| { | |
| "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": 7.000820636749268, | |
| "learning_rate": 1.25e-06, | |
| "loss": 1.2681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07667731629392971, | |
| "grad_norm": 7.010729789733887, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.2919, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11501597444089456, | |
| "grad_norm": 6.599626064300537, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.234, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15335463258785942, | |
| "grad_norm": 6.159054279327393, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2411, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19169329073482427, | |
| "grad_norm": 4.725393772125244, | |
| "learning_rate": 6.25e-06, | |
| "loss": 1.2041, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23003194888178913, | |
| "grad_norm": 2.875958204269409, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.1703, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.268370607028754, | |
| "grad_norm": 6.235777378082275, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 1.171, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.30670926517571884, | |
| "grad_norm": 6.43796968460083, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1877, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3450479233226837, | |
| "grad_norm": 6.087247848510742, | |
| "learning_rate": 9.994965332706574e-06, | |
| "loss": 1.1817, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.38338658146964855, | |
| "grad_norm": 6.090503215789795, | |
| "learning_rate": 9.979871469976197e-06, | |
| "loss": 1.1646, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4217252396166134, | |
| "grad_norm": 3.869046449661255, | |
| "learning_rate": 9.954748808839675e-06, | |
| "loss": 1.0885, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.46006389776357826, | |
| "grad_norm": 2.2247347831726074, | |
| "learning_rate": 9.91964794299315e-06, | |
| "loss": 1.0807, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4984025559105431, | |
| "grad_norm": 2.2890737056732178, | |
| "learning_rate": 9.874639560909118e-06, | |
| "loss": 1.027, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.536741214057508, | |
| "grad_norm": 2.0002832412719727, | |
| "learning_rate": 9.819814303479268e-06, | |
| "loss": 1.0432, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5750798722044729, | |
| "grad_norm": 1.6361793279647827, | |
| "learning_rate": 9.755282581475769e-06, | |
| "loss": 1.0307, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6134185303514377, | |
| "grad_norm": 1.150823950767517, | |
| "learning_rate": 9.681174353198687e-06, | |
| "loss": 0.971, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6517571884984026, | |
| "grad_norm": 1.4973807334899902, | |
| "learning_rate": 9.597638862757255e-06, | |
| "loss": 1.0096, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6900958466453674, | |
| "grad_norm": 1.2875914573669434, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 0.9571, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7284345047923323, | |
| "grad_norm": 1.0247159004211426, | |
| "learning_rate": 9.40297765928369e-06, | |
| "loss": 1.0203, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7667731629392971, | |
| "grad_norm": 1.0895007848739624, | |
| "learning_rate": 9.292243968009332e-06, | |
| "loss": 0.9534, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.805111821086262, | |
| "grad_norm": 1.149806261062622, | |
| "learning_rate": 9.172866268606514e-06, | |
| "loss": 0.9644, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8434504792332268, | |
| "grad_norm": 0.9425738453865051, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.9298, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8817891373801917, | |
| "grad_norm": 0.9909608364105225, | |
| "learning_rate": 8.90915741234015e-06, | |
| "loss": 0.9526, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9201277955271565, | |
| "grad_norm": 0.9320346117019653, | |
| "learning_rate": 8.765357330018056e-06, | |
| "loss": 0.9474, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9584664536741214, | |
| "grad_norm": 0.901214599609375, | |
| "learning_rate": 8.613974319136959e-06, | |
| "loss": 0.96, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9968051118210862, | |
| "grad_norm": 1.051206111907959, | |
| "learning_rate": 8.455313244934324e-06, | |
| "loss": 0.9351, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.035143769968051, | |
| "grad_norm": 2.599987030029297, | |
| "learning_rate": 8.289693629698564e-06, | |
| "loss": 1.7616, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.073482428115016, | |
| "grad_norm": 1.0360617637634277, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 0.8903, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1118210862619808, | |
| "grad_norm": 1.0993787050247192, | |
| "learning_rate": 7.938926261462366e-06, | |
| "loss": 1.022, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1501597444089458, | |
| "grad_norm": 0.7516313195228577, | |
| "learning_rate": 7.754484907260513e-06, | |
| "loss": 0.8428, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1884984025559104, | |
| "grad_norm": 0.9304578304290771, | |
| "learning_rate": 7.564496387029532e-06, | |
| "loss": 0.9037, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2268370607028753, | |
| "grad_norm": 0.835986316204071, | |
| "learning_rate": 7.369343312364994e-06, | |
| "loss": 0.8848, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2651757188498403, | |
| "grad_norm": 0.6572882533073425, | |
| "learning_rate": 7.169418695587791e-06, | |
| "loss": 0.8824, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3035143769968052, | |
| "grad_norm": 0.7613012194633484, | |
| "learning_rate": 6.965125158269619e-06, | |
| "loss": 0.9101, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.34185303514377, | |
| "grad_norm": 0.7818209528923035, | |
| "learning_rate": 6.7568741204067145e-06, | |
| "loss": 0.8892, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3801916932907348, | |
| "grad_norm": 0.703815758228302, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.8909, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4185303514376997, | |
| "grad_norm": 0.5774455070495605, | |
| "learning_rate": 6.330184227833376e-06, | |
| "loss": 0.9114, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4568690095846646, | |
| "grad_norm": 0.6940023899078369, | |
| "learning_rate": 6.112604669781572e-06, | |
| "loss": 0.9284, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4952076677316293, | |
| "grad_norm": 0.6584268808364868, | |
| "learning_rate": 5.892784473993184e-06, | |
| "loss": 0.9126, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5335463258785942, | |
| "grad_norm": 0.6575169563293457, | |
| "learning_rate": 5.671166329088278e-06, | |
| "loss": 0.9031, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.571884984025559, | |
| "grad_norm": 0.675748348236084, | |
| "learning_rate": 5.448196544517168e-06, | |
| "loss": 0.9036, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.610223642172524, | |
| "grad_norm": 0.600158154964447, | |
| "learning_rate": 5.224324151752575e-06, | |
| "loss": 0.8753, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.648562300319489, | |
| "grad_norm": 0.7212960124015808, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8456, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6869009584664538, | |
| "grad_norm": 0.7690831422805786, | |
| "learning_rate": 4.775675848247427e-06, | |
| "loss": 0.9227, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7252396166134185, | |
| "grad_norm": 0.6147218942642212, | |
| "learning_rate": 4.551803455482833e-06, | |
| "loss": 0.9113, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7635782747603834, | |
| "grad_norm": 0.5056852698326111, | |
| "learning_rate": 4.3288336709117246e-06, | |
| "loss": 0.818, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8019169329073481, | |
| "grad_norm": 0.6909663677215576, | |
| "learning_rate": 4.107215526006818e-06, | |
| "loss": 0.9319, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.840255591054313, | |
| "grad_norm": 0.6461554169654846, | |
| "learning_rate": 3.887395330218429e-06, | |
| "loss": 0.8432, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.878594249201278, | |
| "grad_norm": 0.6330693364143372, | |
| "learning_rate": 3.669815772166625e-06, | |
| "loss": 0.8842, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9169329073482428, | |
| "grad_norm": 0.571108877658844, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.9103, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9552715654952078, | |
| "grad_norm": 0.5688198804855347, | |
| "learning_rate": 3.2431258795932863e-06, | |
| "loss": 0.8426, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.9936102236421727, | |
| "grad_norm": 0.5545569658279419, | |
| "learning_rate": 3.0348748417303826e-06, | |
| "loss": 0.9255, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.0319488817891376, | |
| "grad_norm": 1.561452865600586, | |
| "learning_rate": 2.83058130441221e-06, | |
| "loss": 1.5372, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.070287539936102, | |
| "grad_norm": 0.5394285917282104, | |
| "learning_rate": 2.6306566876350072e-06, | |
| "loss": 0.8853, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.108626198083067, | |
| "grad_norm": 0.5029667019844055, | |
| "learning_rate": 2.43550361297047e-06, | |
| "loss": 0.8347, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.146964856230032, | |
| "grad_norm": 0.5258843302726746, | |
| "learning_rate": 2.245515092739488e-06, | |
| "loss": 0.9051, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.1853035143769968, | |
| "grad_norm": 0.4812494218349457, | |
| "learning_rate": 2.061073738537635e-06, | |
| "loss": 0.7357, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.2236421725239617, | |
| "grad_norm": 0.5169485807418823, | |
| "learning_rate": 1.8825509907063328e-06, | |
| "loss": 0.8855, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.2619808306709266, | |
| "grad_norm": 0.5759406685829163, | |
| "learning_rate": 1.7103063703014372e-06, | |
| "loss": 0.9336, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3003194888178915, | |
| "grad_norm": 0.5117246508598328, | |
| "learning_rate": 1.544686755065677e-06, | |
| "loss": 0.8488, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3386581469648564, | |
| "grad_norm": 0.5215947031974792, | |
| "learning_rate": 1.3860256808630429e-06, | |
| "loss": 0.8287, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.376996805111821, | |
| "grad_norm": 0.43954411149024963, | |
| "learning_rate": 1.234642669981946e-06, | |
| "loss": 0.8179, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.415335463258786, | |
| "grad_norm": 0.47497275471687317, | |
| "learning_rate": 1.0908425876598512e-06, | |
| "loss": 0.8735, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.4536741214057507, | |
| "grad_norm": 0.43999558687210083, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.8404, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.4920127795527156, | |
| "grad_norm": 0.4681786000728607, | |
| "learning_rate": 8.271337313934869e-07, | |
| "loss": 0.8916, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.5303514376996805, | |
| "grad_norm": 0.5225021839141846, | |
| "learning_rate": 7.077560319906696e-07, | |
| "loss": 0.8705, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.5686900958466454, | |
| "grad_norm": 0.4491012394428253, | |
| "learning_rate": 5.9702234071631e-07, | |
| "loss": 0.8514, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.6070287539936103, | |
| "grad_norm": 0.43601951003074646, | |
| "learning_rate": 4.951556604879049e-07, | |
| "loss": 0.8701, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.6453674121405752, | |
| "grad_norm": 0.39648109674453735, | |
| "learning_rate": 4.0236113724274716e-07, | |
| "loss": 0.7914, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.68370607028754, | |
| "grad_norm": 0.45205458998680115, | |
| "learning_rate": 3.18825646801314e-07, | |
| "loss": 0.8926, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.722044728434505, | |
| "grad_norm": 0.4663619101047516, | |
| "learning_rate": 2.447174185242324e-07, | |
| "loss": 0.8852, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.7603833865814695, | |
| "grad_norm": 0.4435560703277588, | |
| "learning_rate": 1.801856965207338e-07, | |
| "loss": 0.8625, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.7987220447284344, | |
| "grad_norm": 0.37866494059562683, | |
| "learning_rate": 1.253604390908819e-07, | |
| "loss": 0.814, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.8370607028753994, | |
| "grad_norm": 0.4168011546134949, | |
| "learning_rate": 8.035205700685167e-08, | |
| "loss": 0.9637, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.8753993610223643, | |
| "grad_norm": 0.37660109996795654, | |
| "learning_rate": 4.52511911603265e-08, | |
| "loss": 0.8286, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.913738019169329, | |
| "grad_norm": 0.4270866811275482, | |
| "learning_rate": 2.012853002380466e-08, | |
| "loss": 0.8685, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.952076677316294, | |
| "grad_norm": 0.3865389823913574, | |
| "learning_rate": 5.034667293427053e-09, | |
| "loss": 0.7887, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.9904153354632586, | |
| "grad_norm": 0.4038066864013672, | |
| "learning_rate": 0.0, | |
| "loss": 0.8801, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.9904153354632586, | |
| "step": 78, | |
| "total_flos": 86865591648256.0, | |
| "train_loss": 0.9630531806212205, | |
| "train_runtime": 8164.2098, | |
| "train_samples_per_second": 0.918, | |
| "train_steps_per_second": 0.01 | |
| } | |
| ], | |
| "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": 86865591648256.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |