| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9984, | |
| "eval_steps": 500, | |
| "global_step": 156, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0064, | |
| "grad_norm": 4.46052360534668, | |
| "learning_rate": 0.0, | |
| "loss": 1.1926, | |
| "mean_token_accuracy": 0.7001730054616928, | |
| "num_tokens": 14640.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0128, | |
| "grad_norm": 3.8626222610473633, | |
| "learning_rate": 6.25e-07, | |
| "loss": 1.3138, | |
| "mean_token_accuracy": 0.6548218131065369, | |
| "num_tokens": 27693.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0192, | |
| "grad_norm": 3.952249050140381, | |
| "learning_rate": 1.25e-06, | |
| "loss": 1.3569, | |
| "mean_token_accuracy": 0.6562561392784119, | |
| "num_tokens": 40525.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0256, | |
| "grad_norm": 4.109567165374756, | |
| "learning_rate": 1.8750000000000003e-06, | |
| "loss": 1.3472, | |
| "mean_token_accuracy": 0.656329445540905, | |
| "num_tokens": 55822.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 4.119779586791992, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.3473, | |
| "mean_token_accuracy": 0.6558413058519363, | |
| "num_tokens": 70670.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0384, | |
| "grad_norm": 3.3819665908813477, | |
| "learning_rate": 3.125e-06, | |
| "loss": 1.4108, | |
| "mean_token_accuracy": 0.6545125097036362, | |
| "num_tokens": 84335.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0448, | |
| "grad_norm": 3.7010326385498047, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.2498, | |
| "mean_token_accuracy": 0.6681988388299942, | |
| "num_tokens": 95857.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0512, | |
| "grad_norm": 3.496901035308838, | |
| "learning_rate": 4.3750000000000005e-06, | |
| "loss": 1.2894, | |
| "mean_token_accuracy": 0.6635143309831619, | |
| "num_tokens": 109806.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0576, | |
| "grad_norm": 3.2937991619110107, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2092, | |
| "mean_token_accuracy": 0.6767952516674995, | |
| "num_tokens": 125631.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 6.788699626922607, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4017, | |
| "mean_token_accuracy": 0.6475312933325768, | |
| "num_tokens": 140029.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0704, | |
| "grad_norm": 8.16016674041748, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4182, | |
| "mean_token_accuracy": 0.6417016983032227, | |
| "num_tokens": 153863.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0768, | |
| "grad_norm": 7.313711643218994, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2493, | |
| "mean_token_accuracy": 0.6722374185919762, | |
| "num_tokens": 169366.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0832, | |
| "grad_norm": 7.297321319580078, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2984, | |
| "mean_token_accuracy": 0.6654682904481888, | |
| "num_tokens": 182285.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0896, | |
| "grad_norm": 5.980355262756348, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3728, | |
| "mean_token_accuracy": 0.6474195793271065, | |
| "num_tokens": 200009.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 5.341892242431641, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1786, | |
| "mean_token_accuracy": 0.6898260414600372, | |
| "num_tokens": 217172.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1024, | |
| "grad_norm": 5.044528961181641, | |
| "learning_rate": 5e-06, | |
| "loss": 1.473, | |
| "mean_token_accuracy": 0.6259094700217247, | |
| "num_tokens": 232308.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1088, | |
| "grad_norm": 4.829463005065918, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4725, | |
| "mean_token_accuracy": 0.6119906902313232, | |
| "num_tokens": 243772.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1152, | |
| "grad_norm": 3.969775676727295, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2455, | |
| "mean_token_accuracy": 0.6761033684015274, | |
| "num_tokens": 260674.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1216, | |
| "grad_norm": 4.059275150299072, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3388, | |
| "mean_token_accuracy": 0.6495725736021996, | |
| "num_tokens": 276352.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 3.6464030742645264, | |
| "learning_rate": 5e-06, | |
| "loss": 1.277, | |
| "mean_token_accuracy": 0.6567010655999184, | |
| "num_tokens": 291765.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1344, | |
| "grad_norm": 4.572549819946289, | |
| "learning_rate": 5e-06, | |
| "loss": 1.349, | |
| "mean_token_accuracy": 0.6503036767244339, | |
| "num_tokens": 303401.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1408, | |
| "grad_norm": 3.3478147983551025, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3734, | |
| "mean_token_accuracy": 0.657492570579052, | |
| "num_tokens": 318861.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1472, | |
| "grad_norm": 3.8337855339050293, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2852, | |
| "mean_token_accuracy": 0.6548745334148407, | |
| "num_tokens": 330566.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1536, | |
| "grad_norm": 4.150561809539795, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2668, | |
| "mean_token_accuracy": 0.6780209168791771, | |
| "num_tokens": 341999.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 5.090829849243164, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3751, | |
| "mean_token_accuracy": 0.6607428789138794, | |
| "num_tokens": 358011.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1664, | |
| "grad_norm": 4.033487319946289, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2884, | |
| "mean_token_accuracy": 0.6732476428151131, | |
| "num_tokens": 371643.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1728, | |
| "grad_norm": 3.5941057205200195, | |
| "learning_rate": 5e-06, | |
| "loss": 1.047, | |
| "mean_token_accuracy": 0.7033858001232147, | |
| "num_tokens": 383610.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1792, | |
| "grad_norm": 3.3021464347839355, | |
| "learning_rate": 5e-06, | |
| "loss": 1.233, | |
| "mean_token_accuracy": 0.6834521070122719, | |
| "num_tokens": 398590.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1856, | |
| "grad_norm": 4.259124279022217, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2961, | |
| "mean_token_accuracy": 0.6622931659221649, | |
| "num_tokens": 409575.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 3.220076322555542, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0836, | |
| "mean_token_accuracy": 0.7075582221150398, | |
| "num_tokens": 423461.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1984, | |
| "grad_norm": 3.3759732246398926, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2671, | |
| "mean_token_accuracy": 0.6733162626624107, | |
| "num_tokens": 439184.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2048, | |
| "grad_norm": 13.060998916625977, | |
| "learning_rate": 5e-06, | |
| "loss": 1.263, | |
| "mean_token_accuracy": 0.6846785917878151, | |
| "num_tokens": 451887.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2112, | |
| "grad_norm": 3.4759275913238525, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2905, | |
| "mean_token_accuracy": 0.6659640669822693, | |
| "num_tokens": 466293.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2176, | |
| "grad_norm": 3.615352153778076, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3252, | |
| "mean_token_accuracy": 0.6587846502661705, | |
| "num_tokens": 482281.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 3.8253462314605713, | |
| "learning_rate": 5e-06, | |
| "loss": 1.284, | |
| "mean_token_accuracy": 0.6593102514743805, | |
| "num_tokens": 494866.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2304, | |
| "grad_norm": 3.8242146968841553, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4445, | |
| "mean_token_accuracy": 0.6356016099452972, | |
| "num_tokens": 509737.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2368, | |
| "grad_norm": 3.3142733573913574, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3622, | |
| "mean_token_accuracy": 0.6442921012639999, | |
| "num_tokens": 524987.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2432, | |
| "grad_norm": 3.3738458156585693, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5074, | |
| "mean_token_accuracy": 0.611025758087635, | |
| "num_tokens": 540515.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2496, | |
| "grad_norm": 3.5873780250549316, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2594, | |
| "mean_token_accuracy": 0.672322042286396, | |
| "num_tokens": 554108.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 3.3734376430511475, | |
| "learning_rate": 5e-06, | |
| "loss": 1.386, | |
| "mean_token_accuracy": 0.6393688693642616, | |
| "num_tokens": 570067.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2624, | |
| "grad_norm": 3.8531699180603027, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2987, | |
| "mean_token_accuracy": 0.6596419736742973, | |
| "num_tokens": 583435.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2688, | |
| "grad_norm": 3.7436106204986572, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3517, | |
| "mean_token_accuracy": 0.6706470102071762, | |
| "num_tokens": 596105.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2752, | |
| "grad_norm": 3.717897653579712, | |
| "learning_rate": 5e-06, | |
| "loss": 1.147, | |
| "mean_token_accuracy": 0.7020372673869133, | |
| "num_tokens": 610310.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2816, | |
| "grad_norm": 3.6992413997650146, | |
| "learning_rate": 5e-06, | |
| "loss": 1.19, | |
| "mean_token_accuracy": 0.6930102109909058, | |
| "num_tokens": 624612.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 3.5740365982055664, | |
| "learning_rate": 5e-06, | |
| "loss": 1.368, | |
| "mean_token_accuracy": 0.6361823007464409, | |
| "num_tokens": 637714.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2944, | |
| "grad_norm": 3.959993600845337, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2512, | |
| "mean_token_accuracy": 0.6959773004055023, | |
| "num_tokens": 650333.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3008, | |
| "grad_norm": 3.906562089920044, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2867, | |
| "mean_token_accuracy": 0.6637914702296257, | |
| "num_tokens": 664887.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3072, | |
| "grad_norm": 3.9186768531799316, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3578, | |
| "mean_token_accuracy": 0.6380120068788528, | |
| "num_tokens": 676568.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3136, | |
| "grad_norm": 3.360166549682617, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0643, | |
| "mean_token_accuracy": 0.7167638763785362, | |
| "num_tokens": 690799.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 3.504518508911133, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2447, | |
| "mean_token_accuracy": 0.6620298400521278, | |
| "num_tokens": 706489.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3264, | |
| "grad_norm": 3.65311861038208, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4979, | |
| "mean_token_accuracy": 0.6288957595825195, | |
| "num_tokens": 721499.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3328, | |
| "grad_norm": 3.348665475845337, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3043, | |
| "mean_token_accuracy": 0.6755396276712418, | |
| "num_tokens": 738238.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3392, | |
| "grad_norm": 3.7475781440734863, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3655, | |
| "mean_token_accuracy": 0.6580836474895477, | |
| "num_tokens": 750933.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.3456, | |
| "grad_norm": 3.65537691116333, | |
| "learning_rate": 5e-06, | |
| "loss": 1.428, | |
| "mean_token_accuracy": 0.6435032188892365, | |
| "num_tokens": 766190.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 3.4737765789031982, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3459, | |
| "mean_token_accuracy": 0.6618407666683197, | |
| "num_tokens": 781058.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3584, | |
| "grad_norm": 3.7944328784942627, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4812, | |
| "mean_token_accuracy": 0.6265006363391876, | |
| "num_tokens": 793591.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3648, | |
| "grad_norm": 3.4754698276519775, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1157, | |
| "mean_token_accuracy": 0.6880814656615257, | |
| "num_tokens": 807562.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3712, | |
| "grad_norm": 3.345503568649292, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2552, | |
| "mean_token_accuracy": 0.6683396399021149, | |
| "num_tokens": 822029.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.3776, | |
| "grad_norm": 3.702852487564087, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2624, | |
| "mean_token_accuracy": 0.6913647577166557, | |
| "num_tokens": 833999.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 3.169661045074463, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3735, | |
| "mean_token_accuracy": 0.6340024396777153, | |
| "num_tokens": 848952.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3904, | |
| "grad_norm": 3.8648996353149414, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2589, | |
| "mean_token_accuracy": 0.6712265312671661, | |
| "num_tokens": 865078.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3968, | |
| "grad_norm": 3.6297190189361572, | |
| "learning_rate": 5e-06, | |
| "loss": 1.228, | |
| "mean_token_accuracy": 0.6683308631181717, | |
| "num_tokens": 877815.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4032, | |
| "grad_norm": 3.3031067848205566, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3284, | |
| "mean_token_accuracy": 0.6419568583369255, | |
| "num_tokens": 891433.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4096, | |
| "grad_norm": 3.6126585006713867, | |
| "learning_rate": 5e-06, | |
| "loss": 1.327, | |
| "mean_token_accuracy": 0.6622776314616203, | |
| "num_tokens": 904268.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 3.407878875732422, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3261, | |
| "mean_token_accuracy": 0.6527406051754951, | |
| "num_tokens": 919814.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4224, | |
| "grad_norm": 3.381817102432251, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2016, | |
| "mean_token_accuracy": 0.674388200044632, | |
| "num_tokens": 933076.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4288, | |
| "grad_norm": 3.4750583171844482, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2737, | |
| "mean_token_accuracy": 0.6750325560569763, | |
| "num_tokens": 947949.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.4352, | |
| "grad_norm": 3.401789426803589, | |
| "learning_rate": 5e-06, | |
| "loss": 1.443, | |
| "mean_token_accuracy": 0.6314026713371277, | |
| "num_tokens": 963300.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4416, | |
| "grad_norm": 3.7318997383117676, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3147, | |
| "mean_token_accuracy": 0.6670505329966545, | |
| "num_tokens": 978591.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 3.5171058177948, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2636, | |
| "mean_token_accuracy": 0.6640981435775757, | |
| "num_tokens": 995710.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4544, | |
| "grad_norm": 3.5986971855163574, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4008, | |
| "mean_token_accuracy": 0.6460948511958122, | |
| "num_tokens": 1008761.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4608, | |
| "grad_norm": 3.790513753890991, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0588, | |
| "mean_token_accuracy": 0.7220645099878311, | |
| "num_tokens": 1022118.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4672, | |
| "grad_norm": 3.2633607387542725, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4292, | |
| "mean_token_accuracy": 0.633380301296711, | |
| "num_tokens": 1036809.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.4736, | |
| "grad_norm": 4.51404333114624, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2447, | |
| "mean_token_accuracy": 0.6805145666003227, | |
| "num_tokens": 1051135.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 3.9093401432037354, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2158, | |
| "mean_token_accuracy": 0.6765370890498161, | |
| "num_tokens": 1066566.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4864, | |
| "grad_norm": 3.798604726791382, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2877, | |
| "mean_token_accuracy": 0.6586913466453552, | |
| "num_tokens": 1080474.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.4928, | |
| "grad_norm": 3.8617875576019287, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3414, | |
| "mean_token_accuracy": 0.6375375539064407, | |
| "num_tokens": 1092414.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.4992, | |
| "grad_norm": 3.4888036251068115, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3153, | |
| "mean_token_accuracy": 0.6624401807785034, | |
| "num_tokens": 1105750.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5056, | |
| "grad_norm": 4.31488037109375, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5732, | |
| "mean_token_accuracy": 0.631282813847065, | |
| "num_tokens": 1119046.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 3.053265333175659, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1599, | |
| "mean_token_accuracy": 0.6818074658513069, | |
| "num_tokens": 1135088.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5184, | |
| "grad_norm": 3.616725444793701, | |
| "learning_rate": 5e-06, | |
| "loss": 1.43, | |
| "mean_token_accuracy": 0.6406295001506805, | |
| "num_tokens": 1151156.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5248, | |
| "grad_norm": 4.136235237121582, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0219, | |
| "mean_token_accuracy": 0.730844259262085, | |
| "num_tokens": 1167434.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5312, | |
| "grad_norm": 3.338418483734131, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2563, | |
| "mean_token_accuracy": 0.6696086227893829, | |
| "num_tokens": 1180703.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5376, | |
| "grad_norm": 4.320113658905029, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3359, | |
| "mean_token_accuracy": 0.6449860632419586, | |
| "num_tokens": 1192466.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 3.6109604835510254, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3403, | |
| "mean_token_accuracy": 0.6509855315089226, | |
| "num_tokens": 1207465.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5504, | |
| "grad_norm": 3.9164552688598633, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2705, | |
| "mean_token_accuracy": 0.657896488904953, | |
| "num_tokens": 1218611.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5568, | |
| "grad_norm": 3.731842279434204, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2964, | |
| "mean_token_accuracy": 0.6592853665351868, | |
| "num_tokens": 1231942.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5632, | |
| "grad_norm": 3.651313304901123, | |
| "learning_rate": 5e-06, | |
| "loss": 1.36, | |
| "mean_token_accuracy": 0.6576117277145386, | |
| "num_tokens": 1246108.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5696, | |
| "grad_norm": 3.089268445968628, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2009, | |
| "mean_token_accuracy": 0.6747561246156693, | |
| "num_tokens": 1261356.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 3.238022565841675, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3602, | |
| "mean_token_accuracy": 0.6399379670619965, | |
| "num_tokens": 1277200.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5824, | |
| "grad_norm": 3.467700481414795, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3403, | |
| "mean_token_accuracy": 0.6624496802687645, | |
| "num_tokens": 1292186.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.5888, | |
| "grad_norm": 3.325700283050537, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2627, | |
| "mean_token_accuracy": 0.6559372171759605, | |
| "num_tokens": 1304719.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.5952, | |
| "grad_norm": 3.621305227279663, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1766, | |
| "mean_token_accuracy": 0.6822386905550957, | |
| "num_tokens": 1318790.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6016, | |
| "grad_norm": 3.729935884475708, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3674, | |
| "mean_token_accuracy": 0.645961195230484, | |
| "num_tokens": 1329771.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 3.6264734268188477, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1152, | |
| "mean_token_accuracy": 0.687596932053566, | |
| "num_tokens": 1342886.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6144, | |
| "grad_norm": 3.485283136367798, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4425, | |
| "mean_token_accuracy": 0.6406073719263077, | |
| "num_tokens": 1358395.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6208, | |
| "grad_norm": 3.9530715942382812, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2683, | |
| "mean_token_accuracy": 0.6643862873315811, | |
| "num_tokens": 1371799.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6272, | |
| "grad_norm": 4.173793315887451, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2914, | |
| "mean_token_accuracy": 0.660434328019619, | |
| "num_tokens": 1383470.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6336, | |
| "grad_norm": 3.614288330078125, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2038, | |
| "mean_token_accuracy": 0.6892227753996849, | |
| "num_tokens": 1400378.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 2.9820358753204346, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1759, | |
| "mean_token_accuracy": 0.6901198551058769, | |
| "num_tokens": 1417726.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6464, | |
| "grad_norm": 3.3349997997283936, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3748, | |
| "mean_token_accuracy": 0.6374614164233208, | |
| "num_tokens": 1433643.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.6528, | |
| "grad_norm": 3.2100603580474854, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3996, | |
| "mean_token_accuracy": 0.6497422009706497, | |
| "num_tokens": 1449613.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.6592, | |
| "grad_norm": 3.778851270675659, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0333, | |
| "mean_token_accuracy": 0.7377151399850845, | |
| "num_tokens": 1462451.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.6656, | |
| "grad_norm": 3.1992948055267334, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3104, | |
| "mean_token_accuracy": 0.6540233194828033, | |
| "num_tokens": 1476702.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 3.510753631591797, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4638, | |
| "mean_token_accuracy": 0.6315533146262169, | |
| "num_tokens": 1491797.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6784, | |
| "grad_norm": 3.976029396057129, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5173, | |
| "mean_token_accuracy": 0.6174216568470001, | |
| "num_tokens": 1506937.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.6848, | |
| "grad_norm": 4.135453224182129, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2671, | |
| "mean_token_accuracy": 0.6688078567385674, | |
| "num_tokens": 1517912.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.6912, | |
| "grad_norm": 3.417698621749878, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3911, | |
| "mean_token_accuracy": 0.653182253241539, | |
| "num_tokens": 1534828.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.6976, | |
| "grad_norm": 3.1860220432281494, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1702, | |
| "mean_token_accuracy": 0.6850942298769951, | |
| "num_tokens": 1549388.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 4.109538555145264, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9738, | |
| "mean_token_accuracy": 0.7242774963378906, | |
| "num_tokens": 1561336.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7104, | |
| "grad_norm": 3.6836867332458496, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1749, | |
| "mean_token_accuracy": 0.6976689174771309, | |
| "num_tokens": 1576039.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.7168, | |
| "grad_norm": 3.6196529865264893, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2509, | |
| "mean_token_accuracy": 0.6862899139523506, | |
| "num_tokens": 1590356.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7232, | |
| "grad_norm": 3.6636641025543213, | |
| "learning_rate": 5e-06, | |
| "loss": 1.222, | |
| "mean_token_accuracy": 0.6742222532629967, | |
| "num_tokens": 1603828.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.7296, | |
| "grad_norm": 3.1560022830963135, | |
| "learning_rate": 5e-06, | |
| "loss": 1.238, | |
| "mean_token_accuracy": 0.6736825779080391, | |
| "num_tokens": 1621001.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 3.1845784187316895, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3708, | |
| "mean_token_accuracy": 0.6455038785934448, | |
| "num_tokens": 1636499.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7424, | |
| "grad_norm": 3.5999317169189453, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1897, | |
| "mean_token_accuracy": 0.6913699880242348, | |
| "num_tokens": 1649043.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.7488, | |
| "grad_norm": 3.9774956703186035, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0401, | |
| "mean_token_accuracy": 0.7169342339038849, | |
| "num_tokens": 1663873.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.7552, | |
| "grad_norm": 3.3667006492614746, | |
| "learning_rate": 5e-06, | |
| "loss": 1.389, | |
| "mean_token_accuracy": 0.6400957256555557, | |
| "num_tokens": 1679667.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.7616, | |
| "grad_norm": 3.5805838108062744, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3896, | |
| "mean_token_accuracy": 0.6595878526568413, | |
| "num_tokens": 1695115.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 3.8038456439971924, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4199, | |
| "mean_token_accuracy": 0.6296796873211861, | |
| "num_tokens": 1707134.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7744, | |
| "grad_norm": 3.626406669616699, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2602, | |
| "mean_token_accuracy": 0.6764451712369919, | |
| "num_tokens": 1720062.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.7808, | |
| "grad_norm": 4.185618877410889, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4208, | |
| "mean_token_accuracy": 0.6561515182256699, | |
| "num_tokens": 1731658.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.7872, | |
| "grad_norm": 3.6125693321228027, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1589, | |
| "mean_token_accuracy": 0.6781378239393234, | |
| "num_tokens": 1747033.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.7936, | |
| "grad_norm": 4.1037373542785645, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2256, | |
| "mean_token_accuracy": 0.6652502194046974, | |
| "num_tokens": 1758454.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 3.3770744800567627, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2673, | |
| "mean_token_accuracy": 0.6793160140514374, | |
| "num_tokens": 1773549.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8064, | |
| "grad_norm": 3.3607754707336426, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2752, | |
| "mean_token_accuracy": 0.6853690519928932, | |
| "num_tokens": 1789080.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8128, | |
| "grad_norm": 3.806748390197754, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1944, | |
| "mean_token_accuracy": 0.6872068718075752, | |
| "num_tokens": 1801796.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.8192, | |
| "grad_norm": 3.8479700088500977, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3977, | |
| "mean_token_accuracy": 0.636077530682087, | |
| "num_tokens": 1814242.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8256, | |
| "grad_norm": 3.4976117610931396, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1139, | |
| "mean_token_accuracy": 0.697039358317852, | |
| "num_tokens": 1826839.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 3.545767307281494, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4587, | |
| "mean_token_accuracy": 0.6343350037932396, | |
| "num_tokens": 1840704.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8384, | |
| "grad_norm": 3.3037948608398438, | |
| "learning_rate": 5e-06, | |
| "loss": 1.051, | |
| "mean_token_accuracy": 0.7136509492993355, | |
| "num_tokens": 1854753.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.8448, | |
| "grad_norm": 3.749946117401123, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5613, | |
| "mean_token_accuracy": 0.6120798960328102, | |
| "num_tokens": 1868075.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8512, | |
| "grad_norm": 3.2564704418182373, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5152, | |
| "mean_token_accuracy": 0.6301259547472, | |
| "num_tokens": 1883671.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.8576, | |
| "grad_norm": 3.6490490436553955, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3408, | |
| "mean_token_accuracy": 0.657665990293026, | |
| "num_tokens": 1895662.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 3.407827615737915, | |
| "learning_rate": 5e-06, | |
| "loss": 1.6605, | |
| "mean_token_accuracy": 0.5928493365645409, | |
| "num_tokens": 1910847.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8704, | |
| "grad_norm": 4.415482521057129, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1946, | |
| "mean_token_accuracy": 0.6526624895632267, | |
| "num_tokens": 1925173.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.8768, | |
| "grad_norm": 4.364404201507568, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3597, | |
| "mean_token_accuracy": 0.6597945764660835, | |
| "num_tokens": 1938507.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.8832, | |
| "grad_norm": 3.498443603515625, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2335, | |
| "mean_token_accuracy": 0.6793266087770462, | |
| "num_tokens": 1955459.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.8896, | |
| "grad_norm": 3.321516275405884, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1991, | |
| "mean_token_accuracy": 0.6588682383298874, | |
| "num_tokens": 1970350.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 3.556004524230957, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1146, | |
| "mean_token_accuracy": 0.7137203514575958, | |
| "num_tokens": 1984042.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9024, | |
| "grad_norm": 3.075051784515381, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2796, | |
| "mean_token_accuracy": 0.6648645251989365, | |
| "num_tokens": 2000795.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.9088, | |
| "grad_norm": 3.5248730182647705, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2528, | |
| "mean_token_accuracy": 0.6755008921027184, | |
| "num_tokens": 2015306.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.9152, | |
| "grad_norm": 3.545891284942627, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5914, | |
| "mean_token_accuracy": 0.6275190636515617, | |
| "num_tokens": 2030477.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.9216, | |
| "grad_norm": 3.4129698276519775, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1794, | |
| "mean_token_accuracy": 0.6718302294611931, | |
| "num_tokens": 2045094.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 4.104367733001709, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2672, | |
| "mean_token_accuracy": 0.680908165872097, | |
| "num_tokens": 2059572.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.9344, | |
| "grad_norm": 3.316425323486328, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4394, | |
| "mean_token_accuracy": 0.6278339251875877, | |
| "num_tokens": 2074507.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.9408, | |
| "grad_norm": 3.6546125411987305, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1124, | |
| "mean_token_accuracy": 0.6924281641840935, | |
| "num_tokens": 2087040.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.9472, | |
| "grad_norm": 3.6782755851745605, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3804, | |
| "mean_token_accuracy": 0.6391346678137779, | |
| "num_tokens": 2101730.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.9536, | |
| "grad_norm": 3.386892080307007, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2437, | |
| "mean_token_accuracy": 0.6677525192499161, | |
| "num_tokens": 2116581.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 3.5542984008789062, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0982, | |
| "mean_token_accuracy": 0.7068964689970016, | |
| "num_tokens": 2131452.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9664, | |
| "grad_norm": 3.5495564937591553, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4026, | |
| "mean_token_accuracy": 0.6545470431447029, | |
| "num_tokens": 2147428.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.9728, | |
| "grad_norm": 3.4057626724243164, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3493, | |
| "mean_token_accuracy": 0.6586249023675919, | |
| "num_tokens": 2164711.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.9792, | |
| "grad_norm": 3.815967559814453, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3319, | |
| "mean_token_accuracy": 0.6602702289819717, | |
| "num_tokens": 2177075.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.9856, | |
| "grad_norm": 3.8833365440368652, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3236, | |
| "mean_token_accuracy": 0.6528388634324074, | |
| "num_tokens": 2190015.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "grad_norm": 3.010931968688965, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3359, | |
| "mean_token_accuracy": 0.6606268882751465, | |
| "num_tokens": 2208904.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9984, | |
| "grad_norm": 3.366220474243164, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2807, | |
| "mean_token_accuracy": 0.6731663048267365, | |
| "num_tokens": 2223354.0, | |
| "step": 156 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 156, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6046380687360.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |