| { | |
| "best_metric": 0.4453, | |
| "best_model_checkpoint": "runs/legis-qwen_2-5-7b-valid/checkpoint-2000", | |
| "epoch": 1.0, | |
| "eval_steps": 25, | |
| "global_step": 2353, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010624734381640459, | |
| "grad_norm": 1.3824252776738029, | |
| "learning_rate": 2.1186440677966103e-05, | |
| "loss": 0.9908, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010624734381640459, | |
| "eval_loss": 0.8797302842140198, | |
| "eval_runtime": 13.696, | |
| "eval_samples_per_second": 1.314, | |
| "eval_steps_per_second": 0.657, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.021249468763280918, | |
| "grad_norm": 0.5848728162132136, | |
| "learning_rate": 4.2372881355932206e-05, | |
| "loss": 0.7379, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021249468763280918, | |
| "eval_loss": 0.7652693390846252, | |
| "eval_runtime": 13.4778, | |
| "eval_samples_per_second": 1.336, | |
| "eval_steps_per_second": 0.668, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03187420314492138, | |
| "grad_norm": 0.4083536495349737, | |
| "learning_rate": 6.35593220338983e-05, | |
| "loss": 0.6739, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03187420314492138, | |
| "eval_loss": 0.7201825976371765, | |
| "eval_runtime": 13.6633, | |
| "eval_samples_per_second": 1.317, | |
| "eval_steps_per_second": 0.659, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.042498937526561836, | |
| "grad_norm": 0.40319269494868826, | |
| "learning_rate": 8.474576271186441e-05, | |
| "loss": 0.6333, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.042498937526561836, | |
| "eval_loss": 0.6928180456161499, | |
| "eval_runtime": 13.5603, | |
| "eval_samples_per_second": 1.327, | |
| "eval_steps_per_second": 0.664, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.053123671908202295, | |
| "grad_norm": 0.45146499021091163, | |
| "learning_rate": 0.00010593220338983052, | |
| "loss": 0.6138, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.053123671908202295, | |
| "eval_loss": 0.6759499311447144, | |
| "eval_runtime": 13.7103, | |
| "eval_samples_per_second": 1.313, | |
| "eval_steps_per_second": 0.656, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06374840628984275, | |
| "grad_norm": 0.4438422289624626, | |
| "learning_rate": 0.0001271186440677966, | |
| "loss": 0.6053, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06374840628984275, | |
| "eval_loss": 0.6635024547576904, | |
| "eval_runtime": 13.5819, | |
| "eval_samples_per_second": 1.325, | |
| "eval_steps_per_second": 0.663, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0743731406714832, | |
| "grad_norm": 0.4272726064498105, | |
| "learning_rate": 0.00014830508474576273, | |
| "loss": 0.5893, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.0743731406714832, | |
| "eval_loss": 0.6542551517486572, | |
| "eval_runtime": 13.5533, | |
| "eval_samples_per_second": 1.328, | |
| "eval_steps_per_second": 0.664, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.08499787505312367, | |
| "grad_norm": 0.40810966129419957, | |
| "learning_rate": 0.00016949152542372882, | |
| "loss": 0.5912, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08499787505312367, | |
| "eval_loss": 0.6452566385269165, | |
| "eval_runtime": 13.556, | |
| "eval_samples_per_second": 1.328, | |
| "eval_steps_per_second": 0.664, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.09562260943476412, | |
| "grad_norm": 0.317957905950078, | |
| "learning_rate": 0.00019067796610169492, | |
| "loss": 0.588, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.09562260943476412, | |
| "eval_loss": 0.6399930119514465, | |
| "eval_runtime": 13.7279, | |
| "eval_samples_per_second": 1.311, | |
| "eval_steps_per_second": 0.656, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.10624734381640459, | |
| "grad_norm": 0.33193624291905227, | |
| "learning_rate": 0.00019997841915310352, | |
| "loss": 0.5738, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.10624734381640459, | |
| "eval_loss": 0.635059654712677, | |
| "eval_runtime": 13.7296, | |
| "eval_samples_per_second": 1.311, | |
| "eval_steps_per_second": 0.656, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.11687207819804504, | |
| "grad_norm": 0.2478181869132683, | |
| "learning_rate": 0.0001998325689426475, | |
| "loss": 0.5511, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.11687207819804504, | |
| "eval_loss": 0.6286189556121826, | |
| "eval_runtime": 13.6848, | |
| "eval_samples_per_second": 1.315, | |
| "eval_steps_per_second": 0.658, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.1274968125796855, | |
| "grad_norm": 0.29097194553722133, | |
| "learning_rate": 0.00019954932703763562, | |
| "loss": 0.5663, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1274968125796855, | |
| "eval_loss": 0.6214559078216553, | |
| "eval_runtime": 13.6708, | |
| "eval_samples_per_second": 1.317, | |
| "eval_steps_per_second": 0.658, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.13812154696132597, | |
| "grad_norm": 0.2608796359844066, | |
| "learning_rate": 0.00019912908324157293, | |
| "loss": 0.5544, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.13812154696132597, | |
| "eval_loss": 0.615837812423706, | |
| "eval_runtime": 13.627, | |
| "eval_samples_per_second": 1.321, | |
| "eval_steps_per_second": 0.66, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.1487462813429664, | |
| "grad_norm": 0.28941490682658677, | |
| "learning_rate": 0.00019857241590286702, | |
| "loss": 0.5553, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1487462813429664, | |
| "eval_loss": 0.6113396286964417, | |
| "eval_runtime": 13.5958, | |
| "eval_samples_per_second": 1.324, | |
| "eval_steps_per_second": 0.662, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.15937101572460688, | |
| "grad_norm": 0.30035371415468154, | |
| "learning_rate": 0.00019788009111889248, | |
| "loss": 0.5665, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.15937101572460688, | |
| "eval_loss": 0.6078417301177979, | |
| "eval_runtime": 13.54, | |
| "eval_samples_per_second": 1.329, | |
| "eval_steps_per_second": 0.665, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.16999575010624735, | |
| "grad_norm": 0.2835386050077782, | |
| "learning_rate": 0.0001970530616816716, | |
| "loss": 0.5429, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.16999575010624735, | |
| "eval_loss": 0.6027636528015137, | |
| "eval_runtime": 13.735, | |
| "eval_samples_per_second": 1.311, | |
| "eval_steps_per_second": 0.655, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1806204844878878, | |
| "grad_norm": 0.22659224554756538, | |
| "learning_rate": 0.00019609246576662184, | |
| "loss": 0.5532, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.1806204844878878, | |
| "eval_loss": 0.5958096981048584, | |
| "eval_runtime": 13.671, | |
| "eval_samples_per_second": 1.317, | |
| "eval_steps_per_second": 0.658, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.19124521886952825, | |
| "grad_norm": 0.1914569343973938, | |
| "learning_rate": 0.00019499962536617454, | |
| "loss": 0.5554, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.19124521886952825, | |
| "eval_loss": 0.5921241044998169, | |
| "eval_runtime": 13.7061, | |
| "eval_samples_per_second": 1.313, | |
| "eval_steps_per_second": 0.657, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.20186995325116872, | |
| "grad_norm": 0.23443045180153105, | |
| "learning_rate": 0.00019377604447042127, | |
| "loss": 0.5428, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.20186995325116872, | |
| "eval_loss": 0.5899159908294678, | |
| "eval_runtime": 13.5568, | |
| "eval_samples_per_second": 1.328, | |
| "eval_steps_per_second": 0.664, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.21249468763280918, | |
| "grad_norm": 0.2161122041133258, | |
| "learning_rate": 0.00019242340699729047, | |
| "loss": 0.5514, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.21249468763280918, | |
| "eval_loss": 0.5880197882652283, | |
| "eval_runtime": 13.624, | |
| "eval_samples_per_second": 1.321, | |
| "eval_steps_per_second": 0.661, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.22311942201444965, | |
| "grad_norm": 0.2070053292137905, | |
| "learning_rate": 0.0001909435744751043, | |
| "loss": 0.5209, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.22311942201444965, | |
| "eval_loss": 0.5879865884780884, | |
| "eval_runtime": 13.7028, | |
| "eval_samples_per_second": 1.314, | |
| "eval_steps_per_second": 0.657, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.23374415639609009, | |
| "grad_norm": 0.23609205770661978, | |
| "learning_rate": 0.0001893385834807037, | |
| "loss": 0.5208, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.23374415639609009, | |
| "eval_loss": 0.5853844881057739, | |
| "eval_runtime": 13.7354, | |
| "eval_samples_per_second": 1.31, | |
| "eval_steps_per_second": 0.655, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.24436889077773055, | |
| "grad_norm": 0.19954431376676118, | |
| "learning_rate": 0.0001876106428366683, | |
| "loss": 0.5196, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.24436889077773055, | |
| "eval_loss": 0.5810511112213135, | |
| "eval_runtime": 13.5807, | |
| "eval_samples_per_second": 1.325, | |
| "eval_steps_per_second": 0.663, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.254993625159371, | |
| "grad_norm": 0.17831651642966287, | |
| "learning_rate": 0.00018576213057148815, | |
| "loss": 0.5278, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.254993625159371, | |
| "eval_loss": 0.5783408880233765, | |
| "eval_runtime": 13.6189, | |
| "eval_samples_per_second": 1.322, | |
| "eval_steps_per_second": 0.661, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2656183595410115, | |
| "grad_norm": 0.2049029334189066, | |
| "learning_rate": 0.00018379559064687047, | |
| "loss": 0.5408, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.2656183595410115, | |
| "eval_loss": 0.575043261051178, | |
| "eval_runtime": 13.6594, | |
| "eval_samples_per_second": 1.318, | |
| "eval_steps_per_second": 0.659, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.27624309392265195, | |
| "grad_norm": 0.1904505136620864, | |
| "learning_rate": 0.0001817137294566856, | |
| "loss": 0.5275, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.27624309392265195, | |
| "eval_loss": 0.5728871822357178, | |
| "eval_runtime": 13.7391, | |
| "eval_samples_per_second": 1.31, | |
| "eval_steps_per_second": 0.655, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.2868678283042924, | |
| "grad_norm": 0.22154830832529648, | |
| "learning_rate": 0.00017951941210237073, | |
| "loss": 0.533, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.2868678283042924, | |
| "eval_loss": 0.5692403316497803, | |
| "eval_runtime": 13.545, | |
| "eval_samples_per_second": 1.329, | |
| "eval_steps_per_second": 0.664, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.2974925626859328, | |
| "grad_norm": 0.2174115807792657, | |
| "learning_rate": 0.00017721565844991643, | |
| "loss": 0.5258, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.2974925626859328, | |
| "eval_loss": 0.5680803656578064, | |
| "eval_runtime": 13.7424, | |
| "eval_samples_per_second": 1.31, | |
| "eval_steps_per_second": 0.655, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3081172970675733, | |
| "grad_norm": 0.19207104639056627, | |
| "learning_rate": 0.00017480563897386326, | |
| "loss": 0.5175, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.3081172970675733, | |
| "eval_loss": 0.5652768611907959, | |
| "eval_runtime": 13.5314, | |
| "eval_samples_per_second": 1.33, | |
| "eval_steps_per_second": 0.665, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.31874203144921376, | |
| "grad_norm": 0.19862950596297196, | |
| "learning_rate": 0.00017229267039402753, | |
| "loss": 0.5053, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.31874203144921376, | |
| "eval_loss": 0.5653724074363708, | |
| "eval_runtime": 13.5197, | |
| "eval_samples_per_second": 1.331, | |
| "eval_steps_per_second": 0.666, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3293667658308542, | |
| "grad_norm": 0.2636122695391369, | |
| "learning_rate": 0.00016968021111096133, | |
| "loss": 0.5215, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.3293667658308542, | |
| "eval_loss": 0.5632820129394531, | |
| "eval_runtime": 13.7575, | |
| "eval_samples_per_second": 1.308, | |
| "eval_steps_per_second": 0.654, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.3399915002124947, | |
| "grad_norm": 0.17073712293046736, | |
| "learning_rate": 0.00016697185644642853, | |
| "loss": 0.5205, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.3399915002124947, | |
| "eval_loss": 0.5606775879859924, | |
| "eval_runtime": 13.6853, | |
| "eval_samples_per_second": 1.315, | |
| "eval_steps_per_second": 0.658, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.35061623459413516, | |
| "grad_norm": 0.1877562077800468, | |
| "learning_rate": 0.00016417133369544677, | |
| "loss": 0.5026, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.35061623459413516, | |
| "eval_loss": 0.5574628710746765, | |
| "eval_runtime": 13.6524, | |
| "eval_samples_per_second": 1.318, | |
| "eval_steps_per_second": 0.659, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.3612409689757756, | |
| "grad_norm": 0.2187753211287567, | |
| "learning_rate": 0.0001612824969967052, | |
| "loss": 0.5219, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.3612409689757756, | |
| "eval_loss": 0.5507112145423889, | |
| "eval_runtime": 13.5887, | |
| "eval_samples_per_second": 1.325, | |
| "eval_steps_per_second": 0.662, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.3718657033574161, | |
| "grad_norm": 0.21822616884068516, | |
| "learning_rate": 0.00015830932202841723, | |
| "loss": 0.5138, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.3718657033574161, | |
| "eval_loss": 0.5505152940750122, | |
| "eval_runtime": 13.6074, | |
| "eval_samples_per_second": 1.323, | |
| "eval_steps_per_second": 0.661, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.3824904377390565, | |
| "grad_norm": 0.19921946854007808, | |
| "learning_rate": 0.00015525590053690804, | |
| "loss": 0.5082, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3824904377390565, | |
| "eval_loss": 0.5506541728973389, | |
| "eval_runtime": 13.8251, | |
| "eval_samples_per_second": 1.302, | |
| "eval_steps_per_second": 0.651, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.39311517212069697, | |
| "grad_norm": 0.22351938753382847, | |
| "learning_rate": 0.00015212643470546668, | |
| "loss": 0.5089, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.39311517212069697, | |
| "eval_loss": 0.548447847366333, | |
| "eval_runtime": 13.6917, | |
| "eval_samples_per_second": 1.315, | |
| "eval_steps_per_second": 0.657, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.40373990650233743, | |
| "grad_norm": 0.19131472458469853, | |
| "learning_rate": 0.00014892523137121245, | |
| "loss": 0.5241, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.40373990650233743, | |
| "eval_loss": 0.5444693565368652, | |
| "eval_runtime": 13.7071, | |
| "eval_samples_per_second": 1.313, | |
| "eval_steps_per_second": 0.657, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.4143646408839779, | |
| "grad_norm": 0.19421007360537948, | |
| "learning_rate": 0.00014565669609793442, | |
| "loss": 0.507, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.4143646408839779, | |
| "eval_loss": 0.5411471724510193, | |
| "eval_runtime": 13.6537, | |
| "eval_samples_per_second": 1.318, | |
| "eval_steps_per_second": 0.659, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.42498937526561836, | |
| "grad_norm": 0.19516131766473133, | |
| "learning_rate": 0.00014232532711306155, | |
| "loss": 0.4931, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.42498937526561836, | |
| "eval_loss": 0.5411571860313416, | |
| "eval_runtime": 13.7576, | |
| "eval_samples_per_second": 1.308, | |
| "eval_steps_per_second": 0.654, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.43561410964725883, | |
| "grad_norm": 0.16870156967259758, | |
| "learning_rate": 0.00013893570911710656, | |
| "loss": 0.5033, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.43561410964725883, | |
| "eval_loss": 0.5401651859283447, | |
| "eval_runtime": 13.575, | |
| "eval_samples_per_second": 1.326, | |
| "eval_steps_per_second": 0.663, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.4462388440288993, | |
| "grad_norm": 0.1637560423009355, | |
| "learning_rate": 0.00013549250697410427, | |
| "loss": 0.4781, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.4462388440288993, | |
| "eval_loss": 0.5378057956695557, | |
| "eval_runtime": 13.6055, | |
| "eval_samples_per_second": 1.323, | |
| "eval_steps_per_second": 0.661, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.45686357841053976, | |
| "grad_norm": 0.17989029128302533, | |
| "learning_rate": 0.00013200045929172679, | |
| "loss": 0.4962, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.45686357841053976, | |
| "eval_loss": 0.5310940742492676, | |
| "eval_runtime": 13.7133, | |
| "eval_samples_per_second": 1.313, | |
| "eval_steps_per_second": 0.656, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.46748831279218017, | |
| "grad_norm": 0.18360206121827216, | |
| "learning_rate": 0.00012846437189991162, | |
| "loss": 0.5189, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.46748831279218017, | |
| "eval_loss": 0.5309380292892456, | |
| "eval_runtime": 13.6608, | |
| "eval_samples_per_second": 1.318, | |
| "eval_steps_per_second": 0.659, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.47811304717382064, | |
| "grad_norm": 0.18474682238955895, | |
| "learning_rate": 0.00012488911123697643, | |
| "loss": 0.5085, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.47811304717382064, | |
| "eval_loss": 0.5284863114356995, | |
| "eval_runtime": 13.6774, | |
| "eval_samples_per_second": 1.316, | |
| "eval_steps_per_second": 0.658, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.4887377815554611, | |
| "grad_norm": 0.16088542652738752, | |
| "learning_rate": 0.00012127959765232386, | |
| "loss": 0.4958, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.4887377815554611, | |
| "eval_loss": 0.5277774930000305, | |
| "eval_runtime": 13.5397, | |
| "eval_samples_per_second": 1.329, | |
| "eval_steps_per_second": 0.665, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.49936251593710157, | |
| "grad_norm": 0.16824774903806683, | |
| "learning_rate": 0.00011764079863495239, | |
| "loss": 0.4772, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.49936251593710157, | |
| "eval_loss": 0.5244553089141846, | |
| "eval_runtime": 13.57, | |
| "eval_samples_per_second": 1.326, | |
| "eval_steps_per_second": 0.663, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.509987250318742, | |
| "grad_norm": 0.19032915808439513, | |
| "learning_rate": 0.00011397772197709304, | |
| "loss": 0.4951, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.509987250318742, | |
| "eval_loss": 0.5219236612319946, | |
| "eval_runtime": 13.751, | |
| "eval_samples_per_second": 1.309, | |
| "eval_steps_per_second": 0.654, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5206119847003825, | |
| "grad_norm": 0.19732678264253936, | |
| "learning_rate": 0.00011029540888237941, | |
| "loss": 0.4598, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.5206119847003825, | |
| "eval_loss": 0.5182512402534485, | |
| "eval_runtime": 13.5188, | |
| "eval_samples_per_second": 1.331, | |
| "eval_steps_per_second": 0.666, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.531236719082023, | |
| "grad_norm": 0.18322879510839657, | |
| "learning_rate": 0.00010659892702803677, | |
| "loss": 0.4937, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.531236719082023, | |
| "eval_loss": 0.5168578624725342, | |
| "eval_runtime": 13.6434, | |
| "eval_samples_per_second": 1.319, | |
| "eval_steps_per_second": 0.66, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.5418614534636634, | |
| "grad_norm": 0.16469463785666816, | |
| "learning_rate": 0.00010289336359063726, | |
| "loss": 0.4972, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.5418614534636634, | |
| "eval_loss": 0.515425443649292, | |
| "eval_runtime": 13.5093, | |
| "eval_samples_per_second": 1.332, | |
| "eval_steps_per_second": 0.666, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.5524861878453039, | |
| "grad_norm": 0.18400238161361088, | |
| "learning_rate": 9.918381824501988e-05, | |
| "loss": 0.4761, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5524861878453039, | |
| "eval_loss": 0.5136659145355225, | |
| "eval_runtime": 13.5018, | |
| "eval_samples_per_second": 1.333, | |
| "eval_steps_per_second": 0.667, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5631109222269444, | |
| "grad_norm": 0.17535283435867968, | |
| "learning_rate": 9.547539614601e-05, | |
| "loss": 0.4888, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.5631109222269444, | |
| "eval_loss": 0.509550929069519, | |
| "eval_runtime": 13.7492, | |
| "eval_samples_per_second": 1.309, | |
| "eval_steps_per_second": 0.655, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.5737356566085848, | |
| "grad_norm": 0.19027736106694362, | |
| "learning_rate": 9.17732009025972e-05, | |
| "loss": 0.4788, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.5737356566085848, | |
| "eval_loss": 0.5091434717178345, | |
| "eval_runtime": 13.6692, | |
| "eval_samples_per_second": 1.317, | |
| "eval_steps_per_second": 0.658, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.5843603909902253, | |
| "grad_norm": 0.14945795860859679, | |
| "learning_rate": 8.808232755424066e-05, | |
| "loss": 0.4711, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.5843603909902253, | |
| "eval_loss": 0.5075156688690186, | |
| "eval_runtime": 13.5509, | |
| "eval_samples_per_second": 1.328, | |
| "eval_steps_per_second": 0.664, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.5949851253718657, | |
| "grad_norm": 0.1876115407072482, | |
| "learning_rate": 8.440785555896786e-05, | |
| "loss": 0.4841, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5949851253718657, | |
| "eval_loss": 0.505312442779541, | |
| "eval_runtime": 13.6058, | |
| "eval_samples_per_second": 1.323, | |
| "eval_steps_per_second": 0.661, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.6056098597535061, | |
| "grad_norm": 0.17126471384455877, | |
| "learning_rate": 8.075484180291701e-05, | |
| "loss": 0.4733, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.6056098597535061, | |
| "eval_loss": 0.5053431391716003, | |
| "eval_runtime": 13.6732, | |
| "eval_samples_per_second": 1.316, | |
| "eval_steps_per_second": 0.658, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.6162345941351466, | |
| "grad_norm": 0.1612132057853942, | |
| "learning_rate": 7.712831364094332e-05, | |
| "loss": 0.4801, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.6162345941351466, | |
| "eval_loss": 0.5035179853439331, | |
| "eval_runtime": 13.5528, | |
| "eval_samples_per_second": 1.328, | |
| "eval_steps_per_second": 0.664, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.626859328516787, | |
| "grad_norm": 0.1774699324298755, | |
| "learning_rate": 7.353326197786673e-05, | |
| "loss": 0.4735, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.626859328516787, | |
| "eval_loss": 0.5026558041572571, | |
| "eval_runtime": 13.6414, | |
| "eval_samples_per_second": 1.32, | |
| "eval_steps_per_second": 0.66, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.6374840628984275, | |
| "grad_norm": 0.15538798680363947, | |
| "learning_rate": 6.997463439988324e-05, | |
| "loss": 0.4677, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6374840628984275, | |
| "eval_loss": 0.5013994574546814, | |
| "eval_runtime": 13.5624, | |
| "eval_samples_per_second": 1.327, | |
| "eval_steps_per_second": 0.664, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.648108797280068, | |
| "grad_norm": 0.1819125971720679, | |
| "learning_rate": 6.645732836559187e-05, | |
| "loss": 0.4588, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.648108797280068, | |
| "eval_loss": 0.5008442997932434, | |
| "eval_runtime": 13.7199, | |
| "eval_samples_per_second": 1.312, | |
| "eval_steps_per_second": 0.656, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.6587335316617084, | |
| "grad_norm": 0.17692677070822024, | |
| "learning_rate": 6.298618446600856e-05, | |
| "loss": 0.4803, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.6587335316617084, | |
| "eval_loss": 0.5003005266189575, | |
| "eval_runtime": 13.6645, | |
| "eval_samples_per_second": 1.317, | |
| "eval_steps_per_second": 0.659, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.6693582660433489, | |
| "grad_norm": 0.19223708797121006, | |
| "learning_rate": 5.956597976284239e-05, | |
| "loss": 0.4801, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.6693582660433489, | |
| "eval_loss": 0.49848344922065735, | |
| "eval_runtime": 13.7844, | |
| "eval_samples_per_second": 1.306, | |
| "eval_steps_per_second": 0.653, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.6799830004249894, | |
| "grad_norm": 0.19050620001754145, | |
| "learning_rate": 5.620142121420201e-05, | |
| "loss": 0.4699, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6799830004249894, | |
| "eval_loss": 0.4974481761455536, | |
| "eval_runtime": 13.6881, | |
| "eval_samples_per_second": 1.315, | |
| "eval_steps_per_second": 0.658, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6906077348066298, | |
| "grad_norm": 0.18849962999043668, | |
| "learning_rate": 5.289713919678034e-05, | |
| "loss": 0.4746, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.6906077348066298, | |
| "eval_loss": 0.49532318115234375, | |
| "eval_runtime": 13.6989, | |
| "eval_samples_per_second": 1.314, | |
| "eval_steps_per_second": 0.657, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.7012324691882703, | |
| "grad_norm": 0.17255206587971877, | |
| "learning_rate": 4.965768113343233e-05, | |
| "loss": 0.4677, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.7012324691882703, | |
| "eval_loss": 0.4947270154953003, | |
| "eval_runtime": 13.6686, | |
| "eval_samples_per_second": 1.317, | |
| "eval_steps_per_second": 0.658, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.7118572035699108, | |
| "grad_norm": 0.1772053939786707, | |
| "learning_rate": 4.6487505234914876e-05, | |
| "loss": 0.4673, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.7118572035699108, | |
| "eval_loss": 0.49380868673324585, | |
| "eval_runtime": 13.5528, | |
| "eval_samples_per_second": 1.328, | |
| "eval_steps_per_second": 0.664, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.7224819379515512, | |
| "grad_norm": 0.17206430964699912, | |
| "learning_rate": 4.339097436440346e-05, | |
| "loss": 0.4794, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.7224819379515512, | |
| "eval_loss": 0.4924837648868561, | |
| "eval_runtime": 13.6884, | |
| "eval_samples_per_second": 1.315, | |
| "eval_steps_per_second": 0.657, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.7331066723331917, | |
| "grad_norm": 0.20781990513713502, | |
| "learning_rate": 4.037235003322685e-05, | |
| "loss": 0.4688, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.7331066723331917, | |
| "eval_loss": 0.49092790484428406, | |
| "eval_runtime": 13.5314, | |
| "eval_samples_per_second": 1.33, | |
| "eval_steps_per_second": 0.665, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.7437314067148322, | |
| "grad_norm": 0.15566309201486278, | |
| "learning_rate": 3.7435786536085573e-05, | |
| "loss": 0.4789, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.7437314067148322, | |
| "eval_loss": 0.48968595266342163, | |
| "eval_runtime": 13.561, | |
| "eval_samples_per_second": 1.327, | |
| "eval_steps_per_second": 0.664, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.7543561410964726, | |
| "grad_norm": 0.23381879921923462, | |
| "learning_rate": 3.458532523382323e-05, | |
| "loss": 0.4826, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.7543561410964726, | |
| "eval_loss": 0.4890773594379425, | |
| "eval_runtime": 13.5661, | |
| "eval_samples_per_second": 1.327, | |
| "eval_steps_per_second": 0.663, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.764980875478113, | |
| "grad_norm": 0.16721926504642332, | |
| "learning_rate": 3.1824888991620294e-05, | |
| "loss": 0.4642, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.764980875478113, | |
| "eval_loss": 0.4890780448913574, | |
| "eval_runtime": 13.719, | |
| "eval_samples_per_second": 1.312, | |
| "eval_steps_per_second": 0.656, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.7756056098597535, | |
| "grad_norm": 0.18751577560760466, | |
| "learning_rate": 2.9158276780264006e-05, | |
| "loss": 0.4613, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.7756056098597535, | |
| "eval_loss": 0.48852983117103577, | |
| "eval_runtime": 13.741, | |
| "eval_samples_per_second": 1.31, | |
| "eval_steps_per_second": 0.655, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.7862303442413939, | |
| "grad_norm": 0.1728653190685702, | |
| "learning_rate": 2.6589158447924454e-05, | |
| "loss": 0.4615, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.7862303442413939, | |
| "eval_loss": 0.4880680441856384, | |
| "eval_runtime": 13.6489, | |
| "eval_samples_per_second": 1.319, | |
| "eval_steps_per_second": 0.659, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.7968550786230344, | |
| "grad_norm": 0.18900325234160106, | |
| "learning_rate": 2.4121069669631556e-05, | |
| "loss": 0.4587, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.7968550786230344, | |
| "eval_loss": 0.4873946011066437, | |
| "eval_runtime": 13.7858, | |
| "eval_samples_per_second": 1.306, | |
| "eval_steps_per_second": 0.653, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.8074798130046749, | |
| "grad_norm": 0.14783723259837353, | |
| "learning_rate": 2.175740708140468e-05, | |
| "loss": 0.4679, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.8074798130046749, | |
| "eval_loss": 0.4868377149105072, | |
| "eval_runtime": 13.8172, | |
| "eval_samples_per_second": 1.303, | |
| "eval_steps_per_second": 0.651, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.8181045473863153, | |
| "grad_norm": 0.17087609511278531, | |
| "learning_rate": 1.9501423605729773e-05, | |
| "loss": 0.4738, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.8181045473863153, | |
| "eval_loss": 0.4864993095397949, | |
| "eval_runtime": 13.5968, | |
| "eval_samples_per_second": 1.324, | |
| "eval_steps_per_second": 0.662, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.8287292817679558, | |
| "grad_norm": 0.18872610979845497, | |
| "learning_rate": 1.735622397481901e-05, | |
| "loss": 0.4586, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.8287292817679558, | |
| "eval_loss": 0.4859856069087982, | |
| "eval_runtime": 13.665, | |
| "eval_samples_per_second": 1.317, | |
| "eval_steps_per_second": 0.659, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.8393540161495963, | |
| "grad_norm": 0.16502873183660738, | |
| "learning_rate": 1.5324760457812302e-05, | |
| "loss": 0.4713, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.8393540161495963, | |
| "eval_loss": 0.48532745242118835, | |
| "eval_runtime": 13.52, | |
| "eval_samples_per_second": 1.331, | |
| "eval_steps_per_second": 0.666, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.8499787505312367, | |
| "grad_norm": 0.14410289002259907, | |
| "learning_rate": 1.3409828797802205e-05, | |
| "loss": 0.4453, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8499787505312367, | |
| "eval_loss": 0.485173761844635, | |
| "eval_runtime": 13.584, | |
| "eval_samples_per_second": 1.325, | |
| "eval_steps_per_second": 0.663, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8606034849128772, | |
| "grad_norm": 0.1948838377567367, | |
| "learning_rate": 1.161406436427297e-05, | |
| "loss": 0.473, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.8606034849128772, | |
| "eval_loss": 0.48516422510147095, | |
| "eval_runtime": 13.5308, | |
| "eval_samples_per_second": 1.33, | |
| "eval_steps_per_second": 0.665, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.8712282192945177, | |
| "grad_norm": 0.17372475645367427, | |
| "learning_rate": 9.939938526249337e-06, | |
| "loss": 0.4499, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.8712282192945177, | |
| "eval_loss": 0.484728068113327, | |
| "eval_runtime": 13.4398, | |
| "eval_samples_per_second": 1.339, | |
| "eval_steps_per_second": 0.67, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.8818529536761581, | |
| "grad_norm": 0.15074819772648787, | |
| "learning_rate": 8.389755251146159e-06, | |
| "loss": 0.4631, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.8818529536761581, | |
| "eval_loss": 0.4841134250164032, | |
| "eval_runtime": 13.53, | |
| "eval_samples_per_second": 1.33, | |
| "eval_steps_per_second": 0.665, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.8924776880577986, | |
| "grad_norm": 0.18378461042583777, | |
| "learning_rate": 6.965647933999742e-06, | |
| "loss": 0.4671, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.8924776880577986, | |
| "eval_loss": 0.4838300347328186, | |
| "eval_runtime": 13.4675, | |
| "eval_samples_per_second": 1.337, | |
| "eval_steps_per_second": 0.668, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.9031024224394391, | |
| "grad_norm": 0.1564603040061458, | |
| "learning_rate": 5.669576461444248e-06, | |
| "loss": 0.4463, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.9031024224394391, | |
| "eval_loss": 0.4835617244243622, | |
| "eval_runtime": 13.4511, | |
| "eval_samples_per_second": 1.338, | |
| "eval_steps_per_second": 0.669, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.9137271568210795, | |
| "grad_norm": 0.1814808133368016, | |
| "learning_rate": 4.503324514474483e-06, | |
| "loss": 0.4778, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.9137271568210795, | |
| "eval_loss": 0.48341307044029236, | |
| "eval_runtime": 13.483, | |
| "eval_samples_per_second": 1.335, | |
| "eval_steps_per_second": 0.668, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.9243518912027199, | |
| "grad_norm": 0.16529041233191302, | |
| "learning_rate": 3.4684971137061484e-06, | |
| "loss": 0.4682, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.9243518912027199, | |
| "eval_loss": 0.4833216667175293, | |
| "eval_runtime": 13.6309, | |
| "eval_samples_per_second": 1.321, | |
| "eval_steps_per_second": 0.66, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.9349766255843603, | |
| "grad_norm": 0.16432869665531463, | |
| "learning_rate": 2.566518410512586e-06, | |
| "loss": 0.4462, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.9349766255843603, | |
| "eval_loss": 0.48317214846611023, | |
| "eval_runtime": 13.6155, | |
| "eval_samples_per_second": 1.322, | |
| "eval_steps_per_second": 0.661, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.9456013599660008, | |
| "grad_norm": 0.17027661720242618, | |
| "learning_rate": 1.7986297270775054e-06, | |
| "loss": 0.4573, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.9456013599660008, | |
| "eval_loss": 0.48307955265045166, | |
| "eval_runtime": 13.4168, | |
| "eval_samples_per_second": 1.342, | |
| "eval_steps_per_second": 0.671, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.9562260943476413, | |
| "grad_norm": 0.16582718568525256, | |
| "learning_rate": 1.16588784806112e-06, | |
| "loss": 0.4764, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.9562260943476413, | |
| "eval_loss": 0.48304203152656555, | |
| "eval_runtime": 13.4315, | |
| "eval_samples_per_second": 1.34, | |
| "eval_steps_per_second": 0.67, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.9668508287292817, | |
| "grad_norm": 0.16474906223134622, | |
| "learning_rate": 6.691635662307017e-07, | |
| "loss": 0.467, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.9668508287292817, | |
| "eval_loss": 0.4829782247543335, | |
| "eval_runtime": 13.5849, | |
| "eval_samples_per_second": 1.325, | |
| "eval_steps_per_second": 0.663, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.9774755631109222, | |
| "grad_norm": 0.1846923892020628, | |
| "learning_rate": 3.091404840571799e-07, | |
| "loss": 0.4592, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.9774755631109222, | |
| "eval_loss": 0.4829777479171753, | |
| "eval_runtime": 13.5512, | |
| "eval_samples_per_second": 1.328, | |
| "eval_steps_per_second": 0.664, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.9881002974925627, | |
| "grad_norm": 0.16625664738759183, | |
| "learning_rate": 8.631407292692962e-08, | |
| "loss": 0.4582, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.9881002974925627, | |
| "eval_loss": 0.48291730880737305, | |
| "eval_runtime": 13.3992, | |
| "eval_samples_per_second": 1.343, | |
| "eval_steps_per_second": 0.672, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.9987250318742031, | |
| "grad_norm": 0.16884372416843668, | |
| "learning_rate": 9.909912635497343e-10, | |
| "loss": 0.4576, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.9987250318742031, | |
| "eval_loss": 0.4829167127609253, | |
| "eval_runtime": 13.4537, | |
| "eval_samples_per_second": 1.338, | |
| "eval_steps_per_second": 0.669, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 2353, | |
| "total_flos": 2.65944394463445e+17, | |
| "train_loss": 0.5110978669325849, | |
| "train_runtime": 64922.9003, | |
| "train_samples_per_second": 0.29, | |
| "train_steps_per_second": 0.036 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 2353, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.65944394463445e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |