| { | |
| "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": 2.619734647884394, | |
| "learning_rate": 1e-06, | |
| "loss": 0.7464, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04050632911392405, | |
| "grad_norm": 1.3110390929767555, | |
| "learning_rate": 1e-06, | |
| "loss": 0.6717, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.060759493670886074, | |
| "grad_norm": 1.3224952763615867, | |
| "learning_rate": 1e-06, | |
| "loss": 0.6512, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0810126582278481, | |
| "grad_norm": 1.3086489693521792, | |
| "learning_rate": 1e-06, | |
| "loss": 0.6346, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 1.3283087753221543, | |
| "learning_rate": 1e-06, | |
| "loss": 0.6233, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12151898734177215, | |
| "grad_norm": 1.1178465884062379, | |
| "learning_rate": 1e-06, | |
| "loss": 0.6163, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14177215189873418, | |
| "grad_norm": 1.2331918021301953, | |
| "learning_rate": 1e-06, | |
| "loss": 0.6108, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1620253164556962, | |
| "grad_norm": 1.6108411944833232, | |
| "learning_rate": 1e-06, | |
| "loss": 0.606, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18227848101265823, | |
| "grad_norm": 1.305554857542677, | |
| "learning_rate": 1e-06, | |
| "loss": 0.6047, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 1.793104250174951, | |
| "learning_rate": 1e-06, | |
| "loss": 0.6075, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22278481012658227, | |
| "grad_norm": 1.3859960281591825, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5992, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2430379746835443, | |
| "grad_norm": 1.2082896225688275, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5969, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.26329113924050634, | |
| "grad_norm": 1.4003875457794024, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5954, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.28354430379746837, | |
| "grad_norm": 1.2358927424738422, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5848, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3037974683544304, | |
| "grad_norm": 1.1299189101448799, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5947, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3240506329113924, | |
| "grad_norm": 1.2096301732069465, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5931, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34430379746835443, | |
| "grad_norm": 1.265546733701, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5935, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.36455696202531646, | |
| "grad_norm": 1.2106057402015653, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5882, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3848101265822785, | |
| "grad_norm": 1.2244051024429623, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5878, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": 1.5391402299054162, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5829, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4253164556962025, | |
| "grad_norm": 1.6439731235369328, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5787, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.44556962025316454, | |
| "grad_norm": 1.1897016150319843, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5835, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.46582278481012657, | |
| "grad_norm": 1.3865739063728386, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5823, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4860759493670886, | |
| "grad_norm": 2.0015538377147615, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5784, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5063291139240507, | |
| "grad_norm": 1.5045578486010718, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5817, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5265822784810127, | |
| "grad_norm": 1.4845620551057852, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5676, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5468354430379747, | |
| "grad_norm": 1.2137885977257916, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5767, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5670886075949367, | |
| "grad_norm": 1.297052710054918, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5719, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5873417721518988, | |
| "grad_norm": 1.2965186113129599, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5725, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6075949367088608, | |
| "grad_norm": 1.24410722407025, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5723, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6278481012658228, | |
| "grad_norm": 1.1833863223389307, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5775, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6481012658227848, | |
| "grad_norm": 1.3104465733977155, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5741, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6683544303797468, | |
| "grad_norm": 1.2338650139911316, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5734, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6886075949367089, | |
| "grad_norm": 1.21839346404376, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5727, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7088607594936709, | |
| "grad_norm": 1.2258284648816695, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5743, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7291139240506329, | |
| "grad_norm": 1.3322435098393544, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5762, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7493670886075949, | |
| "grad_norm": 1.1865951370746195, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5689, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.769620253164557, | |
| "grad_norm": 1.2650283942340912, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5652, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.789873417721519, | |
| "grad_norm": 1.219930623175008, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5687, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.810126582278481, | |
| "grad_norm": 1.363607101475477, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5688, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.830379746835443, | |
| "grad_norm": 1.1997640595608225, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5637, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.850632911392405, | |
| "grad_norm": 1.2303222791932693, | |
| "learning_rate": 1e-06, | |
| "loss": 0.571, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8708860759493671, | |
| "grad_norm": 1.3790821675678315, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5644, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8911392405063291, | |
| "grad_norm": 1.2067072176473832, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5694, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9113924050632911, | |
| "grad_norm": 1.1232626295201202, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5604, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9316455696202531, | |
| "grad_norm": 1.5684273306907883, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5649, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9518987341772152, | |
| "grad_norm": 1.2767752293401267, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5659, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9721518987341772, | |
| "grad_norm": 1.1792389357396524, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5631, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9924050632911392, | |
| "grad_norm": 1.2266783322802155, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5595, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9984810126582279, | |
| "eval_loss": 0.07029630243778229, | |
| "eval_runtime": 506.6286, | |
| "eval_samples_per_second": 26.26, | |
| "eval_steps_per_second": 0.411, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.0126582278481013, | |
| "grad_norm": 1.4987756778535, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5525, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0329113924050632, | |
| "grad_norm": 1.9500729588689496, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5399, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.0531645569620254, | |
| "grad_norm": 1.4999748530819137, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5373, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.0734177215189873, | |
| "grad_norm": 1.2207570745496787, | |
| "learning_rate": 1e-06, | |
| "loss": 0.539, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.0936708860759494, | |
| "grad_norm": 1.3096396345453205, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5363, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.1139240506329113, | |
| "grad_norm": 1.2468675797767559, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5378, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.1341772151898735, | |
| "grad_norm": 1.308458617043154, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5343, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.1544303797468354, | |
| "grad_norm": 1.4458279892029302, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5401, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.1746835443037975, | |
| "grad_norm": 1.248961755904894, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5376, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.1949367088607594, | |
| "grad_norm": 1.151828960652174, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5311, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.2151898734177216, | |
| "grad_norm": 1.3452591753168655, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5375, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2354430379746835, | |
| "grad_norm": 1.1913909788694494, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5327, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.2556962025316456, | |
| "grad_norm": 1.8379608066941815, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5377, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.2759493670886077, | |
| "grad_norm": 1.313639181526525, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5363, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.2962025316455696, | |
| "grad_norm": 1.3607185010254312, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5353, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.3164556962025316, | |
| "grad_norm": 1.3378542376279432, | |
| "learning_rate": 1e-06, | |
| "loss": 0.538, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.3367088607594937, | |
| "grad_norm": 1.4476502260378856, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5263, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.3569620253164558, | |
| "grad_norm": 1.2198770948675126, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5405, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.3772151898734177, | |
| "grad_norm": 1.3946891721788628, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5362, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.3974683544303796, | |
| "grad_norm": 1.2386757846192813, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5345, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.4177215189873418, | |
| "grad_norm": 1.2690690040554853, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5313, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.437974683544304, | |
| "grad_norm": 1.3231951956100838, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5369, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.4582278481012658, | |
| "grad_norm": 1.2514121906286146, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5363, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.4784810126582277, | |
| "grad_norm": 1.4236745549913041, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5391, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.4987341772151899, | |
| "grad_norm": 1.2248069146268987, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5308, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.518987341772152, | |
| "grad_norm": 1.3679267958028654, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5333, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.539240506329114, | |
| "grad_norm": 1.1667252140959936, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5342, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.5594936708860758, | |
| "grad_norm": 1.5407484322787957, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5321, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.579746835443038, | |
| "grad_norm": 1.2484454202278648, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5323, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.1067074748834411, | |
| "learning_rate": 1e-06, | |
| "loss": 0.535, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.620253164556962, | |
| "grad_norm": 1.1406466701204283, | |
| "learning_rate": 1e-06, | |
| "loss": 0.53, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.640506329113924, | |
| "grad_norm": 1.333947636738561, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5229, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.660759493670886, | |
| "grad_norm": 1.1745013725212081, | |
| "learning_rate": 1e-06, | |
| "loss": 0.532, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.6810126582278482, | |
| "grad_norm": 1.2364588136381158, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5266, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.70126582278481, | |
| "grad_norm": 1.2994933526015593, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5285, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.721518987341772, | |
| "grad_norm": 1.2235003239800508, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5295, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.7417721518987341, | |
| "grad_norm": 1.2450922426064477, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5297, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.7620253164556963, | |
| "grad_norm": 1.273509950684057, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5328, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.7822784810126582, | |
| "grad_norm": 1.3268221155700262, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5334, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.80253164556962, | |
| "grad_norm": 1.3435835086673222, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5302, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.8227848101265822, | |
| "grad_norm": 1.4154073605673325, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5292, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.8430379746835444, | |
| "grad_norm": 1.2933679126356026, | |
| "learning_rate": 1e-06, | |
| "loss": 0.531, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.8632911392405065, | |
| "grad_norm": 1.2402647320314202, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5291, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.8835443037974684, | |
| "grad_norm": 1.193502227980034, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5251, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.9037974683544303, | |
| "grad_norm": 1.2238044858944368, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5293, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.9240506329113924, | |
| "grad_norm": 1.1862867123066843, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5302, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.9443037974683546, | |
| "grad_norm": 3.031186095809816, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5342, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.9645569620253165, | |
| "grad_norm": 1.2302193007584743, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5325, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.9848101265822784, | |
| "grad_norm": 1.165773133838534, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5327, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.998987341772152, | |
| "eval_loss": 0.0687665268778801, | |
| "eval_runtime": 507.2189, | |
| "eval_samples_per_second": 26.229, | |
| "eval_steps_per_second": 0.41, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 2.0050632911392405, | |
| "grad_norm": 1.5109756330932536, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5186, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.0253164556962027, | |
| "grad_norm": 1.3011762315505613, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5045, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0455696202531644, | |
| "grad_norm": 1.310078278306769, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5055, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.0658227848101265, | |
| "grad_norm": 1.1825460071461764, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5013, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.0860759493670886, | |
| "grad_norm": 1.2271036849087198, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5003, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.1063291139240508, | |
| "grad_norm": 1.3738002207601139, | |
| "learning_rate": 1e-06, | |
| "loss": 0.4983, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.1265822784810124, | |
| "grad_norm": 1.5767467753561857, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5076, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.1468354430379746, | |
| "grad_norm": 1.2576493114793463, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5022, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.1670886075949367, | |
| "grad_norm": 1.4340379170710251, | |
| "learning_rate": 1e-06, | |
| "loss": 0.504, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.187341772151899, | |
| "grad_norm": 1.3466263742794538, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5018, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.207594936708861, | |
| "grad_norm": 1.3135843161677987, | |
| "learning_rate": 1e-06, | |
| "loss": 0.4977, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.2278481012658227, | |
| "grad_norm": 1.3416842121020573, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5085, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.248101265822785, | |
| "grad_norm": 1.3471741637598718, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5033, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.268354430379747, | |
| "grad_norm": 1.440841937469427, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5041, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.2886075949367086, | |
| "grad_norm": 1.2222358962574047, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5059, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.3088607594936708, | |
| "grad_norm": 1.2473884146385428, | |
| "learning_rate": 1e-06, | |
| "loss": 0.4994, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.329113924050633, | |
| "grad_norm": 1.240146365885156, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5075, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.349367088607595, | |
| "grad_norm": 1.4035406768534098, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5063, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.369620253164557, | |
| "grad_norm": 1.2571413637770001, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5065, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.389873417721519, | |
| "grad_norm": 1.3554388776685469, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5057, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.410126582278481, | |
| "grad_norm": 1.2294989792596434, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5049, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.430379746835443, | |
| "grad_norm": 1.3430103042723693, | |
| "learning_rate": 1e-06, | |
| "loss": 0.503, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.4506329113924052, | |
| "grad_norm": 1.2400614179737601, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5012, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.470886075949367, | |
| "grad_norm": 1.313749813003456, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5046, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.491139240506329, | |
| "grad_norm": 1.6716580704347377, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5033, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.511392405063291, | |
| "grad_norm": 1.4652147251621395, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5077, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.5316455696202533, | |
| "grad_norm": 1.408598695635922, | |
| "learning_rate": 1e-06, | |
| "loss": 0.4998, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.5518987341772155, | |
| "grad_norm": 1.296610081566108, | |
| "learning_rate": 1e-06, | |
| "loss": 0.4944, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.572151898734177, | |
| "grad_norm": 1.189136444524376, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5016, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.5924050632911393, | |
| "grad_norm": 1.5529027245769111, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5044, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.6126582278481014, | |
| "grad_norm": 1.6669279525565228, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5096, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.632911392405063, | |
| "grad_norm": 1.2610161044084751, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5028, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.6531645569620252, | |
| "grad_norm": 1.2905853928976894, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5016, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.6734177215189874, | |
| "grad_norm": 1.1841307795553861, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5038, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.6936708860759495, | |
| "grad_norm": 1.4445740618141194, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5067, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.7139240506329116, | |
| "grad_norm": 1.2667753935755368, | |
| "learning_rate": 1e-06, | |
| "loss": 0.504, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.7341772151898733, | |
| "grad_norm": 6.693530671084289, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5022, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.7544303797468355, | |
| "grad_norm": 1.2648668198224975, | |
| "learning_rate": 1e-06, | |
| "loss": 0.498, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.7746835443037976, | |
| "grad_norm": 1.348036748024328, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5033, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.7949367088607593, | |
| "grad_norm": 1.14937166812925, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5013, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.8151898734177214, | |
| "grad_norm": 1.5681826175046818, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5034, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.8354430379746836, | |
| "grad_norm": 1.4069758036447177, | |
| "learning_rate": 1e-06, | |
| "loss": 0.4962, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.8556962025316457, | |
| "grad_norm": 1.2870578408991291, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5055, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.875949367088608, | |
| "grad_norm": 1.3597008765741436, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5003, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.8962025316455695, | |
| "grad_norm": 1.2088761309707992, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5007, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.9164556962025316, | |
| "grad_norm": 1.2311447055966478, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5036, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.9367088607594938, | |
| "grad_norm": 1.1855473023997445, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5124, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.9569620253164555, | |
| "grad_norm": 1.3332973643566783, | |
| "learning_rate": 1e-06, | |
| "loss": 0.498, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.9772151898734176, | |
| "grad_norm": 1.3545952990313994, | |
| "learning_rate": 1e-06, | |
| "loss": 0.5031, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "eval_loss": 0.06836653500795364, | |
| "eval_runtime": 506.6941, | |
| "eval_samples_per_second": 26.256, | |
| "eval_steps_per_second": 0.411, | |
| "step": 1479 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "step": 1479, | |
| "total_flos": 2477170706350080.0, | |
| "train_loss": 0.5417223895539135, | |
| "train_runtime": 84138.7543, | |
| "train_samples_per_second": 9.012, | |
| "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 | |
| } | |