{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.5023380093520374, "eval_steps": 47, "global_step": 94, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005344021376085505, "grad_norm": 46.01194381713867, "learning_rate": 1e-05, "loss": 7.1426, "step": 1 }, { "epoch": 0.005344021376085505, "eval_loss": 8.964194297790527, "eval_runtime": 16.0493, "eval_samples_per_second": 19.689, "eval_steps_per_second": 4.922, "step": 1 }, { "epoch": 0.01068804275217101, "grad_norm": 57.69265365600586, "learning_rate": 2e-05, "loss": 7.9573, "step": 2 }, { "epoch": 0.01603206412825651, "grad_norm": 54.09745407104492, "learning_rate": 3e-05, "loss": 8.1933, "step": 3 }, { "epoch": 0.02137608550434202, "grad_norm": 27.1943302154541, "learning_rate": 4e-05, "loss": 8.1016, "step": 4 }, { "epoch": 0.026720106880427523, "grad_norm": 11.922409057617188, "learning_rate": 5e-05, "loss": 8.0041, "step": 5 }, { "epoch": 0.03206412825651302, "grad_norm": 10.52867603302002, "learning_rate": 6e-05, "loss": 7.8208, "step": 6 }, { "epoch": 0.03740814963259853, "grad_norm": 11.152423858642578, "learning_rate": 7e-05, "loss": 7.9175, "step": 7 }, { "epoch": 0.04275217100868404, "grad_norm": 10.940130233764648, "learning_rate": 8e-05, "loss": 7.7791, "step": 8 }, { "epoch": 0.04809619238476954, "grad_norm": 8.973886489868164, "learning_rate": 9e-05, "loss": 7.2009, "step": 9 }, { "epoch": 0.053440213760855046, "grad_norm": 8.348847389221191, "learning_rate": 0.0001, "loss": 6.9716, "step": 10 }, { "epoch": 0.058784235136940546, "grad_norm": 9.494211196899414, "learning_rate": 0.00011000000000000002, "loss": 6.6369, "step": 11 }, { "epoch": 0.06412825651302605, "grad_norm": 16.81532859802246, "learning_rate": 0.00012, "loss": 6.4495, "step": 12 }, { "epoch": 0.06947227788911156, "grad_norm": 10.698507308959961, "learning_rate": 0.00013000000000000002, "loss": 6.0936, "step": 13 }, { "epoch": 0.07481629926519706, "grad_norm": 7.711328983306885, "learning_rate": 0.00014, "loss": 6.3677, "step": 14 }, { "epoch": 0.08016032064128256, "grad_norm": 8.225103378295898, "learning_rate": 0.00015000000000000001, "loss": 6.071, "step": 15 }, { "epoch": 0.08550434201736808, "grad_norm": 13.602970123291016, "learning_rate": 0.00016, "loss": 4.9781, "step": 16 }, { "epoch": 0.09084836339345358, "grad_norm": 11.418010711669922, "learning_rate": 0.00017, "loss": 4.3076, "step": 17 }, { "epoch": 0.09619238476953908, "grad_norm": 11.895493507385254, "learning_rate": 0.00018, "loss": 4.0822, "step": 18 }, { "epoch": 0.10153640614562458, "grad_norm": 8.579840660095215, "learning_rate": 0.00019, "loss": 3.4058, "step": 19 }, { "epoch": 0.10688042752171009, "grad_norm": 18.057723999023438, "learning_rate": 0.0002, "loss": 4.8878, "step": 20 }, { "epoch": 0.11222444889779559, "grad_norm": 12.423249244689941, "learning_rate": 0.00019998230608242915, "loss": 5.1401, "step": 21 }, { "epoch": 0.11756847027388109, "grad_norm": 9.204449653625488, "learning_rate": 0.00019992923059121106, "loss": 5.112, "step": 22 }, { "epoch": 0.1229124916499666, "grad_norm": 15.079995155334473, "learning_rate": 0.00019984079230861296, "loss": 4.8558, "step": 23 }, { "epoch": 0.1282565130260521, "grad_norm": 32.646522521972656, "learning_rate": 0.00019971702253102856, "loss": 4.1068, "step": 24 }, { "epoch": 0.13360053440213762, "grad_norm": 10.601286888122559, "learning_rate": 0.00019955796505790268, "loss": 3.5866, "step": 25 }, { "epoch": 0.13894455577822312, "grad_norm": 9.367355346679688, "learning_rate": 0.00019936367617623171, "loss": 5.0576, "step": 26 }, { "epoch": 0.14428857715430862, "grad_norm": 7.64223575592041, "learning_rate": 0.0001991342246406448, "loss": 5.3104, "step": 27 }, { "epoch": 0.14963259853039412, "grad_norm": 6.789806842803955, "learning_rate": 0.00019886969164907307, "loss": 4.7237, "step": 28 }, { "epoch": 0.15497661990647962, "grad_norm": 6.976108551025391, "learning_rate": 0.00019857017081401548, "loss": 4.3104, "step": 29 }, { "epoch": 0.16032064128256512, "grad_norm": 4.512085914611816, "learning_rate": 0.00019823576812941137, "loss": 4.2295, "step": 30 }, { "epoch": 0.16566466265865062, "grad_norm": 4.308312892913818, "learning_rate": 0.00019786660193313148, "loss": 4.3143, "step": 31 }, { "epoch": 0.17100868403473615, "grad_norm": 3.4649343490600586, "learning_rate": 0.0001974628028651007, "loss": 4.1055, "step": 32 }, { "epoch": 0.17635270541082165, "grad_norm": 4.710155963897705, "learning_rate": 0.0001970245138210676, "loss": 3.2729, "step": 33 }, { "epoch": 0.18169672678690715, "grad_norm": 4.550477027893066, "learning_rate": 0.00019655188990203647, "loss": 3.0624, "step": 34 }, { "epoch": 0.18704074816299265, "grad_norm": 4.579635143280029, "learning_rate": 0.00019604509835938064, "loss": 3.0187, "step": 35 }, { "epoch": 0.19238476953907815, "grad_norm": 4.524958610534668, "learning_rate": 0.00019550431853565577, "loss": 3.6331, "step": 36 }, { "epoch": 0.19772879091516365, "grad_norm": 3.702008008956909, "learning_rate": 0.00019492974180113426, "loss": 3.2045, "step": 37 }, { "epoch": 0.20307281229124916, "grad_norm": 3.5903921127319336, "learning_rate": 0.00019432157148608378, "loss": 3.7639, "step": 38 }, { "epoch": 0.20841683366733466, "grad_norm": 4.272071838378906, "learning_rate": 0.00019368002280881278, "loss": 3.5112, "step": 39 }, { "epoch": 0.21376085504342018, "grad_norm": 7.924098968505859, "learning_rate": 0.00019300532279950948, "loss": 3.8263, "step": 40 }, { "epoch": 0.21910487641950568, "grad_norm": 3.829366683959961, "learning_rate": 0.00019229771021990095, "loss": 2.9752, "step": 41 }, { "epoch": 0.22444889779559118, "grad_norm": 10.562247276306152, "learning_rate": 0.00019155743547876023, "loss": 1.8046, "step": 42 }, { "epoch": 0.22979291917167669, "grad_norm": 6.675294399261475, "learning_rate": 0.00019078476054329237, "loss": 1.5568, "step": 43 }, { "epoch": 0.23513694054776219, "grad_norm": 22.542741775512695, "learning_rate": 0.00018997995884642967, "loss": 1.4916, "step": 44 }, { "epoch": 0.24048096192384769, "grad_norm": 11.773090362548828, "learning_rate": 0.00018914331519006986, "loss": 2.6503, "step": 45 }, { "epoch": 0.2458249832999332, "grad_norm": 7.742423057556152, "learning_rate": 0.00018827512564429074, "loss": 3.6861, "step": 46 }, { "epoch": 0.2511690046760187, "grad_norm": 7.848352909088135, "learning_rate": 0.00018737569744257756, "loss": 3.7844, "step": 47 }, { "epoch": 0.2511690046760187, "eval_loss": 3.2015836238861084, "eval_runtime": 16.1976, "eval_samples_per_second": 19.509, "eval_steps_per_second": 4.877, "step": 47 }, { "epoch": 0.2565130260521042, "grad_norm": 6.551794052124023, "learning_rate": 0.00018644534887309944, "loss": 3.9149, "step": 48 }, { "epoch": 0.2618570474281897, "grad_norm": 6.568101406097412, "learning_rate": 0.00018548440916607453, "loss": 3.0155, "step": 49 }, { "epoch": 0.26720106880427524, "grad_norm": 5.584553241729736, "learning_rate": 0.00018449321837726208, "loss": 2.9737, "step": 50 }, { "epoch": 0.2725450901803607, "grad_norm": 17.561307907104492, "learning_rate": 0.00018347212726762437, "loss": 5.1934, "step": 51 }, { "epoch": 0.27788911155644624, "grad_norm": 18.844377517700195, "learning_rate": 0.00018242149717919993, "loss": 5.1302, "step": 52 }, { "epoch": 0.2832331329325317, "grad_norm": 10.627951622009277, "learning_rate": 0.00018134169990723247, "loss": 4.5663, "step": 53 }, { "epoch": 0.28857715430861725, "grad_norm": 6.735750198364258, "learning_rate": 0.00018023311756860038, "loss": 3.7202, "step": 54 }, { "epoch": 0.2939211756847027, "grad_norm": 4.434415817260742, "learning_rate": 0.00017909614246659409, "loss": 4.1791, "step": 55 }, { "epoch": 0.29926519706078825, "grad_norm": 4.674170017242432, "learning_rate": 0.00017793117695208828, "loss": 3.8663, "step": 56 }, { "epoch": 0.3046092184368738, "grad_norm": 5.160229206085205, "learning_rate": 0.0001767386332811587, "loss": 3.8715, "step": 57 }, { "epoch": 0.30995323981295925, "grad_norm": 4.293652057647705, "learning_rate": 0.00017551893346919362, "loss": 2.5835, "step": 58 }, { "epoch": 0.3152972611890448, "grad_norm": 4.6995625495910645, "learning_rate": 0.0001742725091415517, "loss": 2.7618, "step": 59 }, { "epoch": 0.32064128256513025, "grad_norm": 5.258271217346191, "learning_rate": 0.00017299980138081922, "loss": 3.1181, "step": 60 }, { "epoch": 0.3259853039412158, "grad_norm": 3.5829501152038574, "learning_rate": 0.00017170126057072032, "loss": 3.3912, "step": 61 }, { "epoch": 0.33132932531730125, "grad_norm": 4.662436485290527, "learning_rate": 0.00017037734623673615, "loss": 3.1201, "step": 62 }, { "epoch": 0.3366733466933868, "grad_norm": 4.6757307052612305, "learning_rate": 0.00016902852688348866, "loss": 3.1055, "step": 63 }, { "epoch": 0.3420173680694723, "grad_norm": 3.675757884979248, "learning_rate": 0.00016765527982894689, "loss": 3.4294, "step": 64 }, { "epoch": 0.3473613894455578, "grad_norm": 3.7871510982513428, "learning_rate": 0.00016625809103551462, "loss": 3.1576, "step": 65 }, { "epoch": 0.3527054108216433, "grad_norm": 7.090997219085693, "learning_rate": 0.0001648374549380587, "loss": 1.9401, "step": 66 }, { "epoch": 0.3580494321977288, "grad_norm": 5.046462535858154, "learning_rate": 0.00016339387426893918, "loss": 1.7757, "step": 67 }, { "epoch": 0.3633934535738143, "grad_norm": 4.517994403839111, "learning_rate": 0.00016192785988010353, "loss": 1.3564, "step": 68 }, { "epoch": 0.3687374749498998, "grad_norm": 3.0163919925689697, "learning_rate": 0.0001604399305623067, "loss": 1.3458, "step": 69 }, { "epoch": 0.3740814963259853, "grad_norm": 4.087157249450684, "learning_rate": 0.00015893061286152276, "loss": 2.8926, "step": 70 }, { "epoch": 0.37942551770207084, "grad_norm": 4.707438945770264, "learning_rate": 0.00015740044089261138, "loss": 3.0473, "step": 71 }, { "epoch": 0.3847695390781563, "grad_norm": 8.234162330627441, "learning_rate": 0.00015584995615030634, "loss": 3.6788, "step": 72 }, { "epoch": 0.39011356045424184, "grad_norm": 7.497130870819092, "learning_rate": 0.00015427970731759212, "loss": 4.081, "step": 73 }, { "epoch": 0.3954575818303273, "grad_norm": 6.302802085876465, "learning_rate": 0.000152690250071537, "loss": 3.5992, "step": 74 }, { "epoch": 0.40080160320641284, "grad_norm": 7.252871036529541, "learning_rate": 0.0001510821468866508, "loss": 3.1878, "step": 75 }, { "epoch": 0.4061456245824983, "grad_norm": 4.067234516143799, "learning_rate": 0.00014945596683583754, "loss": 3.7711, "step": 76 }, { "epoch": 0.41148964595858384, "grad_norm": 3.713172435760498, "learning_rate": 0.00014781228538901267, "loss": 3.8432, "step": 77 }, { "epoch": 0.4168336673346693, "grad_norm": 3.5716781616210938, "learning_rate": 0.00014615168420945688, "loss": 3.6756, "step": 78 }, { "epoch": 0.42217768871075484, "grad_norm": 3.4458560943603516, "learning_rate": 0.00014447475094797797, "loss": 3.1908, "step": 79 }, { "epoch": 0.42752171008684037, "grad_norm": 2.959568500518799, "learning_rate": 0.0001427820790349539, "loss": 3.6547, "step": 80 }, { "epoch": 0.43286573146292584, "grad_norm": 3.844724178314209, "learning_rate": 0.00014107426747033075, "loss": 3.4797, "step": 81 }, { "epoch": 0.43820975283901137, "grad_norm": 3.2627336978912354, "learning_rate": 0.00013935192061164956, "loss": 3.4215, "step": 82 }, { "epoch": 0.44355377421509684, "grad_norm": 3.0022361278533936, "learning_rate": 0.00013761564796017724, "loss": 2.3842, "step": 83 }, { "epoch": 0.44889779559118237, "grad_norm": 2.4692890644073486, "learning_rate": 0.0001358660639452173, "loss": 2.2673, "step": 84 }, { "epoch": 0.45424181696726784, "grad_norm": 2.601637363433838, "learning_rate": 0.0001341037877066766, "loss": 2.8049, "step": 85 }, { "epoch": 0.45958583834335337, "grad_norm": 2.877810478210449, "learning_rate": 0.00013232944287596522, "loss": 2.9897, "step": 86 }, { "epoch": 0.4649298597194389, "grad_norm": 2.801961898803711, "learning_rate": 0.00013054365735530664, "loss": 2.969, "step": 87 }, { "epoch": 0.47027388109552437, "grad_norm": 3.4799296855926514, "learning_rate": 0.00012874706309553698, "loss": 2.7851, "step": 88 }, { "epoch": 0.4756179024716099, "grad_norm": 3.7868473529815674, "learning_rate": 0.00012694029587247095, "loss": 3.4085, "step": 89 }, { "epoch": 0.48096192384769537, "grad_norm": 3.071875810623169, "learning_rate": 0.0001251239950619149, "loss": 3.3867, "step": 90 }, { "epoch": 0.4863059452237809, "grad_norm": 8.204347610473633, "learning_rate": 0.0001232988034134053, "loss": 1.6884, "step": 91 }, { "epoch": 0.4916499665998664, "grad_norm": 5.938605785369873, "learning_rate": 0.00012146536682275387, "loss": 1.5711, "step": 92 }, { "epoch": 0.4969939879759519, "grad_norm": 3.6202452182769775, "learning_rate": 0.0001196243341034786, "loss": 1.7918, "step": 93 }, { "epoch": 0.5023380093520374, "grad_norm": 3.0969438552856445, "learning_rate": 0.00011777635675720313, "loss": 1.42, "step": 94 }, { "epoch": 0.5023380093520374, "eval_loss": 2.7997498512268066, "eval_runtime": 16.1659, "eval_samples_per_second": 19.547, "eval_steps_per_second": 4.887, "step": 94 } ], "logging_steps": 1, "max_steps": 187, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 47, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 7.740853165699891e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }