014, | |
| "loss": 0.5481, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.2718922412272493, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.5712, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.1738778643221334, | |
| "learning_rate": 0.00016, | |
| "loss": 0.5411, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.21499941994899305, | |
| "learning_rate": 0.00017, | |
| "loss": 0.5027, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.20489858306613132, | |
| "learning_rate": 0.00018, | |
| "loss": 0.5767, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.24056111577627579, | |
| "learning_rate": 0.00019, | |
| "loss": 0.5421, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.15268967552446508, | |
| "learning_rate": 0.0002, | |
| "loss": 0.506, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.17773072794431682, | |
| "learning_rate": 0.00019999941186316965, | |
| "loss": 0.5292, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.1330523638956641, | |
| "learning_rate": 0.0001999976474595967, | |
| "loss": 0.506, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.15247689444377824, | |
| "learning_rate": 0.00019999470681003533, | |
| "loss": 0.5204, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.14847842706334002, | |
| "learning_rate": 0.00019999058994907564, | |
| "loss": 0.5359, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.1300483595096366, | |
| "learning_rate": 0.00019998529692514318, | |
| "loss": 0.5155, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.1346403590192289, | |
| "learning_rate": 0.00019997882780049847, | |
| "loss": 0.5203, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.11581205785711204, | |
| "learning_rate": 0.00019997118265123597, | |
| "loss": 0.4835, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.11009362550902224, | |
| "learning_rate": 0.0001999623615672837, | |
| "loss": 0.4818, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.12262722388709488, | |
| "learning_rate": 0.00019995236465240166, | |
| "loss": 0.5387, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.11415360254903537, | |
| "learning_rate": 0.00019994119202418098, | |
| "loss": 0.4935, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.10625733392311923, | |
| "learning_rate": 0.00019992884381404228, | |
| "loss": 0.4954, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.10408231081274523, | |
| "learning_rate": 0.00019991532016723439, | |
| "loss": 0.4981, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.12116179169734417, | |
| "learning_rate": 0.0001999006212428323, | |
| "loss": 0.5182, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.09639005433005014, | |
| "learning_rate": 0.00019988474721373568, | |
| "loss": 0.5046, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.11341575332666715, | |
| "learning_rate": 0.00019986769826666652, | |
| "loss": 0.5032, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.10863502561913564, | |
| "learning_rate": 0.00019984947460216707, | |
| "loss": 0.4632, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.09725726160608462, | |
| "learning_rate": 0.00019983007643459755, | |
| "loss": 0.5136, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.1487734781898315, | |
| "learning_rate": 0.00019980950399213344, | |
| "loss": 0.4819, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.10134372163943337, | |
| "learning_rate": 0.00019978775751676298, | |
| "loss": 0.4583, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.13260067147290625, | |
| "learning_rate": 0.00019976483726428422, | |
| "loss": 0.4806, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.09313217373073629, | |
| "learning_rate": 0.0001997407435043021, | |
| "loss": 0.4804, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.1063366694244067, | |
| "learning_rate": 0.0001997154765202251, | |
| "loss": 0.4838, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.10118302188133363, | |
| "learning_rate": 0.0001996890366092622, | |
| "loss": 0.4945, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.08349800107684799, | |
| "learning_rate": 0.00019966142408241901, | |
| "loss": 0.4731, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.10305227185997523, | |
| "learning_rate": 0.00019963263926449444, | |
| "loss": 0.5103, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.1110744514147631, | |
| "learning_rate": 0.00019960268249407675, | |
| "loss": 0.477, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.09089637463027624, | |
| "learning_rate": 0.0001995715541235395, | |
| "loss": 0.5098, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.0984910569500165, | |
| "learning_rate": 0.00019953925451903756, | |
| "loss": 0.4858, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.09532986564810285, | |
| "learning_rate": 0.0001995057840605026, | |
| "loss": 0.481, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.09727596147605447, | |
| "learning_rate": 0.0001994711431416389, | |
| "loss": 0.4865, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.1007337964879899, | |
| "learning_rate": 0.00019943533216991842, | |
| "loss": 0.4935, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.09688005011223824, | |
| "learning_rate": 0.00019939835156657616, | |
| "loss": 0.4946, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.09613043891056636, | |
| "learning_rate": 0.00019936020176660523, | |
| "loss": 0.5456, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.0923212626633401, | |
| "learning_rate": 0.00019932088321875172, | |
| "loss": 0.4415, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.09433328455004313, | |
| "learning_rate": 0.0001992803963855093, | |
| "loss": 0.4549, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.08678947584579345, | |
| "learning_rate": 0.00019923874174311394, | |
| "loss": 0.4298, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.1007218414977894, | |
| "learning_rate": 0.00019919591978153825, | |
| "loss": 0.4923, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.08982692436561156, | |
| "learning_rate": 0.0001991519310044857, | |
| "loss": 0.4676, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.0966803088312702, | |
| "learning_rate": 0.00019910677592938457, | |
| "loss": 0.4852, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.10036826886716708, | |
| "learning_rate": 0.00019906045508738228, | |
| "loss": 0.4971, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.08759982957982607, | |
| "learning_rate": 0.00019901296902333858, | |
| "loss": 0.4427, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.0945857909391986, | |
| "learning_rate": 0.0001989643182958196, | |
| "loss": 0.4889, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.08970742144791523, | |
| "learning_rate": 0.00019891450347709098, | |
| "loss": 0.4653, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.0933078731551041, | |
| "learning_rate": 0.00019886352515311134, | |
| "loss": 0.5026, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.09508030017536839, | |
| "learning_rate": 0.00019881138392352529, | |
| "loss": 0.485, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.08532480173881492, | |
| "learning_rate": 0.0001987580804016563, | |
| "loss": 0.4466, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.0975360321136373, | |
| "learning_rate": 0.00019870361521449978, | |
| "loss": 0.5092, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.09452286182577921, | |
| "learning_rate": 0.00019864798900271532, | |
| "loss": 0.5005, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.08588180037396312, | |
| "learning_rate": 0.0001985912024206194, | |
| "loss": 0.4765, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.08939276891250153, | |
| "learning_rate": 0.0001985332561361776, | |
| "loss": 0.4809, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.09136596957761277, | |
| "learning_rate": 0.00019847415083099686, | |
| "loss": 0.4623, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.08058342031522184, | |
| "learning_rate": 0.00019841388720031727, | |
| "loss": 0.4581, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.08903152864251228, | |
| "learning_rate": 0.00019835246595300405, | |
| "loss": 0.4647, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.09267486555734437, | |
| "learning_rate": 0.00019828988781153917, | |
| "loss": 0.4747, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.07947015831997378, | |
| "learning_rate": 0.0001982261535120128, | |
| "loss": 0.4424, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.09075749183237583, | |
| "learning_rate": 0.00019816126380411476, | |
| "loss": 0.4879, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.08936961119418464, | |
| "learning_rate": 0.00019809521945112559, | |
| "loss": 0.4298, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.08916644651821774, | |
| "learning_rate": 0.00019802802122990758, | |
| "loss": 0.461, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.46426287293434143, | |
| "eval_runtime": 33.4798, | |
| "eval_samples_per_second": 47.372, | |
| "eval_steps_per_second": 0.747, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.0835418297057729, | |
| "learning_rate": 0.00019795966993089574, | |
| "loss": 0.4471, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.09426108761285606, | |
| "learning_rate": 0.00019789016635808837, | |
| "loss": 0.4862, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.09096422381199437, | |
| "learning_rate": 0.0001978195113290377, | |
| "loss": 0.4695, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.09464459953445767, | |
| "learning_rate": 0.00019774770567484022, | |
| "loss": 0.4449, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.0925267302225083, | |
| "learning_rate": 0.00019767475024012697, | |
| "loss": 0.4286, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.08720064599047793, | |
| "learning_rate": 0.00019760064588305345, | |
| "loss": 0.4565, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.1043647229323193, | |
| "learning_rate": 0.00019752539347528972, | |
| "loss": 0.4738, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.08653114383555988, | |
| "learning_rate": 0.00019744899390201006, | |
| "loss": 0.4455, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.10005509006457683, | |
| "learning_rate": 0.00019737144806188247, | |
| "loss": 0.4912, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.0871277710601868, | |
| "learning_rate": 0.0001972927568670583, | |
| "loss": 0.4652, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.08262178755414733, | |
| "learning_rate": 0.00019721292124316131, | |
| "loss": 0.4559, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.07806264355744019, | |
| "learning_rate": 0.00019713194212927696, | |
| "loss": 0.4387, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.10192076143799457, | |
| "learning_rate": 0.00019704982047794115, | |
| "loss": 0.5133, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.08488730550374232, | |
| "learning_rate": 0.00019696655725512933, | |
| "loss": 0.4511, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.0912147794808805, | |
| "learning_rate": 0.0001968821534402448, | |
| "loss": 0.4499, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.08092431706233014, | |
| "learning_rate": 0.00019679661002610743, | |
| "loss": 0.4402, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.09948161758362849, | |
| "learning_rate": 0.00019670992801894185, | |
| "loss": 0.4233, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.09749325023572918, | |
| "learning_rate": 0.00019662210843836574, | |
| "loss": 0.4647, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.09311349184019083, | |
| "learning_rate": 0.00019653315231737758, | |
| "loss": 0.4561, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.09958824700322794, | |
| "learning_rate": 0.0001964430607023449, | |
| "loss": 0.4743, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.10077251795709927, | |
| "learning_rate": 0.00019635183465299157, | |
| "loss": 0.4674, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.0943760778589781, | |
| "learning_rate": 0.00019625947524238563, | |
| "loss": 0.505, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.08850257609007128, | |
| "learning_rate": 0.00019616598355692643, | |
| "loss": 0.4527, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.08708609742539798, | |
| "learning_rate": 0.00019607136069633212, | |
| "loss": 0.4679, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.0976677935453425, | |
| "learning_rate": 0.00019597560777362644, | |
| "loss": 0.4584, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.07695630449416883, | |
| "learning_rate": 0.0001958787259151258, | |
| "loss": 0.4461, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.08078615967331339, | |
| "learning_rate": 0.00019578071626042602, | |
| "loss": 0.3908, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.09699025508232283, | |
| "learning_rate": 0.00019568157996238884, | |
| "loss": 0.4872, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.08993320572670008, | |
| "learning_rate": 0.00019558131818712838, | |
| "loss": 0.4613, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.09980754680232995, | |
| "learning_rate": 0.0001954799321139975, | |
| "loss": 0.4427, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.0934118440659259, | |
| "learning_rate": 0.00019537742293557396, | |
| "loss": 0.5052, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.10143523311961267, | |
| "learning_rate": 0.00019527379185764612, | |
| "loss": 0.4935, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.08720025082123407, | |
| "learning_rate": 0.0001951690400991991, | |
| "loss": 0.4528, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.08523385564801446, | |
| "learning_rate": 0.00019506316889240027, | |
| "loss": 0.4261, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.09263741912190988, | |
| "learning_rate": 0.0001949561794825847, | |
| "loss": 0.4476, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.0867556430119442, | |
| "learning_rate": 0.00019484807312824067, | |
| "loss": 0.4221, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.08185420060136846, | |
| "learning_rate": 0.0001947388511009947, | |
| "loss": 0.4192, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.10721864115182216, | |
| "learning_rate": 0.0001946285146855968, | |
| "loss": 0.4624, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.09013208478627394, | |
| "learning_rate": 0.00019451706517990513, | |
| "loss": 0.4451, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.11085560976399411, | |
| "learning_rate": 0.0001944045038948709, | |
| "loss": 0.4453, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.09297242157361825, | |
| "learning_rate": 0.00019429083215452276, | |
| "loss": 0.4496, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.1049146845321401, | |
| "learning_rate": 0.00019417605129595157, | |
| "loss": 0.4925, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.08752497535855448, | |
| "learning_rate": 0.0001940601626692943, | |
| "loss": 0.446, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.08097277374347386, | |
| "learning_rate": 0.0001939431676377183, | |
| "loss": 0.4251, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.08657657270480511, | |
| "learning_rate": 0.00019382506757740532, | |
| "loss": 0.4326, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.0868022553160936, | |
| "learning_rate": 0.0001937058638775353, | |
| "loss": 0.4646, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.08172973214382595, | |
| "learning_rate": 0.00019358555794027, | |
| "loss": 0.4261, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.10091452029925362, | |
| "learning_rate": 0.00019346415118073632, | |
| "loss": 0.4636, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.08167141374874119, | |
| "learning_rate": 0.00019334164502701016, | |
| "loss": 0.4372, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.09891138301504553, | |
| "learning_rate": 0.00019321804092009906, | |
| "loss": 0.4515, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.07393321210333707, | |
| "learning_rate": 0.0001930933403139256, | |
| "loss": 0.4223, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.09407907092073936, | |
| "learning_rate": 0.00019296754467531014, | |
| "loss": 0.4213, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.08953404431368055, | |
| "learning_rate": 0.00019284065548395363, | |
| "loss": 0.4371, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.09036795443129188, | |
| "learning_rate": 0.00019271267423242024, | |
| "loss": 0.4644, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.07966446157817311, | |
| "learning_rate": 0.00019258360242611973, | |
| "loss": 0.3846, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.0869354398561824, | |
| "learning_rate": 0.00019245344158328972, | |
| "loss": 0.4375, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.09126502542865338, | |
| "learning_rate": 0.00019232219323497797, | |
| "loss": 0.4923, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.08048817275182775, | |
| "learning_rate": 0.0001921898589250242, | |
| "loss": 0.4158, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.09441190744764841, | |
| "learning_rate": 0.00019205644021004202, | |
| "loss": 0.4299, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.10323532409312523, | |
| "learning_rate": 0.0001919219386594007, | |
| "loss": 0.4386, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.09603916746354269, | |
| "learning_rate": 0.0001917863558552065, | |
| "loss": 0.446, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.09362300078984864, | |
| "learning_rate": 0.00019164969339228422, | |
| "loss": 0.4204, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.08188922826700003, | |
| "learning_rate": 0.0001915119528781585, | |
| "loss": 0.4396, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.08879411229056809, | |
| "learning_rate": 0.00019137313593303463, | |
| "loss": 0.4135, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.08704843474305249, | |
| "learning_rate": 0.00019123324418977982, | |
| "loss": 0.4632, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.08715920220665294, | |
| "learning_rate": 0.00019109227929390378, | |
| "loss": 0.4605, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.09261336822711629, | |
| "learning_rate": 0.0001909502429035395, | |
| "loss": 0.4898, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.10047632096183474, | |
| "learning_rate": 0.00019080713668942356, | |
| "loss": 0.4482, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.09158304348559299, | |
| "learning_rate": 0.00019066296233487672, | |
| "loss": 0.5113, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.09415066554711225, | |
| "learning_rate": 0.00019051772153578389, | |
| "loss": 0.4923, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.08275762890385109, | |
| "learning_rate": 0.00019037141600057437, | |
| "loss": 0.4363, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.09162823424999712, | |
| "learning_rate": 0.00019022404745020163, | |
| "loss": 0.4384, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.09009536464050111, | |
| "learning_rate": 0.0001900756176181231, | |
| "loss": 0.4906, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.08039801657683925, | |
| "learning_rate": 0.00018992612825027976, | |
| "loss": 0.4107, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.09125094710472535, | |
| "learning_rate": 0.00018977558110507578, | |
| "loss": 0.4576, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.08539510103118245, | |
| "learning_rate": 0.0001896239779533575, | |
| "loss": 0.4179, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.08442693917503184, | |
| "learning_rate": 0.00018947132057839285, | |
| "loss": 0.4488, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.076915364755714, | |
| "learning_rate": 0.00018931761077585035, | |
| "loss": 0.409, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.43720224499702454, | |
| "eval_runtime": 33.5025, | |
| "eval_samples_per_second": 47.34, | |
| "eval_steps_per_second": 0.746, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.09850246011740704, | |
| "learning_rate": 0.00018916285035377794, | |
| "loss": 0.4501, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.09085206532943994, | |
| "learning_rate": 0.00018900704113258165, | |
| "loss": 0.3894, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.10238148525037052, | |
| "learning_rate": 0.00018885018494500436, | |
| "loss": 0.4627, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.07901425900899442, | |
| "learning_rate": 0.00018869228363610404, | |
| "loss": 0.428, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.0915805265840374, | |
| "learning_rate": 0.00018853333906323225, | |
| "loss": 0.438, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.09196124173902274, | |
| "learning_rate": 0.00018837335309601213, | |
| "loss": 0.4321, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.09226392067700642, | |
| "learning_rate": 0.0001882123276163164, | |
| "loss": 0.4532, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.10546138084239873, | |
| "learning_rate": 0.00018805026451824546, | |
| "loss": 0.4489, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.10316685636320119, | |
| "learning_rate": 0.0001878871657081048, | |
| "loss": 0.4711, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.09552407058071744, | |
| "learning_rate": 0.00018772303310438275, | |
| "loss": 0.3972, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.08979015721452269, | |
| "learning_rate": 0.00018755786863772792, | |
| "loss": 0.4493, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.07853760542106596, | |
| "learning_rate": 0.00018739167425092644, | |
| "loss": 0.4374, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.08633370802160478, | |
| "learning_rate": 0.00018722445189887907, | |
| "loss": 0.4432, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.08580166474340543, | |
| "learning_rate": 0.00018705620354857833, | |
| "loss": 0.4021, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.07908431206502199, | |
| "learning_rate": 0.00018688693117908521, | |
| "loss": 0.4676, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.08382980683178104, | |
| "learning_rate": 0.00018671663678150607, | |
| "loss": 0.4224, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.08818054859315155, | |
| "learning_rate": 0.00018654532235896898, | |
| "loss": 0.4255, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.09758651150656848, | |
| "learning_rate": 0.0001863729899266004, | |
| "loss": 0.4449, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.0854990868148432, | |
| "learning_rate": 0.00018619964151150137, | |
| "loss": 0.4309, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.09238156323868559, | |
| "learning_rate": 0.0001860252791527236, | |
| "loss": 0.4366, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.0982691841496931, | |
| "learning_rate": 0.0001858499049012456, | |
| "loss": 0.4412, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.08775652881305933, | |
| "learning_rate": 0.00018567352081994852, | |
| "loss": 0.4383, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.09164336741084732, | |
| "learning_rate": 0.00018549612898359182, | |
| "loss": 0.4442, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.09012714037522863, | |
| "learning_rate": 0.00018531773147878895, | |
| "loss": 0.4346, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.08547763352019036, | |
| "learning_rate": 0.0001851383304039828, | |
| "loss": 0.4203, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.09725124298762505, | |
| "learning_rate": 0.0001849579278694209, | |
| "loss": 0.4263, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.0898937780578857, | |
| "learning_rate": 0.0001847765259971308, | |
| "loss": 0.4148, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.09142961488740592, | |
| "learning_rate": 0.00018459412692089494, | |
| "loss": 0.435, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.09258456831452319, | |
| "learning_rate": 0.0001844107327862256, | |
| "loss": 0.4497, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.09277226798675627, | |
| "learning_rate": 0.0001842263457503397, | |
| "loss": 0.4492, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.08980220373103064, | |
| "learning_rate": 0.00018404096798213334, | |
| "loss": 0.421, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.08228805059725107, | |
| "learning_rate": 0.00018385460166215638, | |
| "loss": 0.4057, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.08924904202166163, | |
| "learning_rate": 0.00018366724898258676, | |
| "loss": 0.4496, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.08264577114117949, | |
| "learning_rate": 0.00018347891214720477, | |
| "loss": 0.4622, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.07774647266334128, | |
| "learning_rate": 0.0001832895933713669, | |
| "loss": 0.4171, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.0930136081519194, | |
| "learning_rate": 0.00018309929488198012, | |
| "loss": 0.4628, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.08104336613560284, | |
| "learning_rate": 0.0001829080189174754, | |
| "loss": 0.4345, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.07928202788411534, | |
| "learning_rate": 0.00018271576772778154, | |
| "loss": 0.4302, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.08860639410431671, | |
| "learning_rate": 0.00018252254357429862, | |
| "loss": 0.4147, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.09399022676320304, | |
| "learning_rate": 0.00018232834872987147, | |
| "loss": 0.3923, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.08691123357733746, | |
| "learning_rate": 0.00018213318547876298, | |
| "loss": 0.436, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.07809297083904465, | |
| "learning_rate": 0.00018193705611662696, | |
| "loss": 0.4073, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.10248225318688482, | |
| "learning_rate": 0.00018173996295048147, | |
| "loss": 0.4735, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.0815516912626354, | |
| "learning_rate": 0.0001815419082986815, | |
| "loss": 0.4222, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.08451837614394679, | |
| "learning_rate": 0.00018134289449089184, | |
| "loss": 0.4278, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.10254852614554928, | |
| "learning_rate": 0.00018114292386805936, | |
| "loss": 0.5034, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.09151211664093219, | |
| "learning_rate": 0.0001809419987823859, | |
| "loss": 0.3997, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.08363004725310991, | |
| "learning_rate": 0.00018074012159730032, | |
| "loss": 0.4249, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.09026541960271757, | |
| "learning_rate": 0.00018053729468743077, | |
| "loss": 0.3821, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.09415587839831263, | |
| "learning_rate": 0.00018033352043857675, | |
| "loss": 0.4253, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.09148986183443925, | |
| "learning_rate": 0.0001801288012476811, | |
| "loss": 0.4019, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.09250271599074991, | |
| "learning_rate": 0.00017992313952280172, | |
| "loss": 0.4238, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.08617245460377582, | |
| "learning_rate": 0.00017971653768308332, | |
| "loss": 0.4301, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.07940807825199672, | |
| "learning_rate": 0.00017950899815872892, | |
| "loss": 0.3954, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.08168451792509902, | |
| "learning_rate": 0.0001793005233909713, | |
| "loss": 0.4165, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.09077786407295318, | |
| "learning_rate": 0.00017909111583204422, | |
| "loss": 0.4375, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.0969599313060573, | |
| "learning_rate": 0.0001788807779451536, | |
| "loss": 0.415, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.08714615447380912, | |
| "learning_rate": 0.0001786695122044487, | |
| "loss": 0.4425, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.08784000210415467, | |
| "learning_rate": 0.00017845732109499275, | |
| "loss": 0.4081, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.08677394427128078, | |
| "learning_rate": 0.0001782442071127338, | |
| "loss": 0.3926, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.08466009336581957, | |
| "learning_rate": 0.00017803017276447558, | |
| "loss": 0.403, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.08707450940870536, | |
| "learning_rate": 0.0001778152205678477, | |
| "loss": 0.403, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.09376117520484097, | |
| "learning_rate": 0.00017759935305127628, | |
| "loss": 0.4167, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.08525932465209134, | |
| "learning_rate": 0.00017738257275395404, | |
| "loss": 0.4444, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.08754648544828071, | |
| "learning_rate": 0.0001771648822258105, | |
| "loss": 0.4187, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.08509030577612932, | |
| "learning_rate": 0.00017694628402748202, | |
| "loss": 0.4141, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.0955135794226628, | |
| "learning_rate": 0.00017672678073028163, | |
| "loss": 0.4678, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.09590616389302117, | |
| "learning_rate": 0.0001765063749161688, | |
| "loss": 0.4047, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.0841385595967817, | |
| "learning_rate": 0.00017628506917771906, | |
| "loss": 0.4741, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.08292169872496655, | |
| "learning_rate": 0.00017606286611809353, | |
| "loss": 0.4227, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.08230070579304821, | |
| "learning_rate": 0.0001758397683510083, | |
| "loss": 0.424, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.09436953994606803, | |
| "learning_rate": 0.00017561577850070355, | |
| "loss": 0.4383, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.08222009855401928, | |
| "learning_rate": 0.00017539089920191298, | |
| "loss": 0.3992, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.09428296981408717, | |
| "learning_rate": 0.00017516513309983253, | |
| "loss": 0.4092, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.09439450986780247, | |
| "learning_rate": 0.0001749384828500894, | |
| "loss": 0.4604, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.07753738910781505, | |
| "learning_rate": 0.00017471095111871074, | |
| "loss": 0.4051, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.08996751801792417, | |
| "learning_rate": 0.00017448254058209244, | |
| "loss": 0.4637, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.08753945608446327, | |
| "learning_rate": 0.0001742532539269674, | |
| "loss": 0.435, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.42369240522384644, | |
| "eval_runtime": 33.5099, | |
| "eval_samples_per_second": 47.329, | |
| "eval_steps_per_second": 0.746, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.08491927528525615, | |
| "learning_rate": 0.00017402309385037423, | |
| "loss": 0.4309, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.09093975600986907, | |
| "learning_rate": 0.00017379206305962526, | |
| "loss": 0.445, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.09091296648304192, | |
| "learning_rate": 0.0001735601642722748, | |
| "loss": 0.4521, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.07960232244853832, | |
| "learning_rate": 0.00017332740021608722, | |
| "loss": 0.413, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.07580258029924936, | |
| "learning_rate": 0.00017309377362900486, | |
| "loss": 0.401, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.08570325691035646, | |
| "learning_rate": 0.00017285928725911562, | |
| "loss": 0.4114, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.09156413198097288, | |
| "learning_rate": 0.00017262394386462101, | |
| "loss": 0.4671, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.08797742213516978, | |
| "learning_rate": 0.00017238774621380337, | |
| "loss": 0.4437, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.08658523182769413, | |
| "learning_rate": 0.0001721506970849934, | |
| "loss": 0.4471, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.08569755978628026, | |
| "learning_rate": 0.00017191279926653761, | |
| "loss": 0.4599, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.08178513083271026, | |
| "learning_rate": 0.00017167405555676535, | |
| "loss": 0.4199, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.07862195565363486, | |
| "learning_rate": 0.00017143446876395602, | |
| "loss": 0.4381, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.08029940317475186, | |
| "learning_rate": 0.00017119404170630594, | |
| "loss": 0.4315, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.08601348400483078, | |
| "learning_rate": 0.00017095277721189528, | |
| "loss": 0.4344, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.09056606390557032, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.4392, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.0835352549263579, | |
| "learning_rate": 0.00017046774727433222, | |
| "loss": 0.4, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.08676463043237778, | |
| "learning_rate": 0.00017022398753645916, | |
| "loss": 0.3797, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.09281014168116082, | |
| "learning_rate": 0.00016997940177231722, | |
| "loss": 0.4353, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.07641120749267657, | |
| "learning_rate": 0.0001697339928589043, | |
| "loss": 0.3745, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.09458214772825033, | |
| "learning_rate": 0.00016948776368290084, | |
| "loss": 0.418, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.08980687566433464, | |
| "learning_rate": 0.00016924071714063575, | |
| "loss": 0.4381, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.08888409003182665, | |
| "learning_rate": 0.00016899285613805246, | |
| "loss": 0.4129, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.08376748334000564, | |
| "learning_rate": 0.00016874418359067464, | |
| "loss": 0.4212, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.0826736962614022, | |
| "learning_rate": 0.00016849470242357196, | |
| "loss": 0.4181, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.09064355179385528, | |
| "learning_rate": 0.00016824441557132568, | |
| "loss": 0.4186, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.07601556267299625, | |
| "learning_rate": 0.00016799332597799413, | |
| "loss": 0.3922, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.08378338605597233, | |
| "learning_rate": 0.00016774143659707808, | |
| "loss": 0.4031, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.09187080571598095, | |
| "learning_rate": 0.00016748875039148593, | |
| "loss": 0.399, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.0764188339396186, | |
| "learning_rate": 0.000167235270333499, | |
| "loss": 0.4301, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.09348037312635721, | |
| "learning_rate": 0.0001669809994047364, | |
| "loss": 0.4169, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.08338935621699814, | |
| "learning_rate": 0.00016672594059612017, | |
| "loss": 0.4004, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.08778526295672542, | |
| "learning_rate": 0.0001664700969078398, | |
| "loss": 0.4434, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.07912322618976857, | |
| "learning_rate": 0.00016621347134931729, | |
| "loss": 0.4018, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.07903254700660213, | |
| "learning_rate": 0.00016595606693917142, | |
| "loss": 0.4363, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.08389331904902901, | |
| "learning_rate": 0.00016569788670518253, | |
| "loss": 0.4294, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.08943572895527772, | |
| "learning_rate": 0.00016543893368425666, | |
| "loss": 0.429, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.09056740587286256, | |
| "learning_rate": 0.00016517921092239, | |
| "loss": 0.4942, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.07612613686388393, | |
| "learning_rate": 0.00016491872147463306, | |
| "loss": 0.4159, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.08967898124850737, | |
| "learning_rate": 0.00016465746840505448, | |
| "loss": 0.4554, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.0790976623468464, | |
| "learning_rate": 0.00016439545478670543, | |
| "loss": 0.407, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.08438860840905067, | |
| "learning_rate": 0.000164132683701583, | |
| "loss": 0.4008, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.0825894950782118, | |
| "learning_rate": 0.00016386915824059427, | |
| "loss": 0.3925, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.0812291026751519, | |
| "learning_rate": 0.00016360488150351984, | |
| "loss": 0.4466, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.07845425366059137, | |
| "learning_rate": 0.00016333985659897735, | |
| "loss": 0.4216, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.07412695227025372, | |
| "learning_rate": 0.00016307408664438495, | |
| "loss": 0.4089, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.07941889981287002, | |
| "learning_rate": 0.00016280757476592466, | |
| "loss": 0.4299, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.08059777891665271, | |
| "learning_rate": 0.0001625403240985054, | |
| "loss": 0.4446, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.07142572498397551, | |
| "learning_rate": 0.0001622723377857265, | |
| "loss": 0.3781, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.07398014866198567, | |
| "learning_rate": 0.0001620036189798403, | |
| "loss": 0.417, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.08227299083979323, | |
| "learning_rate": 0.00016173417084171536, | |
| "loss": 0.4, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.07646152250401912, | |
| "learning_rate": 0.00016146399654079914, | |
| "loss": 0.4129, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.08134972637239814, | |
| "learning_rate": 0.00016119309925508078, | |
| "loss": 0.4518, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.07805947297559439, | |
| "learning_rate": 0.00016092148217105372, | |
| "loss": 0.4153, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.08357104345121277, | |
| "learning_rate": 0.0001606491484836782, | |
| "loss": 0.3958, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.07409448007652703, | |
| "learning_rate": 0.00016037610139634358, | |
| "loss": 0.4491, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.07884594742286537, | |
| "learning_rate": 0.00016010234412083086, | |
| "loss": 0.4072, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.08320707638630387, | |
| "learning_rate": 0.0001598278798772748, | |
| "loss": 0.4356, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.08395040457144812, | |
| "learning_rate": 0.00015955271189412598, | |
| "loss": 0.4186, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.08493307084152114, | |
| "learning_rate": 0.0001592768434081129, | |
| "loss": 0.4014, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.08662197506100384, | |
| "learning_rate": 0.00015900027766420393, | |
| "loss": 0.4225, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.07831181898700043, | |
| "learning_rate": 0.00015872301791556903, | |
| "loss": 0.3827, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.08025460451573849, | |
| "learning_rate": 0.00015844506742354164, | |
| "loss": 0.4293, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.080734017890353, | |
| "learning_rate": 0.00015816642945758012, | |
| "loss": 0.4313, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.07799154446273825, | |
| "learning_rate": 0.00015788710729522953, | |
| "loss": 0.4103, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.09159608958798666, | |
| "learning_rate": 0.00015760710422208288, | |
| "loss": 0.3966, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.08507253180089401, | |
| "learning_rate": 0.00015732642353174259, | |
| "loss": 0.4064, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.07764807504092833, | |
| "learning_rate": 0.00015704506852578165, | |
| "loss": 0.3771, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.08042977625326454, | |
| "learning_rate": 0.0001567630425137049, | |
| "loss": 0.4116, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.09438628596597481, | |
| "learning_rate": 0.00015648034881291003, | |
| "loss": 0.3588, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.07506130402709629, | |
| "learning_rate": 0.00015619699074864864, | |
| "loss": 0.3459, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.08428749562602489, | |
| "learning_rate": 0.00015591297165398692, | |
| "loss": 0.4058, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.08198875223317398, | |
| "learning_rate": 0.00015562829486976673, | |
| "loss": 0.3761, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.08398415875961499, | |
| "learning_rate": 0.0001553429637445661, | |
| "loss": 0.3879, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.09228760347704129, | |
| "learning_rate": 0.00015505698163465986, | |
| "loss": 0.4371, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.09295607207912268, | |
| "learning_rate": 0.00015477035190398025, | |
| "loss": 0.426, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.07278877741111027, | |
| "learning_rate": 0.00015448307792407734, | |
| "loss": 0.4111, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.08487168644675179, | |
| "learning_rate": 0.00015419516307407926, | |
| "loss": 0.4083, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.0961655276967335, | |
| "learning_rate": 0.00015390661074065256, | |
| "loss": 0.4599, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.41404005885124207, | |
| "eval_runtime": 33.546, | |
| "eval_samples_per_second": 47.278, | |
| "eval_steps_per_second": 0.745, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.07758121485765818, | |
| "learning_rate": 0.00015361742431796235, | |
| "loss": 0.4053, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.08223356264721718, | |
| "learning_rate": 0.00015332760720763232, | |
| "loss": 0.366, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.08038434641280369, | |
| "learning_rate": 0.00015303716281870483, | |
| "loss": 0.3675, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.08718063963284592, | |
| "learning_rate": 0.00015274609456760073, | |
| "loss": 0.3835, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.07673941299504924, | |
| "learning_rate": 0.00015245440587807917, | |
| "loss": 0.4009, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.08348547717410501, | |
| "learning_rate": 0.00015216210018119733, | |
| "loss": 0.4149, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.09255156337185536, | |
| "learning_rate": 0.00015186918091527024, | |
| "loss": 0.3486, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.07596028111813842, | |
| "learning_rate": 0.00015157565152583002, | |
| "loss": 0.3927, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.07544561934964225, | |
| "learning_rate": 0.00015128151546558554, | |
| "loss": 0.3924, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.08758514882743974, | |
| "learning_rate": 0.0001509867761943818, | |
| "loss": 0.3918, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.08474673476002027, | |
| "learning_rate": 0.00015069143717915927, | |
| "loss": 0.3487, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.09492895782795552, | |
| "learning_rate": 0.00015039550189391298, | |
| "loss": 0.4004, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.0757364119530662, | |
| "learning_rate": 0.0001500989738196517, | |
| "loss": 0.3515, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.07540437506266724, | |
| "learning_rate": 0.0001498018564443571, | |
| "loss": 0.3682, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.08268469021039043, | |
| "learning_rate": 0.0001495041532629426, | |
| "loss": 0.3956, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.07970392791793818, | |
| "learning_rate": 0.0001492058677772123, | |
| "loss": 0.3612, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.07954735587219544, | |
| "learning_rate": 0.00014890700349581986, | |
| "loss": 0.3441, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.08178968283177249, | |
| "learning_rate": 0.000148607563934227, | |
| "loss": 0.3844, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.09513679141795814, | |
| "learning_rate": 0.0001483075526146625, | |
| "loss": 0.3894, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.09348192232278749, | |
| "learning_rate": 0.00014800697306608044, | |
| "loss": 0.3936, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.08847535387270497, | |
| "learning_rate": 0.00014770582882411888, | |
| "loss": 0.3819, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.08002816944829381, | |
| "learning_rate": 0.00014740412343105828, | |
| "loss": 0.3262, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.08650040502949523, | |
| "learning_rate": 0.00014710186043577966, | |
| "loss": 0.3832, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.085677245926437, | |
| "learning_rate": 0.00014679904339372302, | |
| "loss": 0.3887, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.08896584850459943, | |
| "learning_rate": 0.00014649567586684547, | |
| "loss": 0.3803, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.0808079768115023, | |
| "learning_rate": 0.00014619176142357935, | |
| "loss": 0.3703, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.08383343128748613, | |
| "learning_rate": 0.00014588730363879014, | |
| "loss": 0.3698, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.08327275796504381, | |
| "learning_rate": 0.0001455823060937347, | |
| "loss": 0.3845, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.09433989901547166, | |
| "learning_rate": 0.00014527677237601865, | |
| "loss": 0.4287, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.08603421913268781, | |
| "learning_rate": 0.00014497070607955476, | |
| "loss": 0.3688, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.0857512096750318, | |
| "learning_rate": 0.00014466411080452018, | |
| "loss": 0.3835, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.08772603890023843, | |
| "learning_rate": 0.00014435699015731448, | |
| "loss": 0.3811, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.08762427343456393, | |
| "learning_rate": 0.00014404934775051682, | |
| "loss": 0.3723, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.08385715718692362, | |
| "learning_rate": 0.00014374118720284388, | |
| "loss": 0.3795, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.08747903826089705, | |
| "learning_rate": 0.00014343251213910698, | |
| "loss": 0.4006, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.09359760614007491, | |
| "learning_rate": 0.00014312332619016965, | |
| "loss": 0.3847, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.09196222914917314, | |
| "learning_rate": 0.00014281363299290466, | |
| "loss": 0.4156, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.08526413354780343, | |
| "learning_rate": 0.0001425034361901516, | |
| "loss": 0.3659, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.08051458773082706, | |
| "learning_rate": 0.00014219273943067375, | |
| "loss": 0.3548, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.08188096539772795, | |
| "learning_rate": 0.00014188154636911524, | |
| "loss": 0.3863, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.07832750063894078, | |
| "learning_rate": 0.00014156986066595807, | |
| "loss": 0.388, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.0884174663242081, | |
| "learning_rate": 0.0001412576859874791, | |
| "loss": 0.3722, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.0816717529958263, | |
| "learning_rate": 0.00014094502600570688, | |
| "loss": 0.3816, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.08873452250587119, | |
| "learning_rate": 0.00014063188439837832, | |
| "loss": 0.4085, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.0884893370241925, | |
| "learning_rate": 0.00014031826484889578, | |
| "loss": 0.3787, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.0930470847840911, | |
| "learning_rate": 0.0001400041710462833, | |
| "loss": 0.3843, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.09103324498558216, | |
| "learning_rate": 0.00013968960668514372, | |
| "loss": 0.3909, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.0834708928676139, | |
| "learning_rate": 0.0001393745754656146, | |
| "loss": 0.3453, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.08664145472278023, | |
| "learning_rate": 0.00013905908109332525, | |
| "loss": 0.3601, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.08004293017260566, | |
| "learning_rate": 0.00013874312727935292, | |
| "loss": 0.3538, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.09178725658915923, | |
| "learning_rate": 0.00013842671774017906, | |
| "loss": 0.3944, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.08848659530075587, | |
| "learning_rate": 0.00013810985619764572, | |
| "loss": 0.3862, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.09289158776492573, | |
| "learning_rate": 0.0001377925463789118, | |
| "loss": 0.4025, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.08759269817273997, | |
| "learning_rate": 0.00013747479201640914, | |
| "loss": 0.387, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.09039996402240508, | |
| "learning_rate": 0.00013715659684779855, | |
| "loss": 0.3932, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.08935600551589921, | |
| "learning_rate": 0.00013683796461592604, | |
| "loss": 0.4324, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.0808523939869351, | |
| "learning_rate": 0.00013651889906877865, | |
| "loss": 0.3789, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.08654623743012835, | |
| "learning_rate": 0.00013619940395944027, | |
| "loss": 0.3789, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.0852708344186728, | |
| "learning_rate": 0.00013587948304604781, | |
| "loss": 0.3839, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.08945078013815819, | |
| "learning_rate": 0.00013555914009174663, | |
| "loss": 0.3942, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.08899395672567659, | |
| "learning_rate": 0.00013523837886464664, | |
| "loss": 0.3675, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.08919685126750927, | |
| "learning_rate": 0.00013491720313777756, | |
| "loss": 0.4009, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.0931633835293962, | |
| "learning_rate": 0.00013459561668904496, | |
| "loss": 0.3922, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.09541278706635728, | |
| "learning_rate": 0.00013427362330118543, | |
| "loss": 0.3952, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.08473203780306135, | |
| "learning_rate": 0.00013395122676172248, | |
| "loss": 0.3592, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.09692789737028881, | |
| "learning_rate": 0.0001336284308629216, | |
| "loss": 0.3778, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.09671902578712055, | |
| "learning_rate": 0.00013330523940174602, | |
| "loss": 0.3894, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.08854209733839573, | |
| "learning_rate": 0.00013298165617981172, | |
| "loss": 0.4048, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.09139807289586219, | |
| "learning_rate": 0.00013265768500334287, | |
| "loss": 0.3618, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.09040599578560599, | |
| "learning_rate": 0.00013233332968312715, | |
| "loss": 0.368, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.09365590161356441, | |
| "learning_rate": 0.00013200859403447073, | |
| "loss": 0.4006, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.08489999558575993, | |
| "learning_rate": 0.0001316834818771535, | |
| "loss": 0.3705, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.08481449353398847, | |
| "learning_rate": 0.00013135799703538418, | |
| "loss": 0.3727, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.08679167831943593, | |
| "learning_rate": 0.00013103214333775521, | |
| "loss": 0.3769, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.08194941457743836, | |
| "learning_rate": 0.00013070592461719778, | |
| "loss": 0.3984, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.07855173035210027, | |
| "learning_rate": 0.00013037934471093682, | |
| "loss": 0.3829, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.08622752094954457, | |
| "learning_rate": 0.00013005240746044572, | |
| "loss": 0.3843, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.07636814629033357, | |
| "learning_rate": 0.00012972511671140125, | |
| "loss": 0.3508, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.4115259051322937, | |
| "eval_runtime": 33.5441, | |
| "eval_samples_per_second": 47.281, | |
| "eval_steps_per_second": 0.745, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.0809444660471662, | |
| "learning_rate": 0.0001293974763136383, | |
| "loss": 0.3875, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.08396899836630907, | |
| "learning_rate": 0.00012906949012110456, | |
| "loss": 0.3919, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.07689146207246444, | |
| "learning_rate": 0.0001287411619918152, | |
| "loss": 0.3888, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.08197508603617483, | |
| "learning_rate": 0.00012841249578780757, | |
| "loss": 0.382, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.0837673471450245, | |
| "learning_rate": 0.00012808349537509563, | |
| "loss": 0.3679, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.08391041326672148, | |
| "learning_rate": 0.00012775416462362457, | |
| "loss": 0.3596, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.08414466388203702, | |
| "learning_rate": 0.00012742450740722532, | |
| "loss": 0.3525, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.08670027563985289, | |
| "learning_rate": 0.00012709452760356884, | |
| "loss": 0.3478, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.087541296592948, | |
| "learning_rate": 0.00012676422909412068, | |
| "loss": 0.3953, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.09132304561707849, | |
| "learning_rate": 0.00012643361576409516, | |
| "loss": 0.3664, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.08253268413568746, | |
| "learning_rate": 0.00012610269150240986, | |
| "loss": 0.3958, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.09170497697457354, | |
| "learning_rate": 0.00012577146020163968, | |
| "loss": 0.3773, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.08277890956895972, | |
| "learning_rate": 0.00012543992575797115, | |
| "loss": 0.393, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.07813823409046901, | |
| "learning_rate": 0.00012510809207115666, | |
| "loss": 0.3601, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.08066835022584401, | |
| "learning_rate": 0.0001247759630444684, | |
| "loss": 0.358, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.08895746822331095, | |
| "learning_rate": 0.00012444354258465268, | |
| "loss": 0.3985, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.08441319881352181, | |
| "learning_rate": 0.00012411083460188378, | |
| "loss": 0.4069, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.08207581932824212, | |
| "learning_rate": 0.00012377784300971807, | |
| "loss": 0.3505, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.07718599286615756, | |
| "learning_rate": 0.00012344457172504795, | |
| "loss": 0.38, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.08569158514202131, | |
| "learning_rate": 0.0001231110246680558, | |
| "loss": 0.4123, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.083521236850263, | |
| "learning_rate": 0.00012277720576216771, | |
| "loss": 0.3594, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.07798617366576854, | |
| "learning_rate": 0.00012244311893400763, | |
| "loss": 0.3232, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.08515871529991537, | |
| "learning_rate": 0.00012210876811335087, | |
| "loss": 0.3896, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.0829298242081797, | |
| "learning_rate": 0.00012177415723307808, | |
| "loss": 0.3692, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.085247064973593, | |
| "learning_rate": 0.00012143929022912894, | |
| "loss": 0.3503, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.07866341017364432, | |
| "learning_rate": 0.00012110417104045575, | |
| "loss": 0.3442, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.08248913786466326, | |
| "learning_rate": 0.00012076880360897736, | |
| "loss": 0.352, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.08660560155421923, | |
| "learning_rate": 0.00012043319187953241, | |
| "loss": 0.3843, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.087398113382778, | |
| "learning_rate": 0.00012009733979983337, | |
| "loss": 0.3864, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.08113911551895618, | |
| "learning_rate": 0.00011976125132041974, | |
| "loss": 0.373, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.09448858236095908, | |
| "learning_rate": 0.00011942493039461184, | |
| "loss": 0.3788, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.08737127988100234, | |
| "learning_rate": 0.00011908838097846404, | |
| "loss": 0.3432, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.09001387163059323, | |
| "learning_rate": 0.0001187516070307186, | |
| "loss": 0.3825, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.081212438901607, | |
| "learning_rate": 0.00011841461251275867, | |
| "loss": 0.3912, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.08550952962804158, | |
| "learning_rate": 0.00011807740138856202, | |
| "loss": 0.3747, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.08478590045981083, | |
| "learning_rate": 0.00011773997762465429, | |
| "loss": 0.3797, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.08370976129934676, | |
| "learning_rate": 0.00011740234519006236, | |
| "loss": 0.3729, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.08620998143511623, | |
| "learning_rate": 0.0001170645080562676, | |
| "loss": 0.3851, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.09153129835313098, | |
| "learning_rate": 0.00011672647019715925, | |
| "loss": 0.4137, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.0856707072953288, | |
| "learning_rate": 0.00011638823558898762, | |
| "loss": 0.4016, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.08422697314632974, | |
| "learning_rate": 0.00011604980821031726, | |
| "loss": 0.3682, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.07838559200841783, | |
| "learning_rate": 0.00011571119204198037, | |
| "loss": 0.3389, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.08340487879640397, | |
| "learning_rate": 0.00011537239106702969, | |
| "loss": 0.3518, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.08963946253910657, | |
| "learning_rate": 0.00011503340927069189, | |
| "loss": 0.3683, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.08178119638049125, | |
| "learning_rate": 0.0001146942506403205, | |
| "loss": 0.3446, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.08160421218788426, | |
| "learning_rate": 0.00011435491916534919, | |
| "loss": 0.3545, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.08455597346280576, | |
| "learning_rate": 0.00011401541883724474, | |
| "loss": 0.3907, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.080653623131708, | |
| "learning_rate": 0.00011367575364946006, | |
| "loss": 0.3859, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.0864253933138142, | |
| "learning_rate": 0.00011333592759738729, | |
| "loss": 0.3701, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.0862649779427639, | |
| "learning_rate": 0.00011299594467831078, | |
| "loss": 0.3999, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.07995568486484875, | |
| "learning_rate": 0.00011265580889136007, | |
| "loss": 0.3696, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.08525208485461254, | |
| "learning_rate": 0.00011231552423746283, | |
| "loss": 0.3891, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.08765930623916067, | |
| "learning_rate": 0.00011197509471929779, | |
| "loss": 0.3585, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.08238738386911129, | |
| "learning_rate": 0.00011163452434124773, | |
| "loss": 0.3619, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.079749520560097, | |
| "learning_rate": 0.0001112938171093523, | |
| "loss": 0.3382, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.08502890619512629, | |
| "learning_rate": 0.00011095297703126093, | |
| "loss": 0.3518, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.09544368045601513, | |
| "learning_rate": 0.00011061200811618564, | |
| "loss": 0.4044, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.08933924439101468, | |
| "learning_rate": 0.00011027091437485404, | |
| "loss": 0.3365, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.0862897513618102, | |
| "learning_rate": 0.00010992969981946191, | |
| "loss": 0.4096, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.08745185153170981, | |
| "learning_rate": 0.00010958836846362621, | |
| "loss": 0.3849, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.08836641012545768, | |
| "learning_rate": 0.0001092469243223378, | |
| "loss": 0.3681, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.08534746378434717, | |
| "learning_rate": 0.00010890537141191417, | |
| "loss": 0.3996, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.08284534093310571, | |
| "learning_rate": 0.00010856371374995222, | |
| "loss": 0.4036, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.0923929694804189, | |
| "learning_rate": 0.00010822195535528106, | |
| "loss": 0.3838, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.08347914339644683, | |
| "learning_rate": 0.00010788010024791464, | |
| "loss": 0.3767, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.08327606836341962, | |
| "learning_rate": 0.00010753815244900458, | |
| "loss": 0.3562, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.07913176819327579, | |
| "learning_rate": 0.00010719611598079278, | |
| "loss": 0.3822, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.08663429548862385, | |
| "learning_rate": 0.00010685399486656406, | |
| "loss": 0.3945, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.08626421681660665, | |
| "learning_rate": 0.00010651179313059905, | |
| "loss": 0.3725, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.07415395342545632, | |
| "learning_rate": 0.00010616951479812658, | |
| "loss": 0.326, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.08030108488537366, | |
| "learning_rate": 0.00010582716389527658, | |
| "loss": 0.3916, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.08609428517232394, | |
| "learning_rate": 0.00010548474444903247, | |
| "loss": 0.3764, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.08923825147715536, | |
| "learning_rate": 0.0001051422604871841, | |
| "loss": 0.3809, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.07927467101094104, | |
| "learning_rate": 0.00010479971603828, | |
| "loss": 0.3545, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.08347594704086488, | |
| "learning_rate": 0.00010445711513158038, | |
| "loss": 0.4028, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.08416736705127845, | |
| "learning_rate": 0.00010411446179700943, | |
| "loss": 0.3746, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.08441695819126487, | |
| "learning_rate": 0.00010377176006510812, | |
| "loss": 0.3943, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.08584069901475365, | |
| "learning_rate": 0.00010342901396698659, | |
| "loss": 0.3497, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.4053783118724823, | |
| "eval_runtime": 33.5448, | |
| "eval_samples_per_second": 47.28, | |
| "eval_steps_per_second": 0.745, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.08945753178298847, | |
| "learning_rate": 0.00010308622753427692, | |
| "loss": 0.4019, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.0828320493655375, | |
| "learning_rate": 0.00010274340479908568, | |
| "loss": 0.349, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.08295310686114485, | |
| "learning_rate": 0.0001024005497939464, | |
| "loss": 0.3932, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.08217702979762125, | |
| "learning_rate": 0.00010205766655177215, | |
| "loss": 0.3521, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.08259346713891956, | |
| "learning_rate": 0.00010171475910580824, | |
| "loss": 0.3959, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.0747149656482954, | |
| "learning_rate": 0.00010137183148958463, | |
| "loss": 0.3405, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.08793468165863222, | |
| "learning_rate": 0.00010102888773686852, | |
| "loss": 0.3983, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.07534080833533163, | |
| "learning_rate": 0.00010068593188161697, | |
| "loss": 0.3667, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.07866167273184164, | |
| "learning_rate": 0.00010034296795792937, | |
| "loss": 0.3651, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.07936943579586331, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3309, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.07649248763496863, | |
| "learning_rate": 9.965703204207066e-05, | |
| "loss": 0.3584, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.07966092218096205, | |
| "learning_rate": 9.931406811838308e-05, | |
| "loss": 0.3418, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.08211647159549972, | |
| "learning_rate": 9.89711122631315e-05, | |
| "loss": 0.3498, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.09103960818175702, | |
| "learning_rate": 9.862816851041541e-05, | |
| "loss": 0.3964, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.08814536635875789, | |
| "learning_rate": 9.828524089419179e-05, | |
| "loss": 0.361, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.08545214784234044, | |
| "learning_rate": 9.79423334482279e-05, | |
| "loss": 0.3528, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.09447243117707267, | |
| "learning_rate": 9.759945020605363e-05, | |
| "loss": 0.3625, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.0898215847039755, | |
| "learning_rate": 9.725659520091433e-05, | |
| "loss": 0.3795, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.08252469729442688, | |
| "learning_rate": 9.691377246572309e-05, | |
| "loss": 0.3687, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.08961836906933171, | |
| "learning_rate": 9.657098603301346e-05, | |
| "loss": 0.4256, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.08162184857550933, | |
| "learning_rate": 9.622823993489193e-05, | |
| "loss": 0.3694, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.08828547581542719, | |
| "learning_rate": 9.588553820299056e-05, | |
| "loss": 0.356, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.08007529300240984, | |
| "learning_rate": 9.554288486841963e-05, | |
| "loss": 0.3548, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.08916015854801038, | |
| "learning_rate": 9.520028396172003e-05, | |
| "loss": 0.3759, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.08216240876530229, | |
| "learning_rate": 9.485773951281595e-05, | |
| "loss": 0.3654, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.0850945715249927, | |
| "learning_rate": 9.451525555096753e-05, | |
| "loss": 0.3938, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.08215831951104548, | |
| "learning_rate": 9.417283610472344e-05, | |
| "loss": 0.3672, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.08901479012042726, | |
| "learning_rate": 9.383048520187344e-05, | |
| "loss": 0.4173, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.08086296467483917, | |
| "learning_rate": 9.348820686940099e-05, | |
| "loss": 0.3307, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.08623393096107944, | |
| "learning_rate": 9.314600513343595e-05, | |
| "loss": 0.3798, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.08102468716731086, | |
| "learning_rate": 9.280388401920724e-05, | |
| "loss": 0.3676, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.07823837220026066, | |
| "learning_rate": 9.246184755099545e-05, | |
| "loss": 0.3547, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.08424799320744991, | |
| "learning_rate": 9.211989975208538e-05, | |
| "loss": 0.3642, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.07691140217730688, | |
| "learning_rate": 9.177804464471898e-05, | |
| "loss": 0.3303, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.08027290288371244, | |
| "learning_rate": 9.143628625004779e-05, | |
| "loss": 0.3744, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.08628613833994034, | |
| "learning_rate": 9.109462858808586e-05, | |
| "loss": 0.3573, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.07905849414598452, | |
| "learning_rate": 9.075307567766222e-05, | |
| "loss": 0.3453, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.09290423960007008, | |
| "learning_rate": 9.041163153637381e-05, | |
| "loss": 0.411, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.09367738335315824, | |
| "learning_rate": 9.00703001805381e-05, | |
| "loss": 0.3661, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.08714316743298807, | |
| "learning_rate": 8.972908562514598e-05, | |
| "loss": 0.3781, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.09228625624874041, | |
| "learning_rate": 8.93879918838144e-05, | |
| "loss": 0.3711, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.08076977349444371, | |
| "learning_rate": 8.904702296873912e-05, | |
| "loss": 0.36, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.07767952332800128, | |
| "learning_rate": 8.870618289064776e-05, | |
| "loss": 0.3662, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.08231174390314516, | |
| "learning_rate": 8.836547565875227e-05, | |
| "loss": 0.3706, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.08482748819787773, | |
| "learning_rate": 8.802490528070223e-05, | |
| "loss": 0.3767, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.07732356993077102, | |
| "learning_rate": 8.76844757625372e-05, | |
| "loss": 0.3731, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.07825246188294603, | |
| "learning_rate": 8.734419110863996e-05, | |
| "loss": 0.3534, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.08215312759354138, | |
| "learning_rate": 8.70040553216892e-05, | |
| "loss": 0.3719, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.08895284590651382, | |
| "learning_rate": 8.666407240261272e-05, | |
| "loss": 0.3785, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.08026649834928365, | |
| "learning_rate": 8.632424635053997e-05, | |
| "loss": 0.3688, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.08467076614844896, | |
| "learning_rate": 8.598458116275531e-05, | |
| "loss": 0.3569, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.08098159504814209, | |
| "learning_rate": 8.564508083465079e-05, | |
| "loss": 0.3412, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.08784637131795085, | |
| "learning_rate": 8.530574935967952e-05, | |
| "loss": 0.3814, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.08784608507106204, | |
| "learning_rate": 8.496659072930813e-05, | |
| "loss": 0.3427, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.08448755540817741, | |
| "learning_rate": 8.462760893297033e-05, | |
| "loss": 0.3833, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.07399808555217596, | |
| "learning_rate": 8.428880795801965e-05, | |
| "loss": 0.3372, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.08475486658532157, | |
| "learning_rate": 8.395019178968274e-05, | |
| "loss": 0.3746, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.08362409194761905, | |
| "learning_rate": 8.36117644110124e-05, | |
| "loss": 0.369, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.07623921376685286, | |
| "learning_rate": 8.327352980284076e-05, | |
| "loss": 0.3686, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.08204309911526386, | |
| "learning_rate": 8.293549194373243e-05, | |
| "loss": 0.3845, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.08422115127877011, | |
| "learning_rate": 8.259765480993766e-05, | |
| "loss": 0.3646, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.07456208797678338, | |
| "learning_rate": 8.226002237534572e-05, | |
| "loss": 0.348, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.07637236265418358, | |
| "learning_rate": 8.192259861143801e-05, | |
| "loss": 0.3376, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.07884815031647592, | |
| "learning_rate": 8.158538748724139e-05, | |
| "loss": 0.3544, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.0823273169453789, | |
| "learning_rate": 8.124839296928144e-05, | |
| "loss": 0.3542, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.0882709776759046, | |
| "learning_rate": 8.091161902153595e-05, | |
| "loss": 0.3914, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.08326330415190343, | |
| "learning_rate": 8.057506960538819e-05, | |
| "loss": 0.349, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.08165350577392554, | |
| "learning_rate": 8.023874867958027e-05, | |
| "loss": 0.3819, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.08647925667576956, | |
| "learning_rate": 7.990266020016667e-05, | |
| "loss": 0.3829, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.08658194845476587, | |
| "learning_rate": 7.95668081204676e-05, | |
| "loss": 0.3919, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.08940687420649465, | |
| "learning_rate": 7.923119639102268e-05, | |
| "loss": 0.3348, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.07506268434795704, | |
| "learning_rate": 7.889582895954427e-05, | |
| "loss": 0.3327, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.08091710950398458, | |
| "learning_rate": 7.85607097708711e-05, | |
| "loss": 0.3426, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.08612720996775053, | |
| "learning_rate": 7.822584276692191e-05, | |
| "loss": 0.3782, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.08779609683089609, | |
| "learning_rate": 7.789123188664914e-05, | |
| "loss": 0.4145, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.08603765330333539, | |
| "learning_rate": 7.755688106599241e-05, | |
| "loss": 0.4015, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.0809985592698887, | |
| "learning_rate": 7.722279423783231e-05, | |
| "loss": 0.3713, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.08384828852946705, | |
| "learning_rate": 7.688897533194424e-05, | |
| "loss": 0.3766, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.3992162346839905, | |
| "eval_runtime": 33.5487, | |
| "eval_samples_per_second": 47.274, | |
| "eval_steps_per_second": 0.745, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.08208751735526602, | |
| "learning_rate": 7.655542827495204e-05, | |
| "loss": 0.3758, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.08275376601001344, | |
| "learning_rate": 7.622215699028196e-05, | |
| "loss": 0.3894, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.07677668019262486, | |
| "learning_rate": 7.588916539811626e-05, | |
| "loss": 0.3394, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.08528626571759709, | |
| "learning_rate": 7.555645741534736e-05, | |
| "loss": 0.3733, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.07682844993362777, | |
| "learning_rate": 7.52240369555316e-05, | |
| "loss": 0.3297, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.08254962011426915, | |
| "learning_rate": 7.489190792884338e-05, | |
| "loss": 0.3729, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.08279433568540118, | |
| "learning_rate": 7.456007424202886e-05, | |
| "loss": 0.368, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.08239076375235224, | |
| "learning_rate": 7.422853979836034e-05, | |
| "loss": 0.3683, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.08074829781125165, | |
| "learning_rate": 7.389730849759017e-05, | |
| "loss": 0.3433, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.09009191199117163, | |
| "learning_rate": 7.356638423590485e-05, | |
| "loss": 0.3837, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.07663429334230384, | |
| "learning_rate": 7.323577090587935e-05, | |
| "loss": 0.3204, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.07659376209251934, | |
| "learning_rate": 7.290547239643117e-05, | |
| "loss": 0.3545, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.08393527691649585, | |
| "learning_rate": 7.257549259277472e-05, | |
| "loss": 0.3615, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.07654043738541885, | |
| "learning_rate": 7.224583537637544e-05, | |
| "loss": 0.3438, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.0855040810077099, | |
| "learning_rate": 7.19165046249044e-05, | |
| "loss": 0.3886, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.07394102171264305, | |
| "learning_rate": 7.158750421219244e-05, | |
| "loss": 0.3528, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.0752877744473657, | |
| "learning_rate": 7.125883800818482e-05, | |
| "loss": 0.337, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.08631346025664761, | |
| "learning_rate": 7.093050987889547e-05, | |
| "loss": 0.3887, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.08146921694387252, | |
| "learning_rate": 7.06025236863617e-05, | |
| "loss": 0.362, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.07692347393411994, | |
| "learning_rate": 7.027488328859876e-05, | |
| "loss": 0.3619, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.07836704904967878, | |
| "learning_rate": 6.994759253955431e-05, | |
| "loss": 0.3415, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.0819627356507886, | |
| "learning_rate": 6.96206552890632e-05, | |
| "loss": 0.3629, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.08305351738100551, | |
| "learning_rate": 6.929407538280222e-05, | |
| "loss": 0.3737, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.08603630833715, | |
| "learning_rate": 6.896785666224481e-05, | |
| "loss": 0.3839, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.0854318437622499, | |
| "learning_rate": 6.864200296461584e-05, | |
| "loss": 0.3788, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.08747940555530277, | |
| "learning_rate": 6.831651812284652e-05, | |
| "loss": 0.3812, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.08517528220636034, | |
| "learning_rate": 6.799140596552928e-05, | |
| "loss": 0.3484, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.07917280285775082, | |
| "learning_rate": 6.766667031687286e-05, | |
| "loss": 0.3627, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.0831711984325957, | |
| "learning_rate": 6.734231499665717e-05, | |
| "loss": 0.3799, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.08525123821422767, | |
| "learning_rate": 6.701834382018832e-05, | |
| "loss": 0.3886, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.08564117668654835, | |
| "learning_rate": 6.669476059825401e-05, | |
| "loss": 0.3941, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.07657244396347064, | |
| "learning_rate": 6.637156913707839e-05, | |
| "loss": 0.3082, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.07369906343987707, | |
| "learning_rate": 6.604877323827755e-05, | |
| "loss": 0.3367, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.07685987309652949, | |
| "learning_rate": 6.572637669881458e-05, | |
| "loss": 0.3461, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.08408366477522602, | |
| "learning_rate": 6.540438331095509e-05, | |
| "loss": 0.376, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.08229812285391792, | |
| "learning_rate": 6.508279686222243e-05, | |
| "loss": 0.3482, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.08535318973220925, | |
| "learning_rate": 6.47616211353534e-05, | |
| "loss": 0.3617, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.08668075816149512, | |
| "learning_rate": 6.444085990825338e-05, | |
| "loss": 0.3467, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.08819480288247905, | |
| "learning_rate": 6.412051695395225e-05, | |
| "loss": 0.3657, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.08193324399289215, | |
| "learning_rate": 6.380059604055974e-05, | |
| "loss": 0.3672, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.08650615424798638, | |
| "learning_rate": 6.34811009312214e-05, | |
| "loss": 0.3957, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.08219994784775382, | |
| "learning_rate": 6.316203538407397e-05, | |
| "loss": 0.3662, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.07904997956893513, | |
| "learning_rate": 6.284340315220146e-05, | |
| "loss": 0.3458, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.07475380586361358, | |
| "learning_rate": 6.252520798359092e-05, | |
| "loss": 0.3188, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.08035109677919272, | |
| "learning_rate": 6.22074536210882e-05, | |
| "loss": 0.3711, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.07595095018884261, | |
| "learning_rate": 6.18901438023543e-05, | |
| "loss": 0.33, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.08607067280029385, | |
| "learning_rate": 6.157328225982097e-05, | |
| "loss": 0.4231, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.0847327549879939, | |
| "learning_rate": 6.125687272064713e-05, | |
| "loss": 0.3647, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.0784138287678255, | |
| "learning_rate": 6.0940918906674726e-05, | |
| "loss": 0.3641, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.07936682786699523, | |
| "learning_rate": 6.0625424534385425e-05, | |
| "loss": 0.3733, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.07891977284006456, | |
| "learning_rate": 6.031039331485631e-05, | |
| "loss": 0.3733, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.07595542881011737, | |
| "learning_rate": 5.9995828953716695e-05, | |
| "loss": 0.313, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.07707374312803282, | |
| "learning_rate": 5.9681735151104265e-05, | |
| "loss": 0.3676, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.07702573240958661, | |
| "learning_rate": 5.936811560162169e-05, | |
| "loss": 0.3791, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.07398091972302649, | |
| "learning_rate": 5.905497399429316e-05, | |
| "loss": 0.3315, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.07120728701527194, | |
| "learning_rate": 5.87423140125209e-05, | |
| "loss": 0.3263, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.08089583411142236, | |
| "learning_rate": 5.8430139334041966e-05, | |
| "loss": 0.3998, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.07970174867735058, | |
| "learning_rate": 5.811845363088477e-05, | |
| "loss": 0.3812, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.07720514217490725, | |
| "learning_rate": 5.780726056932629e-05, | |
| "loss": 0.3317, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.07871542981677206, | |
| "learning_rate": 5.749656380984844e-05, | |
| "loss": 0.3481, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.0821430432266814, | |
| "learning_rate": 5.718636700709537e-05, | |
| "loss": 0.3838, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.07802206649408414, | |
| "learning_rate": 5.687667380983037e-05, | |
| "loss": 0.3521, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.08131025423053755, | |
| "learning_rate": 5.656748786089303e-05, | |
| "loss": 0.3565, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.07835593959108345, | |
| "learning_rate": 5.625881279715615e-05, | |
| "loss": 0.3198, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.08739812670289539, | |
| "learning_rate": 5.59506522494832e-05, | |
| "loss": 0.3665, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.07933056907108374, | |
| "learning_rate": 5.5643009842685554e-05, | |
| "loss": 0.3275, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.08574415804221376, | |
| "learning_rate": 5.5335889195479785e-05, | |
| "loss": 0.3497, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.08414060178683784, | |
| "learning_rate": 5.502929392044528e-05, | |
| "loss": 0.3405, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.08696493256713488, | |
| "learning_rate": 5.472322762398139e-05, | |
| "loss": 0.3686, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.08507397684470745, | |
| "learning_rate": 5.4417693906265365e-05, | |
| "loss": 0.3696, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.08993213390389453, | |
| "learning_rate": 5.411269636120984e-05, | |
| "loss": 0.3851, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.08254573620374057, | |
| "learning_rate": 5.380823857642069e-05, | |
| "loss": 0.376, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.08060182313136507, | |
| "learning_rate": 5.350432413315455e-05, | |
| "loss": 0.3223, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.0902249552198533, | |
| "learning_rate": 5.3200956606277006e-05, | |
| "loss": 0.3669, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.08619047719375636, | |
| "learning_rate": 5.289813956422036e-05, | |
| "loss": 0.3432, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.07999040870242333, | |
| "learning_rate": 5.259587656894174e-05, | |
| "loss": 0.341, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.08462960761259652, | |
| "learning_rate": 5.2294171175881125e-05, | |
| "loss": 0.3939, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.08755472687796698, | |
| "learning_rate": 5.199302693391959e-05, | |
| "loss": 0.3595, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.3928658664226532, | |
| "eval_runtime": 33.5347, | |
| "eval_samples_per_second": 47.294, | |
| "eval_steps_per_second": 0.745, | |
| "step": 624 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 936, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 312, | |
| "total_flos": 3.9528329623277404e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |