| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9954430379746837, | |
| "eval_steps": 500, | |
| "global_step": 1479, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020253164556962026, | |
| "grad_norm": 2.523367947846648, | |
| "learning_rate": 2e-06, | |
| "loss": 0.7211, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04050632911392405, | |
| "grad_norm": 1.769334396847984, | |
| "learning_rate": 2e-06, | |
| "loss": 0.6528, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.060759493670886074, | |
| "grad_norm": 1.5793956641928097, | |
| "learning_rate": 2e-06, | |
| "loss": 0.6349, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0810126582278481, | |
| "grad_norm": 1.6799029370224616, | |
| "learning_rate": 2e-06, | |
| "loss": 0.62, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 1.2954284468153618, | |
| "learning_rate": 2e-06, | |
| "loss": 0.6097, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12151898734177215, | |
| "grad_norm": 1.2561158972455153, | |
| "learning_rate": 2e-06, | |
| "loss": 0.6033, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14177215189873418, | |
| "grad_norm": 2.5474428820357558, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5986, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1620253164556962, | |
| "grad_norm": 1.4575407750395815, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5944, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18227848101265823, | |
| "grad_norm": 2.369922793307101, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5933, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 1.741596834035678, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5959, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22278481012658227, | |
| "grad_norm": 2.499238442279651, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5878, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2430379746835443, | |
| "grad_norm": 1.8321823562536192, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5855, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.26329113924050634, | |
| "grad_norm": 1.8394637321819474, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5844, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.28354430379746837, | |
| "grad_norm": 1.8170126772052912, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5741, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3037974683544304, | |
| "grad_norm": 2.3226919673694124, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5841, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3240506329113924, | |
| "grad_norm": 2.1101835735304864, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5828, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34430379746835443, | |
| "grad_norm": 1.93462861240785, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5831, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.36455696202531646, | |
| "grad_norm": 1.8164588577876344, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5783, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3848101265822785, | |
| "grad_norm": 1.4553734626743444, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5779, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": 1.3491180080430512, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5729, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4253164556962025, | |
| "grad_norm": 1.2931164789708787, | |
| "learning_rate": 2e-06, | |
| "loss": 0.569, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.44556962025316454, | |
| "grad_norm": 1.5024706429671637, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5743, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.46582278481012657, | |
| "grad_norm": 1.85229490313526, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5729, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4860759493670886, | |
| "grad_norm": 2.082454901234663, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5689, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5063291139240507, | |
| "grad_norm": 1.726608104025137, | |
| "learning_rate": 2e-06, | |
| "loss": 0.572, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5265822784810127, | |
| "grad_norm": 1.7690925451713937, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5577, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5468354430379747, | |
| "grad_norm": 1.8139417797315314, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5669, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5670886075949367, | |
| "grad_norm": 1.5107507970732417, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5619, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5873417721518988, | |
| "grad_norm": 1.8780057585040468, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5623, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6075949367088608, | |
| "grad_norm": 1.4346250345671192, | |
| "learning_rate": 2e-06, | |
| "loss": 0.562, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6278481012658228, | |
| "grad_norm": 1.4169278686060502, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5672, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6481012658227848, | |
| "grad_norm": 1.257023671658508, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5641, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6683544303797468, | |
| "grad_norm": 1.4093944069759867, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5637, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6886075949367089, | |
| "grad_norm": 1.4973365573484316, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5634, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7088607594936709, | |
| "grad_norm": 1.3415168590254498, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5648, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7291139240506329, | |
| "grad_norm": 1.2781799167865413, | |
| "learning_rate": 2e-06, | |
| "loss": 0.567, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7493670886075949, | |
| "grad_norm": 1.265343167769912, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5596, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.769620253164557, | |
| "grad_norm": 1.191672852115913, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5561, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.789873417721519, | |
| "grad_norm": 1.3953206888100773, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5593, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.810126582278481, | |
| "grad_norm": 1.1738528696813688, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5595, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.830379746835443, | |
| "grad_norm": 1.1841723935038908, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5544, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.850632911392405, | |
| "grad_norm": 1.3782617764053784, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5619, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8708860759493671, | |
| "grad_norm": 1.2149757289282215, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5551, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8911392405063291, | |
| "grad_norm": 1.2854153088420381, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5603, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9113924050632911, | |
| "grad_norm": 1.232648810299269, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5513, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9316455696202531, | |
| "grad_norm": 1.3378475410751305, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5557, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9518987341772152, | |
| "grad_norm": 1.3844629170138667, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5565, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9721518987341772, | |
| "grad_norm": 1.1823337435426402, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5535, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9924050632911392, | |
| "grad_norm": 1.2435881794622146, | |
| "learning_rate": 2e-06, | |
| "loss": 0.55, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9984810126582279, | |
| "eval_loss": 0.06908208876848221, | |
| "eval_runtime": 505.3113, | |
| "eval_samples_per_second": 26.328, | |
| "eval_steps_per_second": 0.412, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.0126582278481013, | |
| "grad_norm": 2.585135740351158, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5317, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0329113924050632, | |
| "grad_norm": 1.2682450476042617, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5117, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.0531645569620254, | |
| "grad_norm": 1.5778363335912438, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5085, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.0734177215189873, | |
| "grad_norm": 1.3101233095585794, | |
| "learning_rate": 2e-06, | |
| "loss": 0.511, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.0936708860759494, | |
| "grad_norm": 1.9135596904942989, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5085, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.1139240506329113, | |
| "grad_norm": 1.4789557303779457, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5109, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.1341772151898735, | |
| "grad_norm": 1.9107639151322382, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5069, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.1544303797468354, | |
| "grad_norm": 1.345552795552788, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5128, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.1746835443037975, | |
| "grad_norm": 1.294490839190748, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5105, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.1949367088607594, | |
| "grad_norm": 1.2959638629757975, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5044, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.2151898734177216, | |
| "grad_norm": 1.2286418879457723, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5114, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2354430379746835, | |
| "grad_norm": 1.4051032168983806, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5072, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.2556962025316456, | |
| "grad_norm": 1.3849421442986407, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5115, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.2759493670886077, | |
| "grad_norm": 1.5258337811678189, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5104, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.2962025316455696, | |
| "grad_norm": 1.4714410611581017, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5097, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.3164556962025316, | |
| "grad_norm": 1.2874271827125905, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5127, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.3367088607594937, | |
| "grad_norm": 1.625207874373907, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5015, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.3569620253164558, | |
| "grad_norm": 1.4116707031607987, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5153, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.3772151898734177, | |
| "grad_norm": 1.221527311022984, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5114, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.3974683544303796, | |
| "grad_norm": 1.2042351211796771, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5099, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.4177215189873418, | |
| "grad_norm": 1.2805872223371426, | |
| "learning_rate": 2e-06, | |
| "loss": 0.507, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.437974683544304, | |
| "grad_norm": 1.3926598441879094, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5127, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.4582278481012658, | |
| "grad_norm": 1.2336955839559829, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5121, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.4784810126582277, | |
| "grad_norm": 1.543221732924072, | |
| "learning_rate": 2e-06, | |
| "loss": 0.515, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.4987341772151899, | |
| "grad_norm": 1.278390280342278, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5069, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.518987341772152, | |
| "grad_norm": 1.3504291682196217, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5094, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.539240506329114, | |
| "grad_norm": 1.755321109265681, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5104, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.5594936708860758, | |
| "grad_norm": 1.3155881969046814, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5084, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.579746835443038, | |
| "grad_norm": 1.470324564405093, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5089, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.5220659910177938, | |
| "learning_rate": 2e-06, | |
| "loss": 0.511, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.620253164556962, | |
| "grad_norm": 1.39293402110209, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5063, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.640506329113924, | |
| "grad_norm": 1.5110111084806697, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4994, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.660759493670886, | |
| "grad_norm": 1.9122030403855388, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5082, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.6810126582278482, | |
| "grad_norm": 1.2646338437385596, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5029, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.70126582278481, | |
| "grad_norm": 1.2655833293663716, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5048, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.721518987341772, | |
| "grad_norm": 1.150368797861094, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5063, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.7417721518987341, | |
| "grad_norm": 1.55155194662082, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5067, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.7620253164556963, | |
| "grad_norm": 1.7171439624945062, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5097, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.7822784810126582, | |
| "grad_norm": 1.8099073986129026, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5101, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.80253164556962, | |
| "grad_norm": 1.4858277942006235, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5069, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.8227848101265822, | |
| "grad_norm": 1.4878864413870432, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5062, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.8430379746835444, | |
| "grad_norm": 1.327504851086801, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5084, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.8632911392405065, | |
| "grad_norm": 1.1789308280903203, | |
| "learning_rate": 2e-06, | |
| "loss": 0.507, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.8835443037974684, | |
| "grad_norm": 1.251662378881582, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5031, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.9037974683544303, | |
| "grad_norm": 1.196506434668025, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5071, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.9240506329113924, | |
| "grad_norm": 1.2826838927766848, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5082, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.9443037974683546, | |
| "grad_norm": 1.2421418166244196, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5122, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.9645569620253165, | |
| "grad_norm": 1.38438196108533, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5107, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.9848101265822784, | |
| "grad_norm": 1.2134099545097368, | |
| "learning_rate": 2e-06, | |
| "loss": 0.511, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.998987341772152, | |
| "eval_loss": 0.06807009875774384, | |
| "eval_runtime": 505.2365, | |
| "eval_samples_per_second": 26.332, | |
| "eval_steps_per_second": 0.412, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 2.0050632911392405, | |
| "grad_norm": 1.6922792902945458, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4922, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.0253164556962027, | |
| "grad_norm": 1.7805024059221035, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4609, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0455696202531644, | |
| "grad_norm": 1.5660026772277083, | |
| "learning_rate": 2e-06, | |
| "loss": 0.461, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.0658227848101265, | |
| "grad_norm": 1.5959973691268172, | |
| "learning_rate": 2e-06, | |
| "loss": 0.457, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.0860759493670886, | |
| "grad_norm": 1.5168879139949634, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4564, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.1063291139240508, | |
| "grad_norm": 1.660530764697255, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4538, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.1265822784810124, | |
| "grad_norm": 1.4843369102568793, | |
| "learning_rate": 2e-06, | |
| "loss": 0.463, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.1468354430379746, | |
| "grad_norm": 1.678624246445537, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4576, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.1670886075949367, | |
| "grad_norm": 1.3153785609877087, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4598, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.187341772151899, | |
| "grad_norm": 1.4870013163912983, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4578, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.207594936708861, | |
| "grad_norm": 1.2999465758334146, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4545, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.2278481012658227, | |
| "grad_norm": 1.3996281063630598, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4649, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.248101265822785, | |
| "grad_norm": 1.3267624515172962, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4602, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.268354430379747, | |
| "grad_norm": 1.2469515003042624, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4619, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.2886075949367086, | |
| "grad_norm": 1.2576559765245747, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4635, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.3088607594936708, | |
| "grad_norm": 1.216262868231054, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4581, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.329113924050633, | |
| "grad_norm": 1.3737129102693821, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4658, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.349367088607595, | |
| "grad_norm": 1.6183287718171877, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4653, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.369620253164557, | |
| "grad_norm": 1.3383400617420638, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4654, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.389873417721519, | |
| "grad_norm": 1.2119443009240594, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4647, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.410126582278481, | |
| "grad_norm": 1.326934733122976, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4643, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.430379746835443, | |
| "grad_norm": 1.3889183142359904, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4627, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.4506329113924052, | |
| "grad_norm": 1.5581145283265878, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4611, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.470886075949367, | |
| "grad_norm": 1.322657958637839, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4646, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.491139240506329, | |
| "grad_norm": 2.039744415028908, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4638, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.511392405063291, | |
| "grad_norm": 1.3216724477382935, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4681, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.5316455696202533, | |
| "grad_norm": 1.3883035455752406, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4602, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.5518987341772155, | |
| "grad_norm": 1.3727379399668702, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4553, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.572151898734177, | |
| "grad_norm": 1.3761029301566705, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4626, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.5924050632911393, | |
| "grad_norm": 1.468216042571186, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4649, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.6126582278481014, | |
| "grad_norm": 1.5073307163893737, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4704, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.632911392405063, | |
| "grad_norm": 1.3734177001221963, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4638, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.6531645569620252, | |
| "grad_norm": 1.3285663767400802, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4629, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.6734177215189874, | |
| "grad_norm": 1.4605487104711394, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4654, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.6936708860759495, | |
| "grad_norm": 1.2859852384538413, | |
| "learning_rate": 2e-06, | |
| "loss": 0.468, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.7139240506329116, | |
| "grad_norm": 1.2933683570590095, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4656, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.7341772151898733, | |
| "grad_norm": 1.3402860764495008, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4642, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.7544303797468355, | |
| "grad_norm": 1.3056466516681664, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4599, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.7746835443037976, | |
| "grad_norm": 1.4231179248768173, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4659, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.7949367088607593, | |
| "grad_norm": 1.2451413230555421, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4636, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.8151898734177214, | |
| "grad_norm": 1.4787537036993241, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4662, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.8354430379746836, | |
| "grad_norm": 1.2642811017212636, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4594, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.8556962025316457, | |
| "grad_norm": 1.3135588211583467, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4684, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.875949367088608, | |
| "grad_norm": 1.4231992720021234, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4633, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.8962025316455695, | |
| "grad_norm": 1.4199024482257723, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4641, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.9164556962025316, | |
| "grad_norm": 1.3600411030696302, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4665, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.9367088607594938, | |
| "grad_norm": 1.3137743281247942, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4752, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.9569620253164555, | |
| "grad_norm": 1.2926899231065934, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4618, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.9772151898734176, | |
| "grad_norm": 1.337492408562305, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4663, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "eval_loss": 0.06873093545436859, | |
| "eval_runtime": 504.9232, | |
| "eval_samples_per_second": 26.349, | |
| "eval_steps_per_second": 0.412, | |
| "step": 1479 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "step": 1479, | |
| "total_flos": 2477170706350080.0, | |
| "train_loss": 0.5165934994705953, | |
| "train_runtime": 84286.543, | |
| "train_samples_per_second": 8.996, | |
| "train_steps_per_second": 0.018 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1479, | |
| "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": 2477170706350080.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |