| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1266, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023696682464454975, | |
| "grad_norm": 1.8578642304403785, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8806, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04739336492890995, | |
| "grad_norm": 1.183006030611099, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7797, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07109004739336493, | |
| "grad_norm": 1.4765088938253328, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7484, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0947867298578199, | |
| "grad_norm": 1.163022578781007, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7347, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11848341232227488, | |
| "grad_norm": 0.7554926726458471, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7203, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14218009478672985, | |
| "grad_norm": 0.731542170193161, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7096, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16587677725118483, | |
| "grad_norm": 0.9060440478303672, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7059, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1895734597156398, | |
| "grad_norm": 0.7296366219850153, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7001, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2132701421800948, | |
| "grad_norm": 0.7426978264461702, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6962, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23696682464454977, | |
| "grad_norm": 0.6188812479024083, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6868, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26066350710900477, | |
| "grad_norm": 0.5476530648144865, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6824, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2843601895734597, | |
| "grad_norm": 0.694221105485736, | |
| "learning_rate": 5e-06, | |
| "loss": 0.679, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3080568720379147, | |
| "grad_norm": 0.7560482674288443, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6827, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33175355450236965, | |
| "grad_norm": 0.7850327296092002, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6733, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35545023696682465, | |
| "grad_norm": 0.5570389442716736, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6813, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3791469194312796, | |
| "grad_norm": 0.9044873869853465, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6764, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4028436018957346, | |
| "grad_norm": 0.9187588354313664, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6729, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4265402843601896, | |
| "grad_norm": 0.5060518745683197, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6691, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.45023696682464454, | |
| "grad_norm": 0.49447301037625124, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6694, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.47393364928909953, | |
| "grad_norm": 0.6175555086839499, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6681, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4976303317535545, | |
| "grad_norm": 0.6085272766245269, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6604, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5213270142180095, | |
| "grad_norm": 0.5926380925408075, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6656, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5450236966824644, | |
| "grad_norm": 0.6160796498694022, | |
| "learning_rate": 5e-06, | |
| "loss": 0.663, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5687203791469194, | |
| "grad_norm": 0.6914531474013237, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6656, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5924170616113744, | |
| "grad_norm": 0.6596857730992619, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6572, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6161137440758294, | |
| "grad_norm": 0.5279165722236415, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6684, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6398104265402843, | |
| "grad_norm": 0.5689701712166578, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6548, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6635071090047393, | |
| "grad_norm": 0.5166176607170971, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6698, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6872037914691943, | |
| "grad_norm": 0.6445425535849747, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6579, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7109004739336493, | |
| "grad_norm": 0.6506854686970152, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6551, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7345971563981043, | |
| "grad_norm": 0.5085915851296422, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6616, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7582938388625592, | |
| "grad_norm": 0.6487986243452837, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6566, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7819905213270142, | |
| "grad_norm": 0.5441246219276076, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6521, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8056872037914692, | |
| "grad_norm": 0.48980734623494515, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6552, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8293838862559242, | |
| "grad_norm": 0.3938069962058288, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6503, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8530805687203792, | |
| "grad_norm": 0.5653669786380396, | |
| "learning_rate": 5e-06, | |
| "loss": 0.653, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8767772511848341, | |
| "grad_norm": 0.7322605559502221, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6549, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9004739336492891, | |
| "grad_norm": 0.6662476991971801, | |
| "learning_rate": 5e-06, | |
| "loss": 0.658, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9241706161137441, | |
| "grad_norm": 0.568403065783914, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6577, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9478672985781991, | |
| "grad_norm": 0.46948514320296014, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6459, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9715639810426541, | |
| "grad_norm": 0.7292309309979981, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6556, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.995260663507109, | |
| "grad_norm": 0.6757095412992554, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6485, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6513110399246216, | |
| "eval_runtime": 226.1564, | |
| "eval_samples_per_second": 50.257, | |
| "eval_steps_per_second": 0.394, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.018957345971564, | |
| "grad_norm": 0.5805140570845687, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6185, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.042654028436019, | |
| "grad_norm": 0.5434272081051958, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6145, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.066350710900474, | |
| "grad_norm": 0.5326556907180255, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6094, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0900473933649288, | |
| "grad_norm": 0.5829211855668741, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6097, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.113744075829384, | |
| "grad_norm": 0.6319252195360786, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6194, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.1374407582938388, | |
| "grad_norm": 0.504231300635023, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6055, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.161137440758294, | |
| "grad_norm": 0.47691471391766244, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6103, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1848341232227488, | |
| "grad_norm": 0.6579542570947285, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5974, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2085308056872037, | |
| "grad_norm": 0.5296651294386931, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6087, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2322274881516588, | |
| "grad_norm": 0.5136903442393255, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6098, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2559241706161137, | |
| "grad_norm": 0.4323386979195923, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6061, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2796208530805688, | |
| "grad_norm": 0.4569721261280212, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6066, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.3033175355450237, | |
| "grad_norm": 0.6467514503519792, | |
| "learning_rate": 5e-06, | |
| "loss": 0.611, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3270142180094786, | |
| "grad_norm": 0.5707325971904217, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6149, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.3507109004739337, | |
| "grad_norm": 0.6351802477821956, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6117, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3744075829383886, | |
| "grad_norm": 0.4343155173009086, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6061, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3981042654028437, | |
| "grad_norm": 0.4859882284821603, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6161, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4218009478672986, | |
| "grad_norm": 0.5236535463545058, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6096, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4454976303317535, | |
| "grad_norm": 0.4557408062718408, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6137, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4691943127962086, | |
| "grad_norm": 0.4710881048666159, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6104, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4928909952606635, | |
| "grad_norm": 0.4693244351357125, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6113, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5165876777251186, | |
| "grad_norm": 0.5106722321731667, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6099, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.5402843601895735, | |
| "grad_norm": 0.5008718823276928, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6095, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5639810426540284, | |
| "grad_norm": 0.5709206603606636, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6072, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5876777251184833, | |
| "grad_norm": 0.5000142373704568, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6054, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.6113744075829384, | |
| "grad_norm": 0.503815554745896, | |
| "learning_rate": 5e-06, | |
| "loss": 0.609, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6350710900473935, | |
| "grad_norm": 0.4901500964784556, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6144, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.6587677725118484, | |
| "grad_norm": 0.7148462741898324, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6171, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6824644549763033, | |
| "grad_norm": 0.46371859890219064, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6117, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.7061611374407581, | |
| "grad_norm": 0.4868566708300119, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6084, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7298578199052133, | |
| "grad_norm": 0.46557974227861393, | |
| "learning_rate": 5e-06, | |
| "loss": 0.612, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.7535545023696684, | |
| "grad_norm": 0.4614750853949275, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6085, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7772511848341233, | |
| "grad_norm": 0.46000509620123947, | |
| "learning_rate": 5e-06, | |
| "loss": 0.598, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.8009478672985781, | |
| "grad_norm": 0.5069124386887875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6165, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.824644549763033, | |
| "grad_norm": 0.5759098925487337, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6055, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.8483412322274881, | |
| "grad_norm": 0.5688069546656076, | |
| "learning_rate": 5e-06, | |
| "loss": 0.603, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8720379146919433, | |
| "grad_norm": 0.4094394097978499, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6048, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8957345971563981, | |
| "grad_norm": 0.5419176372666504, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6113, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.919431279620853, | |
| "grad_norm": 0.5208348604849014, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6031, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.943127962085308, | |
| "grad_norm": 0.528072870680137, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6079, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.966824644549763, | |
| "grad_norm": 0.5102023817039236, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6057, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9905213270142181, | |
| "grad_norm": 0.4411278261182562, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6114, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6409755349159241, | |
| "eval_runtime": 227.48, | |
| "eval_samples_per_second": 49.965, | |
| "eval_steps_per_second": 0.391, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 2.014218009478673, | |
| "grad_norm": 0.7123835129441645, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5761, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.037914691943128, | |
| "grad_norm": 0.5536575003997367, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5637, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.061611374407583, | |
| "grad_norm": 0.5997737415317981, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5558, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.085308056872038, | |
| "grad_norm": 0.7669561696901881, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5628, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.109004739336493, | |
| "grad_norm": 0.809324396115254, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5659, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.132701421800948, | |
| "grad_norm": 0.632132677022118, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5627, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.156398104265403, | |
| "grad_norm": 0.5363755744993185, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5613, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.1800947867298577, | |
| "grad_norm": 0.7992701994586238, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5647, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.2037914691943126, | |
| "grad_norm": 0.5137612186247765, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5717, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.227488151658768, | |
| "grad_norm": 0.48307350386563647, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5707, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.251184834123223, | |
| "grad_norm": 0.4585281852449342, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5704, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.2748815165876777, | |
| "grad_norm": 0.5158085231030699, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5683, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.2985781990521326, | |
| "grad_norm": 0.5090415152331892, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5675, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.322274881516588, | |
| "grad_norm": 0.5033009699976476, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5677, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.345971563981043, | |
| "grad_norm": 0.6352174600369093, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5713, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.3696682464454977, | |
| "grad_norm": 0.6200134705498003, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5697, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3933649289099526, | |
| "grad_norm": 0.5541614450406952, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5656, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.4170616113744074, | |
| "grad_norm": 0.5662092850065095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5667, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.4407582938388623, | |
| "grad_norm": 0.527115473356076, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5695, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.4644549763033177, | |
| "grad_norm": 0.5199769536715289, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5698, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.4881516587677726, | |
| "grad_norm": 0.5592591939664879, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5649, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.5118483412322274, | |
| "grad_norm": 0.5646160398662861, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5723, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.5355450236966823, | |
| "grad_norm": 0.45824336816755823, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5693, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.5592417061611377, | |
| "grad_norm": 0.5244304501627578, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5611, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.5829383886255926, | |
| "grad_norm": 0.5019930257935107, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5703, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.6066350710900474, | |
| "grad_norm": 0.4876750231159846, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5642, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.6303317535545023, | |
| "grad_norm": 0.436840454337667, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5727, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.654028436018957, | |
| "grad_norm": 0.5230375266459463, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5723, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.677725118483412, | |
| "grad_norm": 0.4743811030949543, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5738, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.7014218009478674, | |
| "grad_norm": 0.480507040656355, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5719, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.7251184834123223, | |
| "grad_norm": 0.4931664579971654, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5668, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.748815165876777, | |
| "grad_norm": 0.5124020975818223, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5674, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.772511848341232, | |
| "grad_norm": 0.4542681202604461, | |
| "learning_rate": 5e-06, | |
| "loss": 0.579, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.7962085308056874, | |
| "grad_norm": 0.49551548889838143, | |
| "learning_rate": 5e-06, | |
| "loss": 0.571, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.8199052132701423, | |
| "grad_norm": 0.47230557330706946, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5684, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.843601895734597, | |
| "grad_norm": 0.4780110660351261, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5709, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.867298578199052, | |
| "grad_norm": 0.49898222281980387, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5663, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.890995260663507, | |
| "grad_norm": 0.5319484749651314, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5617, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.914691943127962, | |
| "grad_norm": 0.47502518298760565, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5673, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.938388625592417, | |
| "grad_norm": 0.5666269567982688, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5735, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.962085308056872, | |
| "grad_norm": 0.5406615669892904, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5753, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.985781990521327, | |
| "grad_norm": 0.4880390264779233, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5796, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6424745321273804, | |
| "eval_runtime": 228.2499, | |
| "eval_samples_per_second": 49.796, | |
| "eval_steps_per_second": 0.39, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1266, | |
| "total_flos": 2120178393415680.0, | |
| "train_loss": 0.6194126374348645, | |
| "train_runtime": 38258.2762, | |
| "train_samples_per_second": 16.934, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1266, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2120178393415680.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |