| { | |
| "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": 2.8544461931274934, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7569, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04050632911392405, | |
| "grad_norm": 2.7444903942187175, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6507, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.060759493670886074, | |
| "grad_norm": 1.3943814336457603, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6289, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0810126582278481, | |
| "grad_norm": 1.4159200277827484, | |
| "learning_rate": 5e-06, | |
| "loss": 0.614, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 1.8420749848935474, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6034, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12151898734177215, | |
| "grad_norm": 1.447732727495403, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5973, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14177215189873418, | |
| "grad_norm": 1.8401989346240508, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5925, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1620253164556962, | |
| "grad_norm": 1.4380019004522187, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5876, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18227848101265823, | |
| "grad_norm": 1.657450409370915, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5863, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 2.311058324506438, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5895, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22278481012658227, | |
| "grad_norm": 1.2759051791468548, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5816, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2430379746835443, | |
| "grad_norm": 1.3376976540526444, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5792, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.26329113924050634, | |
| "grad_norm": 1.6258428242345302, | |
| "learning_rate": 5e-06, | |
| "loss": 0.578, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.28354430379746837, | |
| "grad_norm": 1.5716514169659848, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5677, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3037974683544304, | |
| "grad_norm": 1.5695310925399224, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5779, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3240506329113924, | |
| "grad_norm": 1.5748942702615565, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5762, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34430379746835443, | |
| "grad_norm": 1.739225496496722, | |
| "learning_rate": 5e-06, | |
| "loss": 0.577, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.36455696202531646, | |
| "grad_norm": 1.7585144012617044, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5731, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3848101265822785, | |
| "grad_norm": 1.5833716095990014, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5717, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": 1.6675521594937952, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5664, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4253164556962025, | |
| "grad_norm": 1.5564420443090938, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5621, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.44556962025316454, | |
| "grad_norm": 1.4391864660123526, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5678, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.46582278481012657, | |
| "grad_norm": 1.3545531998280866, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5665, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4860759493670886, | |
| "grad_norm": 1.2117242731823523, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5628, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5063291139240507, | |
| "grad_norm": 1.2967375627557465, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5668, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5265822784810127, | |
| "grad_norm": 1.4423833757840236, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5533, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5468354430379747, | |
| "grad_norm": 1.2030292390095976, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5623, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5670886075949367, | |
| "grad_norm": 1.340394632932045, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5577, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5873417721518988, | |
| "grad_norm": 1.699090610982426, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5579, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6075949367088608, | |
| "grad_norm": 1.2878486189890792, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5576, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6278481012658228, | |
| "grad_norm": 1.2077186320339615, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5629, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6481012658227848, | |
| "grad_norm": 1.3244718672832188, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5594, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6683544303797468, | |
| "grad_norm": 1.417195710228401, | |
| "learning_rate": 5e-06, | |
| "loss": 0.559, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6886075949367089, | |
| "grad_norm": 1.329383308154249, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5588, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7088607594936709, | |
| "grad_norm": 1.3387484647946544, | |
| "learning_rate": 5e-06, | |
| "loss": 0.56, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7291139240506329, | |
| "grad_norm": 1.2546659088358711, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5622, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7493670886075949, | |
| "grad_norm": 1.2552138171718579, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5547, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.769620253164557, | |
| "grad_norm": 1.343049081695452, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5514, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.789873417721519, | |
| "grad_norm": 1.7012223994903535, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5546, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.810126582278481, | |
| "grad_norm": 1.1159081764354688, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5549, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.830379746835443, | |
| "grad_norm": 1.3266370286884424, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5495, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.850632911392405, | |
| "grad_norm": 1.1188079131605666, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5576, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8708860759493671, | |
| "grad_norm": 1.281542150580452, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5508, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8911392405063291, | |
| "grad_norm": 1.1598655378018121, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5562, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9113924050632911, | |
| "grad_norm": 1.2672325826373367, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5473, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9316455696202531, | |
| "grad_norm": 1.0317053256498185, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5516, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9518987341772152, | |
| "grad_norm": 1.4315894237990952, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5526, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9721518987341772, | |
| "grad_norm": 1.2047073476573256, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5499, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9924050632911392, | |
| "grad_norm": 1.1500251693609045, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5464, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9984810126582279, | |
| "eval_loss": 0.06868810206651688, | |
| "eval_runtime": 512.3603, | |
| "eval_samples_per_second": 25.966, | |
| "eval_steps_per_second": 0.406, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.0126582278481013, | |
| "grad_norm": 1.8413916260979792, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5079, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0329113924050632, | |
| "grad_norm": 1.4722173755845698, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4751, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.0531645569620254, | |
| "grad_norm": 1.3281419836326962, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4713, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.0734177215189873, | |
| "grad_norm": 1.9790378457546416, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4733, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.0936708860759494, | |
| "grad_norm": 1.3589991519525444, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4702, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.1139240506329113, | |
| "grad_norm": 1.4545027920691798, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4722, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.1341772151898735, | |
| "grad_norm": 1.3978013602179746, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4695, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.1544303797468354, | |
| "grad_norm": 1.085881264218112, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4762, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.1746835443037975, | |
| "grad_norm": 1.2222577696921726, | |
| "learning_rate": 5e-06, | |
| "loss": 0.475, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.1949367088607594, | |
| "grad_norm": 1.1668742626981172, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4689, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.2151898734177216, | |
| "grad_norm": 1.2276792224748574, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4762, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2354430379746835, | |
| "grad_norm": 1.453085671614249, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4721, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.2556962025316456, | |
| "grad_norm": 1.502759057117359, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4763, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.2759493670886077, | |
| "grad_norm": 1.3654526602741475, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4758, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.2962025316455696, | |
| "grad_norm": 1.2900057606104782, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4751, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.3164556962025316, | |
| "grad_norm": 1.2304140089136695, | |
| "learning_rate": 5e-06, | |
| "loss": 0.479, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.3367088607594937, | |
| "grad_norm": 1.3208086599766524, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4676, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.3569620253164558, | |
| "grad_norm": 1.6255671967857097, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4817, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.3772151898734177, | |
| "grad_norm": 1.2914422612667809, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4777, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.3974683544303796, | |
| "grad_norm": 1.1553498242671723, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4765, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.4177215189873418, | |
| "grad_norm": 1.0985630409409104, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4745, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.437974683544304, | |
| "grad_norm": 1.1922053458640358, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4796, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.4582278481012658, | |
| "grad_norm": 1.3398045780563845, | |
| "learning_rate": 5e-06, | |
| "loss": 0.48, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.4784810126582277, | |
| "grad_norm": 1.177617617952355, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4825, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.4987341772151899, | |
| "grad_norm": 1.2525034867544784, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4753, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.518987341772152, | |
| "grad_norm": 1.2039537283128936, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4779, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.539240506329114, | |
| "grad_norm": 1.1297848909075034, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4789, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.5594936708860758, | |
| "grad_norm": 1.3174710848931364, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4776, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.579746835443038, | |
| "grad_norm": 1.175160970448449, | |
| "learning_rate": 5e-06, | |
| "loss": 0.478, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.2815667975924372, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4807, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.620253164556962, | |
| "grad_norm": 1.158977784005594, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4772, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.640506329113924, | |
| "grad_norm": 1.1864733415229585, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4697, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.660759493670886, | |
| "grad_norm": 1.2895166819237298, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4797, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.6810126582278482, | |
| "grad_norm": 1.300938286282075, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4745, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.70126582278481, | |
| "grad_norm": 1.1424310626896699, | |
| "learning_rate": 5e-06, | |
| "loss": 0.476, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.721518987341772, | |
| "grad_norm": 1.1429559951896378, | |
| "learning_rate": 5e-06, | |
| "loss": 0.478, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.7417721518987341, | |
| "grad_norm": 1.1739860272827067, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4783, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.7620253164556963, | |
| "grad_norm": 1.191849148804322, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4814, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.7822784810126582, | |
| "grad_norm": 1.162039130349595, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4823, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.80253164556962, | |
| "grad_norm": 1.2498690007156736, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4791, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.8227848101265822, | |
| "grad_norm": 1.2554926926315564, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4785, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.8430379746835444, | |
| "grad_norm": 1.1957986226654673, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4804, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.8632911392405065, | |
| "grad_norm": 1.1851282579533418, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4792, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.8835443037974684, | |
| "grad_norm": 1.1068170260766412, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4757, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.9037974683544303, | |
| "grad_norm": 1.2646052261464578, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4801, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.9240506329113924, | |
| "grad_norm": 1.333239155517521, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4804, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.9443037974683546, | |
| "grad_norm": 1.1435808455640823, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4845, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.9645569620253165, | |
| "grad_norm": 1.1466649702197023, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4829, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.9848101265822784, | |
| "grad_norm": 1.268837220918901, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4834, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.998987341772152, | |
| "eval_loss": 0.06870175153017044, | |
| "eval_runtime": 514.0164, | |
| "eval_samples_per_second": 25.882, | |
| "eval_steps_per_second": 0.405, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 2.0050632911392405, | |
| "grad_norm": 2.1408625149508023, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4569, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.0253164556962027, | |
| "grad_norm": 1.72871232368084, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3942, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0455696202531644, | |
| "grad_norm": 1.8639823449544832, | |
| "learning_rate": 5e-06, | |
| "loss": 0.391, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.0658227848101265, | |
| "grad_norm": 1.3817144113711173, | |
| "learning_rate": 5e-06, | |
| "loss": 0.387, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.0860759493670886, | |
| "grad_norm": 1.5869361079541535, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3871, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.1063291139240508, | |
| "grad_norm": 1.2460624418796462, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3851, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.1265822784810124, | |
| "grad_norm": 1.7394900572434608, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3943, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.1468354430379746, | |
| "grad_norm": 1.338895486927167, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3897, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.1670886075949367, | |
| "grad_norm": 1.247982467499197, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3931, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.187341772151899, | |
| "grad_norm": 1.3618812768218835, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3916, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.207594936708861, | |
| "grad_norm": 1.3590221552926487, | |
| "learning_rate": 5e-06, | |
| "loss": 0.389, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.2278481012658227, | |
| "grad_norm": 1.3797000672458826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3983, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.248101265822785, | |
| "grad_norm": 1.2368742400666088, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3934, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.268354430379747, | |
| "grad_norm": 1.2904792214170409, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3961, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.2886075949367086, | |
| "grad_norm": 1.5782227405689053, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3977, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.3088607594936708, | |
| "grad_norm": 1.4737079360584568, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3933, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.329113924050633, | |
| "grad_norm": 1.7303325343844742, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3993, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.349367088607595, | |
| "grad_norm": 1.4518621606722086, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3991, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.369620253164557, | |
| "grad_norm": 2.017892997447158, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3994, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.389873417721519, | |
| "grad_norm": 1.5068146289530309, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3997, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.410126582278481, | |
| "grad_norm": 1.353124441993217, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3992, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.430379746835443, | |
| "grad_norm": 1.4083869167690402, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3978, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.4506329113924052, | |
| "grad_norm": 1.2368765464544949, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3973, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.470886075949367, | |
| "grad_norm": 1.2620787369427364, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4011, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.491139240506329, | |
| "grad_norm": 1.319762068057727, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4009, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.511392405063291, | |
| "grad_norm": 1.508263073515773, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4048, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.5316455696202533, | |
| "grad_norm": 1.393725315494752, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3985, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.5518987341772155, | |
| "grad_norm": 1.7018393169883637, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3942, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.572151898734177, | |
| "grad_norm": 1.6451189563967772, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4009, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.5924050632911393, | |
| "grad_norm": 1.3903269923273418, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4023, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.6126582278481014, | |
| "grad_norm": 1.3438952595757327, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4075, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.632911392405063, | |
| "grad_norm": 1.6369476312471234, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4019, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.6531645569620252, | |
| "grad_norm": 1.4002674708903102, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4019, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.6734177215189874, | |
| "grad_norm": 1.5225886664411385, | |
| "learning_rate": 5e-06, | |
| "loss": 0.404, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.6936708860759495, | |
| "grad_norm": 1.378966215529765, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4067, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.7139240506329116, | |
| "grad_norm": 1.4243714009335353, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4051, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.7341772151898733, | |
| "grad_norm": 1.2628130063930583, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4047, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.7544303797468355, | |
| "grad_norm": 1.4068460224070376, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4003, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.7746835443037976, | |
| "grad_norm": 1.5186731540820997, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4064, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.7949367088607593, | |
| "grad_norm": 1.415787690993235, | |
| "learning_rate": 5e-06, | |
| "loss": 0.404, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.8151898734177214, | |
| "grad_norm": 1.4829742066812814, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4067, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.8354430379746836, | |
| "grad_norm": 1.3153556553473909, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4002, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.8556962025316457, | |
| "grad_norm": 1.258632308468112, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4088, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.875949367088608, | |
| "grad_norm": 1.3069199594530845, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4049, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.8962025316455695, | |
| "grad_norm": 1.348138135055361, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4055, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.9164556962025316, | |
| "grad_norm": 1.3516104016534718, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4076, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.9367088607594938, | |
| "grad_norm": 1.3482820531763435, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4162, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.9569620253164555, | |
| "grad_norm": 1.4854569589520752, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4042, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.9772151898734176, | |
| "grad_norm": 1.2602327451924493, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4082, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "eval_loss": 0.07233163714408875, | |
| "eval_runtime": 515.8273, | |
| "eval_samples_per_second": 25.792, | |
| "eval_steps_per_second": 0.403, | |
| "step": 1479 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "step": 1479, | |
| "total_flos": 2477170706350080.0, | |
| "train_loss": 0.4835145230064366, | |
| "train_runtime": 85503.9751, | |
| "train_samples_per_second": 8.868, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "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 | |
| } | |