| { | |
| "best_metric": 0.20296970009803772, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 2.0106331561140647, | |
| "eval_steps": 25, | |
| "global_step": 130, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015466408893185114, | |
| "grad_norm": 0.34002751111984253, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.4411, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015466408893185114, | |
| "eval_loss": 1.1426082849502563, | |
| "eval_runtime": 7.1707, | |
| "eval_samples_per_second": 6.973, | |
| "eval_steps_per_second": 6.973, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.030932817786370227, | |
| "grad_norm": 0.4139275550842285, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.4555, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04639922667955534, | |
| "grad_norm": 0.481924831867218, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.424, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.061865635572740454, | |
| "grad_norm": 0.4299992322921753, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.3855, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07733204446592556, | |
| "grad_norm": 0.42819246649742126, | |
| "learning_rate": 0.00015, | |
| "loss": 0.4611, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09279845335911067, | |
| "grad_norm": 0.9149371385574341, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.7301, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1082648622522958, | |
| "grad_norm": 1.1431907415390015, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.7905, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12373127114548091, | |
| "grad_norm": 1.802942156791687, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.6581, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13919768003866603, | |
| "grad_norm": 2.6315770149230957, | |
| "learning_rate": 0.00027, | |
| "loss": 0.6625, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15466408893185113, | |
| "grad_norm": 1.5995557308197021, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5518, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17013049782503625, | |
| "grad_norm": 1.1412254571914673, | |
| "learning_rate": 0.00029994859874633357, | |
| "loss": 0.4248, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18559690671822135, | |
| "grad_norm": 1.1108283996582031, | |
| "learning_rate": 0.000299794430213186, | |
| "loss": 0.4044, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.20106331561140647, | |
| "grad_norm": 1.4058749675750732, | |
| "learning_rate": 0.00029953760005996916, | |
| "loss": 0.4258, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2165297245045916, | |
| "grad_norm": 0.8541085124015808, | |
| "learning_rate": 0.00029917828430524096, | |
| "loss": 0.419, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2319961333977767, | |
| "grad_norm": 0.7577608823776245, | |
| "learning_rate": 0.00029871672920607153, | |
| "loss": 0.4055, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.24746254229096182, | |
| "grad_norm": 0.8010592460632324, | |
| "learning_rate": 0.00029815325108927063, | |
| "loss": 0.4587, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26292895118414694, | |
| "grad_norm": 2.178513526916504, | |
| "learning_rate": 0.00029748823613459316, | |
| "loss": 0.3844, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.27839536007733207, | |
| "grad_norm": 1.049085021018982, | |
| "learning_rate": 0.0002967221401100708, | |
| "loss": 0.3085, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.29386176897051713, | |
| "grad_norm": 0.2664034962654114, | |
| "learning_rate": 0.0002958554880596515, | |
| "loss": 0.2314, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.30932817786370226, | |
| "grad_norm": 0.9501022696495056, | |
| "learning_rate": 0.0002948888739433602, | |
| "loss": 0.2162, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3247945867568874, | |
| "grad_norm": 0.29297515749931335, | |
| "learning_rate": 0.00029382296023022894, | |
| "loss": 0.1734, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3402609956500725, | |
| "grad_norm": 0.29325342178344727, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.2472, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.35572740454325763, | |
| "grad_norm": 0.7397837042808533, | |
| "learning_rate": 0.00029139622366382674, | |
| "loss": 0.3872, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3711938134364427, | |
| "grad_norm": 0.5978482365608215, | |
| "learning_rate": 0.00029003706397458023, | |
| "loss": 0.3756, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3866602223296278, | |
| "grad_norm": 0.8143917918205261, | |
| "learning_rate": 0.000288581929876693, | |
| "loss": 0.3305, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3866602223296278, | |
| "eval_loss": 0.2919376492500305, | |
| "eval_runtime": 7.3131, | |
| "eval_samples_per_second": 6.837, | |
| "eval_steps_per_second": 6.837, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.40212663122281295, | |
| "grad_norm": 0.5971204042434692, | |
| "learning_rate": 0.0002870318186463901, | |
| "loss": 0.329, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.41759304011599807, | |
| "grad_norm": 0.5656357407569885, | |
| "learning_rate": 0.0002853877926524791, | |
| "loss": 0.2991, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4330594490091832, | |
| "grad_norm": 0.9046909809112549, | |
| "learning_rate": 0.00028365097862825513, | |
| "loss": 0.3522, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4485258579023683, | |
| "grad_norm": 1.8343451023101807, | |
| "learning_rate": 0.00028182256689929475, | |
| "loss": 0.3253, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4639922667955534, | |
| "grad_norm": 1.3387500047683716, | |
| "learning_rate": 0.0002799038105676658, | |
| "loss": 0.3363, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4794586756887385, | |
| "grad_norm": 0.7546955943107605, | |
| "learning_rate": 0.0002778960246531138, | |
| "loss": 0.3319, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.49492508458192364, | |
| "grad_norm": 0.5383890271186829, | |
| "learning_rate": 0.0002758005851918136, | |
| "loss": 0.4198, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5103914934751087, | |
| "grad_norm": 2.9426941871643066, | |
| "learning_rate": 0.0002736189282933023, | |
| "loss": 0.3846, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5258579023682939, | |
| "grad_norm": 1.3911627531051636, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.2681, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.541324311261479, | |
| "grad_norm": 0.33964619040489197, | |
| "learning_rate": 0.00026900300104368524, | |
| "loss": 0.2078, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5567907201546641, | |
| "grad_norm": 0.6098275780677795, | |
| "learning_rate": 0.0002665718942185456, | |
| "loss": 0.2027, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5722571290478492, | |
| "grad_norm": 0.5025777816772461, | |
| "learning_rate": 0.00026406089484000466, | |
| "loss": 0.206, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5877235379410343, | |
| "grad_norm": 0.4298511743545532, | |
| "learning_rate": 0.00026147172382160914, | |
| "loss": 0.2803, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6031899468342194, | |
| "grad_norm": 0.9432958364486694, | |
| "learning_rate": 0.00025880615565184313, | |
| "loss": 0.3849, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6186563557274045, | |
| "grad_norm": 0.6062995791435242, | |
| "learning_rate": 0.00025606601717798207, | |
| "loss": 0.3508, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6341227646205897, | |
| "grad_norm": 0.5804493427276611, | |
| "learning_rate": 0.0002532531863540631, | |
| "loss": 0.3212, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6495891735137748, | |
| "grad_norm": 0.5816200375556946, | |
| "learning_rate": 0.0002503695909538287, | |
| "loss": 0.2876, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6650555824069598, | |
| "grad_norm": 0.4420316219329834, | |
| "learning_rate": 0.0002474172072495275, | |
| "loss": 0.3054, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.680521991300145, | |
| "grad_norm": 0.45776253938674927, | |
| "learning_rate": 0.0002443980586574756, | |
| "loss": 0.279, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6959884001933301, | |
| "grad_norm": 0.7748484015464783, | |
| "learning_rate": 0.00024131421435130807, | |
| "loss": 0.2875, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7114548090865153, | |
| "grad_norm": 0.5803005695343018, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.3088, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7269212179797003, | |
| "grad_norm": 1.1293902397155762, | |
| "learning_rate": 0.0002349609355387249, | |
| "loss": 0.3188, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7423876268728854, | |
| "grad_norm": 1.2384657859802246, | |
| "learning_rate": 0.00023169585525225405, | |
| "loss": 0.4065, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7578540357660706, | |
| "grad_norm": 1.8807259798049927, | |
| "learning_rate": 0.0002283747847073923, | |
| "loss": 0.2961, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7733204446592556, | |
| "grad_norm": 0.7909408211708069, | |
| "learning_rate": 0.000225, | |
| "loss": 0.2371, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7733204446592556, | |
| "eval_loss": 0.26686012744903564, | |
| "eval_runtime": 7.3174, | |
| "eval_samples_per_second": 6.833, | |
| "eval_steps_per_second": 6.833, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7887868535524408, | |
| "grad_norm": 0.3425706624984741, | |
| "learning_rate": 0.00022157381403894124, | |
| "loss": 0.1907, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8042532624456259, | |
| "grad_norm": 0.5927841663360596, | |
| "learning_rate": 0.00021809857496093199, | |
| "loss": 0.1673, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8197196713388111, | |
| "grad_norm": 0.3090386986732483, | |
| "learning_rate": 0.00021457666452124428, | |
| "loss": 0.2062, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.8351860802319961, | |
| "grad_norm": 0.7005581855773926, | |
| "learning_rate": 0.00021101049646137003, | |
| "loss": 0.3042, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8506524891251812, | |
| "grad_norm": 0.44823092222213745, | |
| "learning_rate": 0.00020740251485476345, | |
| "loss": 0.2754, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8661188980183664, | |
| "grad_norm": 0.43465909361839294, | |
| "learning_rate": 0.000203755192431795, | |
| "loss": 0.2858, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.8815853069115515, | |
| "grad_norm": 0.45701804757118225, | |
| "learning_rate": 0.0002000710288850656, | |
| "loss": 0.2677, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.8970517158047366, | |
| "grad_norm": 0.36131733655929565, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.2443, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.9125181246979217, | |
| "grad_norm": 0.3090292811393738, | |
| "learning_rate": 0.0001926023017055884, | |
| "loss": 0.2337, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.9279845335911068, | |
| "grad_norm": 0.4051980972290039, | |
| "learning_rate": 0.0001888228567653781, | |
| "loss": 0.2617, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.943450942484292, | |
| "grad_norm": 0.4554498493671417, | |
| "learning_rate": 0.0001850168045783858, | |
| "loss": 0.2417, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.958917351377477, | |
| "grad_norm": 0.6270922422409058, | |
| "learning_rate": 0.00018118675362266385, | |
| "loss": 0.2552, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.9743837602706622, | |
| "grad_norm": 0.750235378742218, | |
| "learning_rate": 0.00017733532882382213, | |
| "loss": 0.2594, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.9898501691638473, | |
| "grad_norm": 1.0947400331497192, | |
| "learning_rate": 0.00017346516975603462, | |
| "loss": 0.339, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.0053165780570323, | |
| "grad_norm": 0.9929707050323486, | |
| "learning_rate": 0.00016957892883300775, | |
| "loss": 0.3453, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.0207829869502174, | |
| "grad_norm": 0.45975467562675476, | |
| "learning_rate": 0.000165679269490148, | |
| "loss": 0.2237, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0362493958434027, | |
| "grad_norm": 0.28348809480667114, | |
| "learning_rate": 0.00016176886435917675, | |
| "loss": 0.1931, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.0517158047365878, | |
| "grad_norm": 0.22970043122768402, | |
| "learning_rate": 0.0001578503934364416, | |
| "loss": 0.1668, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.0671822136297728, | |
| "grad_norm": 0.2886936664581299, | |
| "learning_rate": 0.00015392654224618098, | |
| "loss": 0.1539, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.082648622522958, | |
| "grad_norm": 0.3277800977230072, | |
| "learning_rate": 0.00015, | |
| "loss": 0.2382, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.098115031416143, | |
| "grad_norm": 0.7377809882164001, | |
| "learning_rate": 0.00014607345775381904, | |
| "loss": 0.2307, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.1135814403093283, | |
| "grad_norm": 0.4106524884700775, | |
| "learning_rate": 0.0001421496065635584, | |
| "loss": 0.2433, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.1290478492025133, | |
| "grad_norm": 0.5610142350196838, | |
| "learning_rate": 0.00013823113564082325, | |
| "loss": 0.2568, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.1445142580956984, | |
| "grad_norm": 0.9046674370765686, | |
| "learning_rate": 0.000134320730509852, | |
| "loss": 0.2751, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.1599806669888835, | |
| "grad_norm": 0.617001473903656, | |
| "learning_rate": 0.00013042107116699228, | |
| "loss": 0.2139, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.1599806669888835, | |
| "eval_loss": 0.2165301889181137, | |
| "eval_runtime": 7.3111, | |
| "eval_samples_per_second": 6.839, | |
| "eval_steps_per_second": 6.839, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.1754470758820685, | |
| "grad_norm": 0.6039713025093079, | |
| "learning_rate": 0.00012653483024396533, | |
| "loss": 0.2185, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.1909134847752538, | |
| "grad_norm": 0.4915192127227783, | |
| "learning_rate": 0.00012266467117617787, | |
| "loss": 0.2277, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.206379893668439, | |
| "grad_norm": 0.31167200207710266, | |
| "learning_rate": 0.00011881324637733611, | |
| "loss": 0.2205, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.221846302561624, | |
| "grad_norm": 0.4483063817024231, | |
| "learning_rate": 0.00011498319542161423, | |
| "loss": 0.24, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.237312711454809, | |
| "grad_norm": 0.4659959077835083, | |
| "learning_rate": 0.00011117714323462186, | |
| "loss": 0.2655, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.252779120347994, | |
| "grad_norm": 0.2737232446670532, | |
| "learning_rate": 0.0001073976982944116, | |
| "loss": 0.2592, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.2682455292411794, | |
| "grad_norm": 0.49031612277030945, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.2176, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.2837119381343645, | |
| "grad_norm": 0.2844369113445282, | |
| "learning_rate": 9.992897111493437e-05, | |
| "loss": 0.1823, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.2991783470275495, | |
| "grad_norm": 0.30533647537231445, | |
| "learning_rate": 9.624480756820496e-05, | |
| "loss": 0.1705, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.3146447559207346, | |
| "grad_norm": 0.37838345766067505, | |
| "learning_rate": 9.259748514523653e-05, | |
| "loss": 0.1426, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.3301111648139199, | |
| "grad_norm": 0.4842795133590698, | |
| "learning_rate": 8.898950353862998e-05, | |
| "loss": 0.1921, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.345577573707105, | |
| "grad_norm": 0.7472468018531799, | |
| "learning_rate": 8.54233354787557e-05, | |
| "loss": 0.241, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.36104398260029, | |
| "grad_norm": 0.8189084529876709, | |
| "learning_rate": 8.190142503906798e-05, | |
| "loss": 0.2342, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.376510391493475, | |
| "grad_norm": 0.45445919036865234, | |
| "learning_rate": 7.842618596105872e-05, | |
| "loss": 0.2118, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.3919768003866602, | |
| "grad_norm": 0.4599757492542267, | |
| "learning_rate": 7.500000000000002e-05, | |
| "loss": 0.212, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4074432092798452, | |
| "grad_norm": 0.6367545127868652, | |
| "learning_rate": 7.162521529260767e-05, | |
| "loss": 0.2341, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.4229096181730305, | |
| "grad_norm": 0.5731837749481201, | |
| "learning_rate": 6.830414474774594e-05, | |
| "loss": 0.2237, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.4383760270662156, | |
| "grad_norm": 0.5188281536102295, | |
| "learning_rate": 6.50390644612751e-05, | |
| "loss": 0.2233, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.4538424359594007, | |
| "grad_norm": 0.3524056375026703, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.236, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.4693088448525857, | |
| "grad_norm": 0.28299957513809204, | |
| "learning_rate": 5.8685785648691894e-05, | |
| "loss": 0.2433, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.484775253745771, | |
| "grad_norm": 0.3486190736293793, | |
| "learning_rate": 5.56019413425244e-05, | |
| "loss": 0.2873, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.500241662638956, | |
| "grad_norm": 0.28295159339904785, | |
| "learning_rate": 5.2582792750472464e-05, | |
| "loss": 0.2721, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.5157080715321412, | |
| "grad_norm": 0.3966909646987915, | |
| "learning_rate": 4.963040904617131e-05, | |
| "loss": 0.1962, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.5311744804253262, | |
| "grad_norm": 0.3956305682659149, | |
| "learning_rate": 4.6746813645936877e-05, | |
| "loss": 0.1928, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.5466408893185113, | |
| "grad_norm": 0.28398260474205017, | |
| "learning_rate": 4.3933982822017876e-05, | |
| "loss": 0.1685, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5466408893185113, | |
| "eval_loss": 0.20296970009803772, | |
| "eval_runtime": 7.3114, | |
| "eval_samples_per_second": 6.839, | |
| "eval_steps_per_second": 6.839, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5621072982116964, | |
| "grad_norm": 0.1923961192369461, | |
| "learning_rate": 4.1193844348156886e-05, | |
| "loss": 0.1462, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.5775737071048814, | |
| "grad_norm": 0.18478325009346008, | |
| "learning_rate": 3.852827617839084e-05, | |
| "loss": 0.1648, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.5930401159980667, | |
| "grad_norm": 0.30043265223503113, | |
| "learning_rate": 3.593910515999536e-05, | |
| "loss": 0.1844, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.6085065248912518, | |
| "grad_norm": 0.5838200449943542, | |
| "learning_rate": 3.342810578145436e-05, | |
| "loss": 0.2355, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.623972933784437, | |
| "grad_norm": 0.5884765386581421, | |
| "learning_rate": 3.099699895631474e-05, | |
| "loss": 0.2287, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.6394393426776221, | |
| "grad_norm": 0.4631075859069824, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 0.2004, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.6549057515708072, | |
| "grad_norm": 0.3879186809062958, | |
| "learning_rate": 2.6381071706697644e-05, | |
| "loss": 0.1996, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.6703721604639923, | |
| "grad_norm": 0.2909069359302521, | |
| "learning_rate": 2.4199414808186406e-05, | |
| "loss": 0.1985, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.6858385693571774, | |
| "grad_norm": 0.34202706813812256, | |
| "learning_rate": 2.210397534688617e-05, | |
| "loss": 0.1848, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.7013049782503624, | |
| "grad_norm": 0.3348611295223236, | |
| "learning_rate": 2.009618943233419e-05, | |
| "loss": 0.2004, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.7167713871435475, | |
| "grad_norm": 0.4890515208244324, | |
| "learning_rate": 1.8177433100705207e-05, | |
| "loss": 0.2107, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.7322377960367326, | |
| "grad_norm": 0.560546875, | |
| "learning_rate": 1.634902137174483e-05, | |
| "loss": 0.2933, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.7477042049299178, | |
| "grad_norm": 0.5725692510604858, | |
| "learning_rate": 1.4612207347520938e-05, | |
| "loss": 0.2927, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.763170613823103, | |
| "grad_norm": 0.33504927158355713, | |
| "learning_rate": 1.2968181353609852e-05, | |
| "loss": 0.1681, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.7786370227162882, | |
| "grad_norm": 0.34945377707481384, | |
| "learning_rate": 1.1418070123306989e-05, | |
| "loss": 0.1594, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.7941034316094733, | |
| "grad_norm": 0.31711897253990173, | |
| "learning_rate": 9.962936025419754e-06, | |
| "loss": 0.1475, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.8095698405026583, | |
| "grad_norm": 0.25584596395492554, | |
| "learning_rate": 8.603776336173235e-06, | |
| "loss": 0.1476, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.8250362493958434, | |
| "grad_norm": 0.34091395139694214, | |
| "learning_rate": 7.34152255572697e-06, | |
| "loss": 0.1856, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.8405026582890285, | |
| "grad_norm": 0.3409639894962311, | |
| "learning_rate": 6.1770397697710414e-06, | |
| "loss": 0.1982, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.8559690671822135, | |
| "grad_norm": 0.2535560131072998, | |
| "learning_rate": 5.11112605663977e-06, | |
| "loss": 0.1881, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.8714354760753986, | |
| "grad_norm": 0.26184314489364624, | |
| "learning_rate": 4.144511940348516e-06, | |
| "loss": 0.1976, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.886901884968584, | |
| "grad_norm": 0.28429871797561646, | |
| "learning_rate": 3.2778598899291465e-06, | |
| "loss": 0.1938, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.902368293861769, | |
| "grad_norm": 0.23394553363323212, | |
| "learning_rate": 2.511763865406824e-06, | |
| "loss": 0.1655, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.917834702754954, | |
| "grad_norm": 0.36569544672966003, | |
| "learning_rate": 1.8467489107293509e-06, | |
| "loss": 0.2076, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.9333011116481393, | |
| "grad_norm": 0.38919389247894287, | |
| "learning_rate": 1.2832707939284427e-06, | |
| "loss": 0.1977, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.9333011116481393, | |
| "eval_loss": 0.18706867098808289, | |
| "eval_runtime": 7.3048, | |
| "eval_samples_per_second": 6.845, | |
| "eval_steps_per_second": 6.845, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.9487675205413244, | |
| "grad_norm": 0.2989993989467621, | |
| "learning_rate": 8.217156947590064e-07, | |
| "loss": 0.2162, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.9642339294345095, | |
| "grad_norm": 0.41685956716537476, | |
| "learning_rate": 4.623999400308054e-07, | |
| "loss": 0.2151, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.9797003383276945, | |
| "grad_norm": 0.2608714699745178, | |
| "learning_rate": 2.05569786813925e-07, | |
| "loss": 0.2491, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.9951667472208796, | |
| "grad_norm": 0.4548462927341461, | |
| "learning_rate": 5.1401253666411016e-08, | |
| "loss": 0.333, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.0106331561140647, | |
| "grad_norm": 0.17462550103664398, | |
| "learning_rate": 0.0, | |
| "loss": 0.1465, | |
| "step": 130 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.052912237505413e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |