| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9904153354632586, | |
| "eval_steps": 500, | |
| "global_step": 78, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.038338658146964855, | |
| "grad_norm": 6.45109748840332, | |
| "learning_rate": 1.25e-06, | |
| "loss": 1.2212, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07667731629392971, | |
| "grad_norm": 6.449772834777832, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.2011, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11501597444089456, | |
| "grad_norm": 6.236454963684082, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.1949, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15335463258785942, | |
| "grad_norm": 6.070368766784668, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2172, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19169329073482427, | |
| "grad_norm": 4.3351287841796875, | |
| "learning_rate": 6.25e-06, | |
| "loss": 1.1609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23003194888178913, | |
| "grad_norm": 2.6603915691375732, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.0722, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.268370607028754, | |
| "grad_norm": 4.560462951660156, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 1.0798, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.30670926517571884, | |
| "grad_norm": 5.290356159210205, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1219, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3450479233226837, | |
| "grad_norm": 4.381709098815918, | |
| "learning_rate": 9.994965332706574e-06, | |
| "loss": 1.0392, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.38338658146964855, | |
| "grad_norm": 4.178859710693359, | |
| "learning_rate": 9.979871469976197e-06, | |
| "loss": 1.0663, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4217252396166134, | |
| "grad_norm": 3.180849552154541, | |
| "learning_rate": 9.954748808839675e-06, | |
| "loss": 1.031, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.46006389776357826, | |
| "grad_norm": 2.457411289215088, | |
| "learning_rate": 9.91964794299315e-06, | |
| "loss": 1.0179, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4984025559105431, | |
| "grad_norm": 2.3789966106414795, | |
| "learning_rate": 9.874639560909118e-06, | |
| "loss": 0.967, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.536741214057508, | |
| "grad_norm": 1.7590055465698242, | |
| "learning_rate": 9.819814303479268e-06, | |
| "loss": 0.9176, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5750798722044729, | |
| "grad_norm": 1.504982829093933, | |
| "learning_rate": 9.755282581475769e-06, | |
| "loss": 0.9332, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6134185303514377, | |
| "grad_norm": 1.328847885131836, | |
| "learning_rate": 9.681174353198687e-06, | |
| "loss": 0.9285, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6517571884984026, | |
| "grad_norm": 1.3487250804901123, | |
| "learning_rate": 9.597638862757255e-06, | |
| "loss": 0.9548, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6900958466453674, | |
| "grad_norm": 1.309167742729187, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 0.8749, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7284345047923323, | |
| "grad_norm": 1.07999587059021, | |
| "learning_rate": 9.40297765928369e-06, | |
| "loss": 0.906, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7667731629392971, | |
| "grad_norm": 0.9898855686187744, | |
| "learning_rate": 9.292243968009332e-06, | |
| "loss": 0.8826, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.805111821086262, | |
| "grad_norm": 1.084998369216919, | |
| "learning_rate": 9.172866268606514e-06, | |
| "loss": 0.884, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8434504792332268, | |
| "grad_norm": 0.9995360374450684, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.8734, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8817891373801917, | |
| "grad_norm": 0.914259672164917, | |
| "learning_rate": 8.90915741234015e-06, | |
| "loss": 0.8466, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9201277955271565, | |
| "grad_norm": 0.8691526651382446, | |
| "learning_rate": 8.765357330018056e-06, | |
| "loss": 0.9043, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9584664536741214, | |
| "grad_norm": 0.8191248774528503, | |
| "learning_rate": 8.613974319136959e-06, | |
| "loss": 0.9746, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9968051118210862, | |
| "grad_norm": 0.9226800799369812, | |
| "learning_rate": 8.455313244934324e-06, | |
| "loss": 0.8703, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.035143769968051, | |
| "grad_norm": 2.459444046020508, | |
| "learning_rate": 8.289693629698564e-06, | |
| "loss": 1.3673, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.073482428115016, | |
| "grad_norm": 0.8009559512138367, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 0.8485, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1118210862619808, | |
| "grad_norm": 0.703082799911499, | |
| "learning_rate": 7.938926261462366e-06, | |
| "loss": 0.8098, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1501597444089458, | |
| "grad_norm": 0.7537962794303894, | |
| "learning_rate": 7.754484907260513e-06, | |
| "loss": 0.8444, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1884984025559104, | |
| "grad_norm": 0.760931134223938, | |
| "learning_rate": 7.564496387029532e-06, | |
| "loss": 0.8598, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2268370607028753, | |
| "grad_norm": 0.7525911331176758, | |
| "learning_rate": 7.369343312364994e-06, | |
| "loss": 0.865, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2651757188498403, | |
| "grad_norm": 0.723669707775116, | |
| "learning_rate": 7.169418695587791e-06, | |
| "loss": 0.7959, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3035143769968052, | |
| "grad_norm": 0.7163628339767456, | |
| "learning_rate": 6.965125158269619e-06, | |
| "loss": 0.8051, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.34185303514377, | |
| "grad_norm": 0.6843879222869873, | |
| "learning_rate": 6.7568741204067145e-06, | |
| "loss": 0.828, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3801916932907348, | |
| "grad_norm": 0.6427307724952698, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.854, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4185303514376997, | |
| "grad_norm": 0.7232085466384888, | |
| "learning_rate": 6.330184227833376e-06, | |
| "loss": 0.8848, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4568690095846646, | |
| "grad_norm": 0.7611010074615479, | |
| "learning_rate": 6.112604669781572e-06, | |
| "loss": 0.6879, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4952076677316293, | |
| "grad_norm": 0.7250047922134399, | |
| "learning_rate": 5.892784473993184e-06, | |
| "loss": 0.8684, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5335463258785942, | |
| "grad_norm": 0.633452832698822, | |
| "learning_rate": 5.671166329088278e-06, | |
| "loss": 0.8257, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.571884984025559, | |
| "grad_norm": 0.6049233078956604, | |
| "learning_rate": 5.448196544517168e-06, | |
| "loss": 0.8012, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.610223642172524, | |
| "grad_norm": 0.701932430267334, | |
| "learning_rate": 5.224324151752575e-06, | |
| "loss": 0.8206, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.648562300319489, | |
| "grad_norm": 0.626121997833252, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8031, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6869009584664538, | |
| "grad_norm": 0.6095514297485352, | |
| "learning_rate": 4.775675848247427e-06, | |
| "loss": 0.8131, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7252396166134185, | |
| "grad_norm": 0.6313042044639587, | |
| "learning_rate": 4.551803455482833e-06, | |
| "loss": 0.8061, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7635782747603834, | |
| "grad_norm": 0.6074307560920715, | |
| "learning_rate": 4.3288336709117246e-06, | |
| "loss": 0.8172, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8019169329073481, | |
| "grad_norm": 0.6239637732505798, | |
| "learning_rate": 4.107215526006818e-06, | |
| "loss": 0.8394, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.840255591054313, | |
| "grad_norm": 0.6018702983856201, | |
| "learning_rate": 3.887395330218429e-06, | |
| "loss": 0.8024, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.878594249201278, | |
| "grad_norm": 0.6898264288902283, | |
| "learning_rate": 3.669815772166625e-06, | |
| "loss": 0.8907, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9169329073482428, | |
| "grad_norm": 0.5472529530525208, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.7073, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9552715654952078, | |
| "grad_norm": 0.5887239575386047, | |
| "learning_rate": 3.2431258795932863e-06, | |
| "loss": 0.7974, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.9936102236421727, | |
| "grad_norm": 0.5762373805046082, | |
| "learning_rate": 3.0348748417303826e-06, | |
| "loss": 0.8499, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.0319488817891376, | |
| "grad_norm": 1.788190484046936, | |
| "learning_rate": 2.83058130441221e-06, | |
| "loss": 1.4672, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.070287539936102, | |
| "grad_norm": 0.6082499027252197, | |
| "learning_rate": 2.6306566876350072e-06, | |
| "loss": 0.7681, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.108626198083067, | |
| "grad_norm": 0.5818493962287903, | |
| "learning_rate": 2.43550361297047e-06, | |
| "loss": 0.7296, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.146964856230032, | |
| "grad_norm": 0.4775056540966034, | |
| "learning_rate": 2.245515092739488e-06, | |
| "loss": 0.7339, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.1853035143769968, | |
| "grad_norm": 0.48535844683647156, | |
| "learning_rate": 2.061073738537635e-06, | |
| "loss": 0.7905, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.2236421725239617, | |
| "grad_norm": 0.5611085295677185, | |
| "learning_rate": 1.8825509907063328e-06, | |
| "loss": 0.7852, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.2619808306709266, | |
| "grad_norm": 0.554451048374176, | |
| "learning_rate": 1.7103063703014372e-06, | |
| "loss": 0.7263, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3003194888178915, | |
| "grad_norm": 0.5591139793395996, | |
| "learning_rate": 1.544686755065677e-06, | |
| "loss": 0.7394, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3386581469648564, | |
| "grad_norm": 0.5835963487625122, | |
| "learning_rate": 1.3860256808630429e-06, | |
| "loss": 0.7811, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.376996805111821, | |
| "grad_norm": 0.4586201608181, | |
| "learning_rate": 1.234642669981946e-06, | |
| "loss": 0.6595, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.415335463258786, | |
| "grad_norm": 0.6206969618797302, | |
| "learning_rate": 1.0908425876598512e-06, | |
| "loss": 0.9082, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.4536741214057507, | |
| "grad_norm": 0.5300808548927307, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.7043, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.4920127795527156, | |
| "grad_norm": 0.5531863570213318, | |
| "learning_rate": 8.271337313934869e-07, | |
| "loss": 0.7529, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.5303514376996805, | |
| "grad_norm": 0.5038548111915588, | |
| "learning_rate": 7.077560319906696e-07, | |
| "loss": 0.7902, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.5686900958466454, | |
| "grad_norm": 0.4608278274536133, | |
| "learning_rate": 5.9702234071631e-07, | |
| "loss": 0.7202, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.6070287539936103, | |
| "grad_norm": 0.5147573351860046, | |
| "learning_rate": 4.951556604879049e-07, | |
| "loss": 0.8864, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.6453674121405752, | |
| "grad_norm": 0.5285633206367493, | |
| "learning_rate": 4.0236113724274716e-07, | |
| "loss": 0.7205, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.68370607028754, | |
| "grad_norm": 0.511046290397644, | |
| "learning_rate": 3.18825646801314e-07, | |
| "loss": 0.72, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.722044728434505, | |
| "grad_norm": 0.5221746563911438, | |
| "learning_rate": 2.447174185242324e-07, | |
| "loss": 0.7959, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.7603833865814695, | |
| "grad_norm": 0.504964292049408, | |
| "learning_rate": 1.801856965207338e-07, | |
| "loss": 0.7179, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.7987220447284344, | |
| "grad_norm": 0.4362109899520874, | |
| "learning_rate": 1.253604390908819e-07, | |
| "loss": 0.6673, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.8370607028753994, | |
| "grad_norm": 0.5560856461524963, | |
| "learning_rate": 8.035205700685167e-08, | |
| "loss": 0.8126, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.8753993610223643, | |
| "grad_norm": 0.5098027586936951, | |
| "learning_rate": 4.52511911603265e-08, | |
| "loss": 0.7562, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.913738019169329, | |
| "grad_norm": 0.494514137506485, | |
| "learning_rate": 2.012853002380466e-08, | |
| "loss": 0.7857, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.952076677316294, | |
| "grad_norm": 0.5156562924385071, | |
| "learning_rate": 5.034667293427053e-09, | |
| "loss": 0.7503, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.9904153354632586, | |
| "grad_norm": 0.4876989722251892, | |
| "learning_rate": 0.0, | |
| "loss": 0.7684, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.9904153354632586, | |
| "step": 78, | |
| "total_flos": 53089482080256.0, | |
| "train_loss": 0.8778469868195362, | |
| "train_runtime": 3457.6659, | |
| "train_samples_per_second": 2.169, | |
| "train_steps_per_second": 0.023 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 78, | |
| "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": 53089482080256.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |