| { | |
| "best_metric": 6.110002040863037, | |
| "best_model_checkpoint": "./results/models/checkpoint-242575", | |
| "epoch": 34.0, | |
| "eval_steps": 500, | |
| "global_step": 266050, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.001997444089456869, | |
| "loss": 6.3873, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.001994888178913738, | |
| "loss": 6.2714, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0019923322683706073, | |
| "loss": 6.3526, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.001989776357827476, | |
| "loss": 6.3696, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.001987220447284345, | |
| "loss": 6.3501, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.001984664536741214, | |
| "loss": 6.3472, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.001982108626198083, | |
| "loss": 6.347, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0019795527156549523, | |
| "loss": 6.3555, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0019769968051118214, | |
| "loss": 6.3432, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00197444089456869, | |
| "loss": 6.3439, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.001971884984025559, | |
| "loss": 6.3312, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.001969329073482428, | |
| "loss": 6.3279, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0019667731629392973, | |
| "loss": 6.3177, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.001964217252396166, | |
| "loss": 6.3152, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.001961661341853035, | |
| "loss": 6.3086, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 6.252776145935059, | |
| "eval_runtime": 6.9192, | |
| "eval_samples_per_second": 36.276, | |
| "eval_steps_per_second": 1.156, | |
| "step": 7825 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.001959105431309904, | |
| "loss": 6.3102, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.001956549520766773, | |
| "loss": 6.2978, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0019539936102236422, | |
| "loss": 6.2904, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.001951437699680511, | |
| "loss": 6.2953, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0019488817891373802, | |
| "loss": 6.2988, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0019463258785942493, | |
| "loss": 6.2859, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0019437699680511184, | |
| "loss": 6.2906, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0019412140575079872, | |
| "loss": 6.2936, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0019386581469648563, | |
| "loss": 6.288, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0019361022364217254, | |
| "loss": 6.2888, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0019335463258785943, | |
| "loss": 6.2866, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0019309904153354633, | |
| "loss": 6.2776, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0019284345047923324, | |
| "loss": 6.2706, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0019258785942492015, | |
| "loss": 6.2705, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0019233226837060702, | |
| "loss": 6.2807, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0019207667731629392, | |
| "loss": 6.278, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 6.216161251068115, | |
| "eval_runtime": 6.9294, | |
| "eval_samples_per_second": 36.223, | |
| "eval_steps_per_second": 1.155, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0019182108626198083, | |
| "loss": 6.2688, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0019156549520766772, | |
| "loss": 6.2732, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0019130990415335463, | |
| "loss": 6.2603, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0019105431309904154, | |
| "loss": 6.2656, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.0019079872204472844, | |
| "loss": 6.2551, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.0019054313099041533, | |
| "loss": 6.259, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0019028753993610224, | |
| "loss": 6.2607, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.0019003194888178915, | |
| "loss": 6.2634, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0018977635782747603, | |
| "loss": 6.26, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0018952076677316294, | |
| "loss": 6.2502, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.0018926517571884985, | |
| "loss": 6.2453, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.0018900958466453676, | |
| "loss": 6.2529, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.0018875399361022365, | |
| "loss": 6.2493, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0018849840255591055, | |
| "loss": 6.2534, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0018824281150159746, | |
| "loss": 6.2442, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6.19460391998291, | |
| "eval_runtime": 6.7538, | |
| "eval_samples_per_second": 37.164, | |
| "eval_steps_per_second": 1.185, | |
| "step": 23475 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0018798722044728435, | |
| "loss": 6.2498, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0018773162939297126, | |
| "loss": 6.2428, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.0018747603833865817, | |
| "loss": 6.2447, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.0018722044728434505, | |
| "loss": 6.24, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.0018696485623003194, | |
| "loss": 6.2476, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 0.0018670926517571885, | |
| "loss": 6.2486, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.0018645367412140576, | |
| "loss": 6.2428, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 0.0018619808306709264, | |
| "loss": 6.2475, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 0.0018594249201277955, | |
| "loss": 6.2481, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.0018568690095846646, | |
| "loss": 6.2381, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.0018543130990415334, | |
| "loss": 6.2402, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0018517571884984025, | |
| "loss": 6.2389, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 0.0018492012779552716, | |
| "loss": 6.2414, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 0.0018466453674121407, | |
| "loss": 6.2373, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 0.0018440894568690096, | |
| "loss": 6.2408, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 0.0018415335463258786, | |
| "loss": 6.2299, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 6.177552700042725, | |
| "eval_runtime": 6.7861, | |
| "eval_samples_per_second": 36.987, | |
| "eval_steps_per_second": 1.179, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.0018389776357827477, | |
| "loss": 6.2279, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0018364217252396166, | |
| "loss": 6.2341, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 0.0018338658146964857, | |
| "loss": 6.2291, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.0018313099041533548, | |
| "loss": 6.2349, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 0.0018287539936102238, | |
| "loss": 6.231, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.0018261980830670927, | |
| "loss": 6.2295, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.0018236421725239618, | |
| "loss": 6.2344, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.0018210862619808307, | |
| "loss": 6.2289, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 0.0018185303514376995, | |
| "loss": 6.2309, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 0.0018159744408945686, | |
| "loss": 6.2255, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 0.0018134185303514377, | |
| "loss": 6.2281, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.0018108626198083068, | |
| "loss": 6.2269, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 0.0018083067092651756, | |
| "loss": 6.2235, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 0.0018057507987220447, | |
| "loss": 6.2252, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 0.0018031948881789138, | |
| "loss": 6.2243, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 0.0018006389776357827, | |
| "loss": 6.2243, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 6.16984748840332, | |
| "eval_runtime": 6.9467, | |
| "eval_samples_per_second": 36.132, | |
| "eval_steps_per_second": 1.152, | |
| "step": 39125 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.0017980830670926518, | |
| "loss": 6.2197, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0017955271565495208, | |
| "loss": 6.2246, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 0.00179297124600639, | |
| "loss": 6.2219, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 0.0017904153354632588, | |
| "loss": 6.2246, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 0.0017878594249201279, | |
| "loss": 6.2203, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 0.001785303514376997, | |
| "loss": 6.2305, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.0017827476038338658, | |
| "loss": 6.225, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 0.001780191693290735, | |
| "loss": 6.2216, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 0.001777635782747604, | |
| "loss": 6.2242, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 0.001775079872204473, | |
| "loss": 6.224, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 0.001772523961661342, | |
| "loss": 6.2168, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.0017699680511182108, | |
| "loss": 6.2249, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.00176741214057508, | |
| "loss": 6.2202, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 0.0017648562300319488, | |
| "loss": 6.2227, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 0.0017623003194888178, | |
| "loss": 6.2162, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 6.162996768951416, | |
| "eval_runtime": 6.7939, | |
| "eval_samples_per_second": 36.945, | |
| "eval_steps_per_second": 1.178, | |
| "step": 46950 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 0.001759744408945687, | |
| "loss": 6.2237, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 0.0017571884984025558, | |
| "loss": 6.2159, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.0017546325878594249, | |
| "loss": 6.2176, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 0.001752076677316294, | |
| "loss": 6.2175, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.001749520766773163, | |
| "loss": 6.2171, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 0.001746964856230032, | |
| "loss": 6.2105, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 0.001744408945686901, | |
| "loss": 6.221, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.00174185303514377, | |
| "loss": 6.2141, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 0.001739297124600639, | |
| "loss": 6.213, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 0.001736741214057508, | |
| "loss": 6.2182, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 0.0017341853035143771, | |
| "loss": 6.2085, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 0.0017316293929712462, | |
| "loss": 6.2142, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 0.001729073482428115, | |
| "loss": 6.2274, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 0.0017265175718849841, | |
| "loss": 6.2124, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 0.0017239616613418532, | |
| "loss": 6.2105, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 0.0017214057507987219, | |
| "loss": 6.2079, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 6.15675163269043, | |
| "eval_runtime": 6.7761, | |
| "eval_samples_per_second": 37.042, | |
| "eval_steps_per_second": 1.181, | |
| "step": 54775 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 0.001718849840255591, | |
| "loss": 6.2153, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 0.00171629392971246, | |
| "loss": 6.2105, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 0.0017137380191693291, | |
| "loss": 6.2111, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 0.001711182108626198, | |
| "loss": 6.2167, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 0.001708626198083067, | |
| "loss": 6.216, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 0.0017060702875399362, | |
| "loss": 6.2144, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 0.001703514376996805, | |
| "loss": 6.2141, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 0.001700958466453674, | |
| "loss": 6.2139, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 0.0016984025559105432, | |
| "loss": 6.2117, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 0.0016958466453674123, | |
| "loss": 6.2122, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 0.0016932907348242811, | |
| "loss": 6.2096, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 0.0016907348242811502, | |
| "loss": 6.2055, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.0016881789137380193, | |
| "loss": 6.2088, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 0.0016856230031948882, | |
| "loss": 6.2105, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 0.0016830670926517573, | |
| "loss": 6.2161, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 0.0016805111821086263, | |
| "loss": 6.2105, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 6.1555399894714355, | |
| "eval_runtime": 6.9246, | |
| "eval_samples_per_second": 36.248, | |
| "eval_steps_per_second": 1.155, | |
| "step": 62600 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 0.0016779552715654954, | |
| "loss": 6.2111, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 0.0016753993610223643, | |
| "loss": 6.2095, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 0.0016728434504792334, | |
| "loss": 6.2064, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 0.0016702875399361022, | |
| "loss": 6.2147, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 0.001667731629392971, | |
| "loss": 6.1994, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 0.0016651757188498402, | |
| "loss": 6.2094, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 0.0016626198083067093, | |
| "loss": 6.2075, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 0.0016600638977635781, | |
| "loss": 6.2085, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 0.0016575079872204472, | |
| "loss": 6.2004, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 0.0016549520766773163, | |
| "loss": 6.2112, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 0.0016523961661341854, | |
| "loss": 6.2051, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 0.0016498402555910543, | |
| "loss": 6.2024, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 0.0016472843450479233, | |
| "loss": 6.1996, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 0.0016447284345047924, | |
| "loss": 6.2066, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 0.0016421725239616613, | |
| "loss": 6.2013, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 6.147340297698975, | |
| "eval_runtime": 6.7973, | |
| "eval_samples_per_second": 36.927, | |
| "eval_steps_per_second": 1.177, | |
| "step": 70425 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 0.0016396166134185304, | |
| "loss": 6.2085, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 0.0016370607028753995, | |
| "loss": 6.1978, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.0016345047923322685, | |
| "loss": 6.2017, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 0.0016319488817891374, | |
| "loss": 6.2047, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 0.0016293929712460065, | |
| "loss": 6.1998, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 0.0016268370607028756, | |
| "loss": 6.2027, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 0.0016242811501597444, | |
| "loss": 6.2024, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 0.0016217252396166135, | |
| "loss": 6.1936, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 0.0016191693290734824, | |
| "loss": 6.2042, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 0.0016166134185303515, | |
| "loss": 6.2021, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 0.0016140575079872203, | |
| "loss": 6.2054, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 0.0016115015974440894, | |
| "loss": 6.2051, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 0.0016089456869009585, | |
| "loss": 6.1963, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 0.0016063897763578274, | |
| "loss": 6.2039, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 0.0016038338658146965, | |
| "loss": 6.1993, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 0.0016012779552715655, | |
| "loss": 6.199, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 6.143795967102051, | |
| "eval_runtime": 6.7856, | |
| "eval_samples_per_second": 36.99, | |
| "eval_steps_per_second": 1.179, | |
| "step": 78250 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 0.0015987220447284346, | |
| "loss": 6.1969, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 0.0015961661341853035, | |
| "loss": 6.2008, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 0.0015936102236421726, | |
| "loss": 6.1974, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 0.0015910543130990417, | |
| "loss": 6.1966, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 10.29, | |
| "learning_rate": 0.0015884984025559105, | |
| "loss": 6.199, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 0.0015859424920127796, | |
| "loss": 6.2016, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 0.0015833865814696487, | |
| "loss": 6.1986, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 0.0015808306709265178, | |
| "loss": 6.2013, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 10.54, | |
| "learning_rate": 0.0015782747603833866, | |
| "loss": 6.1922, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 10.61, | |
| "learning_rate": 0.0015757188498402557, | |
| "loss": 6.1999, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 0.0015731629392971248, | |
| "loss": 6.1989, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 0.0015706070287539937, | |
| "loss": 6.1963, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 0.0015680511182108625, | |
| "loss": 6.1966, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 0.0015654952076677316, | |
| "loss": 6.1955, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "learning_rate": 0.0015629392971246005, | |
| "loss": 6.1943, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 0.0015603833865814696, | |
| "loss": 6.1953, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 6.140895366668701, | |
| "eval_runtime": 6.7824, | |
| "eval_samples_per_second": 37.007, | |
| "eval_steps_per_second": 1.18, | |
| "step": 86075 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 0.0015578274760383386, | |
| "loss": 6.1972, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 0.0015552715654952077, | |
| "loss": 6.1896, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 0.0015527156549520766, | |
| "loss": 6.1901, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 0.0015501597444089457, | |
| "loss": 6.1917, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 0.0015476038338658148, | |
| "loss": 6.194, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 0.0015450479233226836, | |
| "loss": 6.1934, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "learning_rate": 0.0015424920127795527, | |
| "loss": 6.1912, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 0.0015399361022364218, | |
| "loss": 6.1981, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "learning_rate": 0.0015373801916932909, | |
| "loss": 6.1942, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 11.63, | |
| "learning_rate": 0.0015348242811501597, | |
| "loss": 6.1965, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 11.69, | |
| "learning_rate": 0.0015322683706070288, | |
| "loss": 6.1958, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 0.001529712460063898, | |
| "loss": 6.1981, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 0.0015271565495207668, | |
| "loss": 6.1972, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 0.0015246006389776359, | |
| "loss": 6.1959, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 0.001522044728434505, | |
| "loss": 6.1958, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 6.139165878295898, | |
| "eval_runtime": 6.8854, | |
| "eval_samples_per_second": 36.454, | |
| "eval_steps_per_second": 1.162, | |
| "step": 93900 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 0.001519488817891374, | |
| "loss": 6.1901, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 12.08, | |
| "learning_rate": 0.0015169329073482427, | |
| "loss": 6.1945, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 0.0015143769968051118, | |
| "loss": 6.1949, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 0.0015118210862619808, | |
| "loss": 6.1881, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 0.0015092651757188497, | |
| "loss": 6.189, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 0.0015067092651757188, | |
| "loss": 6.1923, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 0.0015041533546325879, | |
| "loss": 6.1962, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "learning_rate": 0.001501597444089457, | |
| "loss": 6.1911, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 0.0014990415335463258, | |
| "loss": 6.1948, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 12.59, | |
| "learning_rate": 0.001496485623003195, | |
| "loss": 6.197, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 0.001493929712460064, | |
| "loss": 6.1898, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 12.72, | |
| "learning_rate": 0.0014913738019169329, | |
| "loss": 6.1924, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 0.001488817891373802, | |
| "loss": 6.1898, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 0.001486261980830671, | |
| "loss": 6.1934, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 0.0014837060702875401, | |
| "loss": 6.1944, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 0.001481150159744409, | |
| "loss": 6.1935, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 6.138128280639648, | |
| "eval_runtime": 6.8154, | |
| "eval_samples_per_second": 36.829, | |
| "eval_steps_per_second": 1.174, | |
| "step": 101725 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 0.001478594249201278, | |
| "loss": 6.1931, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 0.0014760383386581471, | |
| "loss": 6.1947, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 0.001473482428115016, | |
| "loss": 6.1916, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 0.001470926517571885, | |
| "loss": 6.1923, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 13.29, | |
| "learning_rate": 0.0014683706070287542, | |
| "loss": 6.189, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 13.35, | |
| "learning_rate": 0.0014658146964856228, | |
| "loss": 6.185, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "learning_rate": 0.001463258785942492, | |
| "loss": 6.1979, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 0.001460702875399361, | |
| "loss": 6.1919, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 0.00145814696485623, | |
| "loss": 6.1907, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 0.001455591054313099, | |
| "loss": 6.1877, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 0.001453035143769968, | |
| "loss": 6.1884, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "learning_rate": 0.0014504792332268371, | |
| "loss": 6.1904, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 0.001447923322683706, | |
| "loss": 6.1909, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 0.001445367412140575, | |
| "loss": 6.1957, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 0.0014428115015974441, | |
| "loss": 6.1914, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 0.0014402555910543132, | |
| "loss": 6.1865, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 6.134657859802246, | |
| "eval_runtime": 7.8402, | |
| "eval_samples_per_second": 32.015, | |
| "eval_steps_per_second": 1.02, | |
| "step": 109550 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 0.001437699680511182, | |
| "loss": 6.189, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "learning_rate": 0.0014351437699680512, | |
| "loss": 6.1883, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 0.0014325878594249203, | |
| "loss": 6.1902, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 0.0014300319488817891, | |
| "loss": 6.191, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 0.0014274760383386582, | |
| "loss": 6.1934, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 14.38, | |
| "learning_rate": 0.0014249201277955273, | |
| "loss": 6.1841, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 0.0014223642172523964, | |
| "loss": 6.1861, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 0.0014198083067092652, | |
| "loss": 6.1883, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 0.001417252396166134, | |
| "loss": 6.1884, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 0.0014146964856230032, | |
| "loss": 6.1797, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 0.001412140575079872, | |
| "loss": 6.1894, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 0.0014095846645367411, | |
| "loss": 6.187, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "learning_rate": 0.0014070287539936102, | |
| "loss": 6.1863, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 0.0014044728434504793, | |
| "loss": 6.1849, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 0.0014019169329073482, | |
| "loss": 6.1896, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 6.130258083343506, | |
| "eval_runtime": 6.8222, | |
| "eval_samples_per_second": 36.792, | |
| "eval_steps_per_second": 1.173, | |
| "step": 117375 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 0.0013993610223642173, | |
| "loss": 6.1876, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 0.0013968051118210863, | |
| "loss": 6.1846, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 0.0013942492012779552, | |
| "loss": 6.1883, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 15.21, | |
| "learning_rate": 0.0013916932907348243, | |
| "loss": 6.1785, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 0.0013891373801916934, | |
| "loss": 6.1827, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 15.34, | |
| "learning_rate": 0.0013865814696485625, | |
| "loss": 6.1879, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "learning_rate": 0.0013840255591054313, | |
| "loss": 6.1734, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 15.46, | |
| "learning_rate": 0.0013814696485623004, | |
| "loss": 6.1852, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 0.0013789137380191695, | |
| "loss": 6.1903, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 0.0013763578274760384, | |
| "loss": 6.1877, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 0.0013738019169329074, | |
| "loss": 6.1779, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 0.0013712460063897765, | |
| "loss": 6.185, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 15.78, | |
| "learning_rate": 0.0013686900958466456, | |
| "loss": 6.1835, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 15.85, | |
| "learning_rate": 0.0013661341853035143, | |
| "loss": 6.1792, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 0.0013635782747603833, | |
| "loss": 6.182, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 0.0013610223642172524, | |
| "loss": 6.1884, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 6.127689361572266, | |
| "eval_runtime": 6.7878, | |
| "eval_samples_per_second": 36.978, | |
| "eval_steps_per_second": 1.179, | |
| "step": 125200 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 0.0013584664536741213, | |
| "loss": 6.1881, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 0.0013559105431309904, | |
| "loss": 6.1847, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 0.0013533546325878595, | |
| "loss": 6.1822, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 16.23, | |
| "learning_rate": 0.0013507987220447283, | |
| "loss": 6.1777, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 0.0013482428115015974, | |
| "loss": 6.1886, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 16.36, | |
| "learning_rate": 0.0013456869009584665, | |
| "loss": 6.1844, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 16.42, | |
| "learning_rate": 0.0013431309904153356, | |
| "loss": 6.1775, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 16.49, | |
| "learning_rate": 0.0013405750798722044, | |
| "loss": 6.1829, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 0.0013380191693290735, | |
| "loss": 6.1766, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "learning_rate": 0.0013354632587859426, | |
| "loss": 6.1847, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 16.68, | |
| "learning_rate": 0.0013329073482428115, | |
| "loss": 6.1804, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 16.74, | |
| "learning_rate": 0.0013303514376996806, | |
| "loss": 6.1774, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 16.81, | |
| "learning_rate": 0.0013277955271565496, | |
| "loss": 6.1767, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 16.87, | |
| "learning_rate": 0.0013252396166134187, | |
| "loss": 6.178, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 16.93, | |
| "learning_rate": 0.0013226837060702876, | |
| "loss": 6.1806, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 0.0013201277955271567, | |
| "loss": 6.1809, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 6.124339580535889, | |
| "eval_runtime": 6.8363, | |
| "eval_samples_per_second": 36.716, | |
| "eval_steps_per_second": 1.17, | |
| "step": 133025 | |
| }, | |
| { | |
| "epoch": 17.06, | |
| "learning_rate": 0.0013175718849840258, | |
| "loss": 6.1733, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 0.0013150159744408944, | |
| "loss": 6.1825, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 17.19, | |
| "learning_rate": 0.0013124600638977635, | |
| "loss": 6.1752, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 0.0013099041533546326, | |
| "loss": 6.1785, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 17.32, | |
| "learning_rate": 0.0013073482428115017, | |
| "loss": 6.1761, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 0.0013047923322683705, | |
| "loss": 6.1833, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 0.0013022364217252396, | |
| "loss": 6.1727, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 17.51, | |
| "learning_rate": 0.0012996805111821087, | |
| "loss": 6.1744, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "learning_rate": 0.0012971246006389776, | |
| "loss": 6.1766, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 0.0012945686900958466, | |
| "loss": 6.1754, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 0.0012920127795527157, | |
| "loss": 6.1822, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 0.0012894568690095848, | |
| "loss": 6.1855, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 17.83, | |
| "learning_rate": 0.0012869009584664537, | |
| "loss": 6.1797, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 17.89, | |
| "learning_rate": 0.0012843450479233227, | |
| "loss": 6.1796, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 0.0012817891373801918, | |
| "loss": 6.1814, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 6.123664379119873, | |
| "eval_runtime": 6.845, | |
| "eval_samples_per_second": 36.669, | |
| "eval_steps_per_second": 1.169, | |
| "step": 140850 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 0.0012792332268370607, | |
| "loss": 6.1872, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 0.0012766773162939298, | |
| "loss": 6.1834, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 18.15, | |
| "learning_rate": 0.0012741214057507989, | |
| "loss": 6.1793, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 18.21, | |
| "learning_rate": 0.001271565495207668, | |
| "loss": 6.1731, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 18.27, | |
| "learning_rate": 0.0012690095846645368, | |
| "loss": 6.183, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 0.001266453674121406, | |
| "loss": 6.1745, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 0.0012638977635782748, | |
| "loss": 6.1846, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 0.0012613418530351436, | |
| "loss": 6.1767, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "learning_rate": 0.0012587859424920127, | |
| "loss": 6.1747, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 18.59, | |
| "learning_rate": 0.0012562300319488818, | |
| "loss": 6.1804, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 0.0012536741214057507, | |
| "loss": 6.1729, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 0.0012511182108626197, | |
| "loss": 6.1791, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 18.79, | |
| "learning_rate": 0.0012485623003194888, | |
| "loss": 6.173, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 18.85, | |
| "learning_rate": 0.001246006389776358, | |
| "loss": 6.1732, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 18.91, | |
| "learning_rate": 0.0012434504792332268, | |
| "loss": 6.1771, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "learning_rate": 0.0012408945686900959, | |
| "loss": 6.1754, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 6.119473934173584, | |
| "eval_runtime": 6.9262, | |
| "eval_samples_per_second": 36.239, | |
| "eval_steps_per_second": 1.155, | |
| "step": 148675 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 0.001238338658146965, | |
| "loss": 6.1773, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 19.11, | |
| "learning_rate": 0.0012357827476038338, | |
| "loss": 6.176, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 0.001233226837060703, | |
| "loss": 6.1746, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.001230670926517572, | |
| "loss": 6.1773, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 0.001228115015974441, | |
| "loss": 6.1771, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 0.00122555910543131, | |
| "loss": 6.1736, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 19.42, | |
| "learning_rate": 0.001223003194888179, | |
| "loss": 6.1724, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 0.001220447284345048, | |
| "loss": 6.1809, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 19.55, | |
| "learning_rate": 0.001217891373801917, | |
| "loss": 6.1769, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 19.62, | |
| "learning_rate": 0.001215335463258786, | |
| "loss": 6.1712, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 0.001212779552715655, | |
| "loss": 6.1779, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 19.74, | |
| "learning_rate": 0.001210223642172524, | |
| "loss": 6.1758, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 19.81, | |
| "learning_rate": 0.0012076677316293929, | |
| "loss": 6.1681, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 19.87, | |
| "learning_rate": 0.001205111821086262, | |
| "loss": 6.1728, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 19.94, | |
| "learning_rate": 0.001202555910543131, | |
| "loss": 6.1737, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0012, | |
| "loss": 6.1769, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 6.11764669418335, | |
| "eval_runtime": 6.8248, | |
| "eval_samples_per_second": 36.778, | |
| "eval_steps_per_second": 1.172, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 20.06, | |
| "learning_rate": 0.001197444089456869, | |
| "loss": 6.1785, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 20.13, | |
| "learning_rate": 0.001194888178913738, | |
| "loss": 6.1772, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 20.19, | |
| "learning_rate": 0.0011923322683706071, | |
| "loss": 6.1648, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 20.26, | |
| "learning_rate": 0.001189776357827476, | |
| "loss": 6.1715, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 0.001187220447284345, | |
| "loss": 6.1745, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 20.38, | |
| "learning_rate": 0.0011846645367412142, | |
| "loss": 6.1769, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 20.45, | |
| "learning_rate": 0.001182108626198083, | |
| "loss": 6.1783, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 20.51, | |
| "learning_rate": 0.0011795527156549521, | |
| "loss": 6.1693, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 20.58, | |
| "learning_rate": 0.0011769968051118212, | |
| "loss": 6.1726, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 0.0011744408945686903, | |
| "loss": 6.1676, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 20.7, | |
| "learning_rate": 0.0011718849840255592, | |
| "loss": 6.1669, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 20.77, | |
| "learning_rate": 0.0011693290734824282, | |
| "loss": 6.1636, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0011667731629392973, | |
| "loss": 6.1791, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "learning_rate": 0.001164217252396166, | |
| "loss": 6.1757, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 0.001161661341853035, | |
| "loss": 6.1716, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 6.116322994232178, | |
| "eval_runtime": 6.8185, | |
| "eval_samples_per_second": 36.812, | |
| "eval_steps_per_second": 1.173, | |
| "step": 164325 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 0.0011591054313099041, | |
| "loss": 6.1742, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 21.09, | |
| "learning_rate": 0.001156549520766773, | |
| "loss": 6.1689, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 21.15, | |
| "learning_rate": 0.001153993610223642, | |
| "loss": 6.162, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 21.21, | |
| "learning_rate": 0.0011514376996805112, | |
| "loss": 6.1729, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 0.0011488817891373803, | |
| "loss": 6.1756, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 21.34, | |
| "learning_rate": 0.0011463258785942491, | |
| "loss": 6.1694, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 21.41, | |
| "learning_rate": 0.0011437699680511182, | |
| "loss": 6.1755, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 21.47, | |
| "learning_rate": 0.0011412140575079873, | |
| "loss": 6.1735, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 21.53, | |
| "learning_rate": 0.0011386581469648562, | |
| "loss": 6.1676, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 0.0011361022364217252, | |
| "loss": 6.1716, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 21.66, | |
| "learning_rate": 0.0011335463258785943, | |
| "loss": 6.1737, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 21.73, | |
| "learning_rate": 0.0011309904153354634, | |
| "loss": 6.1743, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 21.79, | |
| "learning_rate": 0.0011284345047923323, | |
| "loss": 6.1749, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 21.85, | |
| "learning_rate": 0.0011258785942492014, | |
| "loss": 6.1724, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 0.0011233226837060704, | |
| "loss": 6.1676, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "learning_rate": 0.0011207667731629393, | |
| "loss": 6.1823, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 6.115005016326904, | |
| "eval_runtime": 57.523, | |
| "eval_samples_per_second": 4.363, | |
| "eval_steps_per_second": 0.139, | |
| "step": 172150 | |
| }, | |
| { | |
| "epoch": 22.04, | |
| "learning_rate": 0.0011182108626198084, | |
| "loss": 6.1729, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 22.11, | |
| "learning_rate": 0.0011156549520766775, | |
| "loss": 6.1746, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 22.17, | |
| "learning_rate": 0.0011130990415335463, | |
| "loss": 6.1732, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 0.0011105431309904152, | |
| "loss": 6.1712, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 22.3, | |
| "learning_rate": 0.0011079872204472843, | |
| "loss": 6.1677, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 22.36, | |
| "learning_rate": 0.0011054313099041534, | |
| "loss": 6.1683, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 22.43, | |
| "learning_rate": 0.0011028753993610222, | |
| "loss": 6.1741, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 22.49, | |
| "learning_rate": 0.0011003194888178913, | |
| "loss": 6.1663, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 0.0010977635782747604, | |
| "loss": 6.1681, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "learning_rate": 0.0010952076677316295, | |
| "loss": 6.174, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 22.68, | |
| "learning_rate": 0.0010926517571884984, | |
| "loss": 6.1674, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 22.75, | |
| "learning_rate": 0.0010900958466453674, | |
| "loss": 6.1701, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 22.81, | |
| "learning_rate": 0.0010875399361022365, | |
| "loss": 6.1724, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 0.0010849840255591054, | |
| "loss": 6.1712, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 22.94, | |
| "learning_rate": 0.0010824281150159745, | |
| "loss": 6.1679, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 6.114222049713135, | |
| "eval_runtime": 6.9135, | |
| "eval_samples_per_second": 36.306, | |
| "eval_steps_per_second": 1.157, | |
| "step": 179975 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 0.0010798722044728436, | |
| "loss": 6.1666, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 23.07, | |
| "learning_rate": 0.0010773162939297126, | |
| "loss": 6.1702, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 23.13, | |
| "learning_rate": 0.0010747603833865815, | |
| "loss": 6.166, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 0.0010722044728434506, | |
| "loss": 6.1651, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 23.26, | |
| "learning_rate": 0.0010696485623003197, | |
| "loss": 6.1721, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 23.32, | |
| "learning_rate": 0.0010670926517571885, | |
| "loss": 6.1721, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 23.39, | |
| "learning_rate": 0.0010645367412140576, | |
| "loss": 6.168, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 23.45, | |
| "learning_rate": 0.0010619808306709265, | |
| "loss": 6.1732, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 23.51, | |
| "learning_rate": 0.0010594249201277954, | |
| "loss": 6.171, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 23.58, | |
| "learning_rate": 0.0010568690095846644, | |
| "loss": 6.1697, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 23.64, | |
| "learning_rate": 0.0010543130990415335, | |
| "loss": 6.1667, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 23.71, | |
| "learning_rate": 0.0010517571884984026, | |
| "loss": 6.1762, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 23.77, | |
| "learning_rate": 0.0010492012779552715, | |
| "loss": 6.1661, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 23.83, | |
| "learning_rate": 0.0010466453674121406, | |
| "loss": 6.1741, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 23.9, | |
| "learning_rate": 0.0010440894568690096, | |
| "loss": 6.166, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 23.96, | |
| "learning_rate": 0.0010415335463258785, | |
| "loss": 6.1697, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 6.112667083740234, | |
| "eval_runtime": 6.8444, | |
| "eval_samples_per_second": 36.672, | |
| "eval_steps_per_second": 1.169, | |
| "step": 187800 | |
| }, | |
| { | |
| "epoch": 24.03, | |
| "learning_rate": 0.0010389776357827476, | |
| "loss": 6.1674, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 24.09, | |
| "learning_rate": 0.0010364217252396167, | |
| "loss": 6.169, | |
| "step": 188500 | |
| }, | |
| { | |
| "epoch": 24.15, | |
| "learning_rate": 0.0010338658146964858, | |
| "loss": 6.1648, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 24.22, | |
| "learning_rate": 0.0010313099041533546, | |
| "loss": 6.1711, | |
| "step": 189500 | |
| }, | |
| { | |
| "epoch": 24.28, | |
| "learning_rate": 0.0010287539936102237, | |
| "loss": 6.1621, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 24.35, | |
| "learning_rate": 0.0010261980830670928, | |
| "loss": 6.1666, | |
| "step": 190500 | |
| }, | |
| { | |
| "epoch": 24.41, | |
| "learning_rate": 0.0010236421725239617, | |
| "loss": 6.1685, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 24.47, | |
| "learning_rate": 0.0010210862619808307, | |
| "loss": 6.171, | |
| "step": 191500 | |
| }, | |
| { | |
| "epoch": 24.54, | |
| "learning_rate": 0.0010185303514376998, | |
| "loss": 6.1777, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 24.6, | |
| "learning_rate": 0.001015974440894569, | |
| "loss": 6.1717, | |
| "step": 192500 | |
| }, | |
| { | |
| "epoch": 24.66, | |
| "learning_rate": 0.0010134185303514378, | |
| "loss": 6.1702, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 24.73, | |
| "learning_rate": 0.0010108626198083066, | |
| "loss": 6.1728, | |
| "step": 193500 | |
| }, | |
| { | |
| "epoch": 24.79, | |
| "learning_rate": 0.0010083067092651757, | |
| "loss": 6.1671, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "learning_rate": 0.0010057507987220446, | |
| "loss": 6.16, | |
| "step": 194500 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "learning_rate": 0.0010031948881789137, | |
| "loss": 6.1631, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 24.98, | |
| "learning_rate": 0.0010006389776357828, | |
| "loss": 6.1719, | |
| "step": 195500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 6.112457275390625, | |
| "eval_runtime": 6.8286, | |
| "eval_samples_per_second": 36.757, | |
| "eval_steps_per_second": 1.172, | |
| "step": 195625 | |
| }, | |
| { | |
| "epoch": 25.05, | |
| "learning_rate": 0.0009980830670926518, | |
| "loss": 6.1638, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "learning_rate": 0.0009955271565495207, | |
| "loss": 6.1723, | |
| "step": 196500 | |
| }, | |
| { | |
| "epoch": 25.18, | |
| "learning_rate": 0.0009929712460063898, | |
| "loss": 6.1753, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 25.24, | |
| "learning_rate": 0.0009904153354632589, | |
| "loss": 6.1636, | |
| "step": 197500 | |
| }, | |
| { | |
| "epoch": 25.3, | |
| "learning_rate": 0.0009878594249201277, | |
| "loss": 6.1734, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 25.37, | |
| "learning_rate": 0.0009853035143769968, | |
| "loss": 6.1705, | |
| "step": 198500 | |
| }, | |
| { | |
| "epoch": 25.43, | |
| "learning_rate": 0.000982747603833866, | |
| "loss": 6.1615, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 25.5, | |
| "learning_rate": 0.000980191693290735, | |
| "loss": 6.1636, | |
| "step": 199500 | |
| }, | |
| { | |
| "epoch": 25.56, | |
| "learning_rate": 0.0009776357827476038, | |
| "loss": 6.1756, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 25.62, | |
| "learning_rate": 0.0009750798722044729, | |
| "loss": 6.1726, | |
| "step": 200500 | |
| }, | |
| { | |
| "epoch": 25.69, | |
| "learning_rate": 0.0009725239616613418, | |
| "loss": 6.1758, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 25.75, | |
| "learning_rate": 0.0009699680511182109, | |
| "loss": 6.1662, | |
| "step": 201500 | |
| }, | |
| { | |
| "epoch": 25.81, | |
| "learning_rate": 0.0009674121405750799, | |
| "loss": 6.1656, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 25.88, | |
| "learning_rate": 0.0009648562300319489, | |
| "loss": 6.1568, | |
| "step": 202500 | |
| }, | |
| { | |
| "epoch": 25.94, | |
| "learning_rate": 0.0009623003194888179, | |
| "loss": 6.1678, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 6.112171649932861, | |
| "eval_runtime": 6.8367, | |
| "eval_samples_per_second": 36.714, | |
| "eval_steps_per_second": 1.17, | |
| "step": 203450 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 0.0009597444089456869, | |
| "loss": 6.1698, | |
| "step": 203500 | |
| }, | |
| { | |
| "epoch": 26.07, | |
| "learning_rate": 0.000957188498402556, | |
| "loss": 6.158, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 26.13, | |
| "learning_rate": 0.000954632587859425, | |
| "loss": 6.1723, | |
| "step": 204500 | |
| }, | |
| { | |
| "epoch": 26.2, | |
| "learning_rate": 0.000952076677316294, | |
| "loss": 6.1665, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 26.26, | |
| "learning_rate": 0.000949520766773163, | |
| "loss": 6.1657, | |
| "step": 205500 | |
| }, | |
| { | |
| "epoch": 26.33, | |
| "learning_rate": 0.0009469648562300319, | |
| "loss": 6.1692, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 26.39, | |
| "learning_rate": 0.000944408945686901, | |
| "loss": 6.1713, | |
| "step": 206500 | |
| }, | |
| { | |
| "epoch": 26.45, | |
| "learning_rate": 0.0009418530351437699, | |
| "loss": 6.1642, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 26.52, | |
| "learning_rate": 0.000939297124600639, | |
| "loss": 6.1679, | |
| "step": 207500 | |
| }, | |
| { | |
| "epoch": 26.58, | |
| "learning_rate": 0.000936741214057508, | |
| "loss": 6.1662, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 26.65, | |
| "learning_rate": 0.0009341853035143771, | |
| "loss": 6.1701, | |
| "step": 208500 | |
| }, | |
| { | |
| "epoch": 26.71, | |
| "learning_rate": 0.000931629392971246, | |
| "loss": 6.1702, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 26.77, | |
| "learning_rate": 0.000929073482428115, | |
| "loss": 6.1672, | |
| "step": 209500 | |
| }, | |
| { | |
| "epoch": 26.84, | |
| "learning_rate": 0.0009265175718849841, | |
| "loss": 6.1697, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 26.9, | |
| "learning_rate": 0.000923961661341853, | |
| "loss": 6.1657, | |
| "step": 210500 | |
| }, | |
| { | |
| "epoch": 26.96, | |
| "learning_rate": 0.000921405750798722, | |
| "loss": 6.1664, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 6.112409591674805, | |
| "eval_runtime": 6.9228, | |
| "eval_samples_per_second": 36.257, | |
| "eval_steps_per_second": 1.156, | |
| "step": 211275 | |
| }, | |
| { | |
| "epoch": 27.03, | |
| "learning_rate": 0.000918849840255591, | |
| "loss": 6.164, | |
| "step": 211500 | |
| }, | |
| { | |
| "epoch": 27.09, | |
| "learning_rate": 0.0009162939297124601, | |
| "loss": 6.1717, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 27.16, | |
| "learning_rate": 0.0009137380191693291, | |
| "loss": 6.1646, | |
| "step": 212500 | |
| }, | |
| { | |
| "epoch": 27.22, | |
| "learning_rate": 0.0009111821086261981, | |
| "loss": 6.1641, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 27.28, | |
| "learning_rate": 0.0009086261980830671, | |
| "loss": 6.1634, | |
| "step": 213500 | |
| }, | |
| { | |
| "epoch": 27.35, | |
| "learning_rate": 0.0009060702875399361, | |
| "loss": 6.17, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 27.41, | |
| "learning_rate": 0.0009035143769968052, | |
| "loss": 6.1703, | |
| "step": 214500 | |
| }, | |
| { | |
| "epoch": 27.48, | |
| "learning_rate": 0.0009009584664536742, | |
| "loss": 6.1721, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "learning_rate": 0.000898402555910543, | |
| "loss": 6.1701, | |
| "step": 215500 | |
| }, | |
| { | |
| "epoch": 27.6, | |
| "learning_rate": 0.0008958466453674121, | |
| "loss": 6.1649, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 27.67, | |
| "learning_rate": 0.0008932907348242811, | |
| "loss": 6.1727, | |
| "step": 216500 | |
| }, | |
| { | |
| "epoch": 27.73, | |
| "learning_rate": 0.0008907348242811502, | |
| "loss": 6.1688, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 27.8, | |
| "learning_rate": 0.0008881789137380192, | |
| "loss": 6.166, | |
| "step": 217500 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "learning_rate": 0.0008856230031948882, | |
| "loss": 6.1683, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 27.92, | |
| "learning_rate": 0.0008830670926517572, | |
| "loss": 6.1647, | |
| "step": 218500 | |
| }, | |
| { | |
| "epoch": 27.99, | |
| "learning_rate": 0.0008805111821086262, | |
| "loss": 6.1643, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 6.111097812652588, | |
| "eval_runtime": 6.8343, | |
| "eval_samples_per_second": 36.727, | |
| "eval_steps_per_second": 1.171, | |
| "step": 219100 | |
| }, | |
| { | |
| "epoch": 28.05, | |
| "learning_rate": 0.0008779552715654953, | |
| "loss": 6.1691, | |
| "step": 219500 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "learning_rate": 0.0008753993610223643, | |
| "loss": 6.1653, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 28.18, | |
| "learning_rate": 0.0008728434504792332, | |
| "loss": 6.1633, | |
| "step": 220500 | |
| }, | |
| { | |
| "epoch": 28.24, | |
| "learning_rate": 0.0008702875399361022, | |
| "loss": 6.1705, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 28.31, | |
| "learning_rate": 0.0008677316293929713, | |
| "loss": 6.1695, | |
| "step": 221500 | |
| }, | |
| { | |
| "epoch": 28.37, | |
| "learning_rate": 0.0008651757188498403, | |
| "loss": 6.168, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 28.43, | |
| "learning_rate": 0.0008626198083067092, | |
| "loss": 6.1652, | |
| "step": 222500 | |
| }, | |
| { | |
| "epoch": 28.5, | |
| "learning_rate": 0.0008600638977635783, | |
| "loss": 6.1695, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 28.56, | |
| "learning_rate": 0.0008575079872204473, | |
| "loss": 6.1675, | |
| "step": 223500 | |
| }, | |
| { | |
| "epoch": 28.63, | |
| "learning_rate": 0.0008549520766773164, | |
| "loss": 6.1634, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 28.69, | |
| "learning_rate": 0.0008523961661341853, | |
| "loss": 6.1728, | |
| "step": 224500 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "learning_rate": 0.0008498402555910543, | |
| "loss": 6.1689, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 28.82, | |
| "learning_rate": 0.0008472843450479233, | |
| "loss": 6.1664, | |
| "step": 225500 | |
| }, | |
| { | |
| "epoch": 28.88, | |
| "learning_rate": 0.0008447284345047923, | |
| "loss": 6.1696, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 28.95, | |
| "learning_rate": 0.0008421725239616614, | |
| "loss": 6.1629, | |
| "step": 226500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 6.1112260818481445, | |
| "eval_runtime": 6.8361, | |
| "eval_samples_per_second": 36.717, | |
| "eval_steps_per_second": 1.17, | |
| "step": 226925 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 0.0008396166134185303, | |
| "loss": 6.1625, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 29.07, | |
| "learning_rate": 0.0008370607028753994, | |
| "loss": 6.167, | |
| "step": 227500 | |
| }, | |
| { | |
| "epoch": 29.14, | |
| "learning_rate": 0.0008345047923322684, | |
| "loss": 6.1627, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 29.2, | |
| "learning_rate": 0.0008319488817891374, | |
| "loss": 6.1653, | |
| "step": 228500 | |
| }, | |
| { | |
| "epoch": 29.27, | |
| "learning_rate": 0.0008293929712460064, | |
| "loss": 6.1711, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 29.33, | |
| "learning_rate": 0.0008268370607028754, | |
| "loss": 6.1661, | |
| "step": 229500 | |
| }, | |
| { | |
| "epoch": 29.39, | |
| "learning_rate": 0.0008242811501597445, | |
| "loss": 6.1655, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 29.46, | |
| "learning_rate": 0.0008217252396166134, | |
| "loss": 6.1738, | |
| "step": 230500 | |
| }, | |
| { | |
| "epoch": 29.52, | |
| "learning_rate": 0.0008191693290734825, | |
| "loss": 6.1657, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 29.58, | |
| "learning_rate": 0.0008166134185303514, | |
| "loss": 6.1686, | |
| "step": 231500 | |
| }, | |
| { | |
| "epoch": 29.65, | |
| "learning_rate": 0.0008140575079872204, | |
| "loss": 6.1636, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 29.71, | |
| "learning_rate": 0.0008115015974440895, | |
| "loss": 6.1645, | |
| "step": 232500 | |
| }, | |
| { | |
| "epoch": 29.78, | |
| "learning_rate": 0.0008089456869009585, | |
| "loss": 6.1653, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 29.84, | |
| "learning_rate": 0.0008063897763578275, | |
| "loss": 6.1602, | |
| "step": 233500 | |
| }, | |
| { | |
| "epoch": 29.9, | |
| "learning_rate": 0.0008038338658146965, | |
| "loss": 6.1667, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 29.97, | |
| "learning_rate": 0.0008012779552715655, | |
| "loss": 6.1712, | |
| "step": 234500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 6.1112165451049805, | |
| "eval_runtime": 6.8132, | |
| "eval_samples_per_second": 36.84, | |
| "eval_steps_per_second": 1.174, | |
| "step": 234750 | |
| }, | |
| { | |
| "epoch": 30.03, | |
| "learning_rate": 0.0007987220447284346, | |
| "loss": 6.1752, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 30.1, | |
| "learning_rate": 0.0007961661341853034, | |
| "loss": 6.1726, | |
| "step": 235500 | |
| }, | |
| { | |
| "epoch": 30.16, | |
| "learning_rate": 0.0007936102236421725, | |
| "loss": 6.1653, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "learning_rate": 0.0007910543130990415, | |
| "loss": 6.1677, | |
| "step": 236500 | |
| }, | |
| { | |
| "epoch": 30.29, | |
| "learning_rate": 0.0007884984025559106, | |
| "loss": 6.1666, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 30.35, | |
| "learning_rate": 0.0007859424920127796, | |
| "loss": 6.1628, | |
| "step": 237500 | |
| }, | |
| { | |
| "epoch": 30.42, | |
| "learning_rate": 0.0007833865814696485, | |
| "loss": 6.1717, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 30.48, | |
| "learning_rate": 0.0007808306709265176, | |
| "loss": 6.1636, | |
| "step": 238500 | |
| }, | |
| { | |
| "epoch": 30.54, | |
| "learning_rate": 0.0007782747603833866, | |
| "loss": 6.1666, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 30.61, | |
| "learning_rate": 0.0007757188498402557, | |
| "loss": 6.1612, | |
| "step": 239500 | |
| }, | |
| { | |
| "epoch": 30.67, | |
| "learning_rate": 0.0007731629392971247, | |
| "loss": 6.1623, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 30.73, | |
| "learning_rate": 0.0007706070287539936, | |
| "loss": 6.1657, | |
| "step": 240500 | |
| }, | |
| { | |
| "epoch": 30.8, | |
| "learning_rate": 0.0007680511182108626, | |
| "loss": 6.1634, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "learning_rate": 0.0007654952076677316, | |
| "loss": 6.1704, | |
| "step": 241500 | |
| }, | |
| { | |
| "epoch": 30.93, | |
| "learning_rate": 0.0007629392971246007, | |
| "loss": 6.1684, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "learning_rate": 0.0007603833865814696, | |
| "loss": 6.1588, | |
| "step": 242500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 6.110002040863037, | |
| "eval_runtime": 6.9156, | |
| "eval_samples_per_second": 36.295, | |
| "eval_steps_per_second": 1.157, | |
| "step": 242575 | |
| }, | |
| { | |
| "epoch": 31.05, | |
| "learning_rate": 0.0007578274760383387, | |
| "loss": 6.167, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 31.12, | |
| "learning_rate": 0.0007552715654952077, | |
| "loss": 6.1609, | |
| "step": 243500 | |
| }, | |
| { | |
| "epoch": 31.18, | |
| "learning_rate": 0.0007527156549520767, | |
| "loss": 6.1638, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 0.0007501597444089458, | |
| "loss": 6.1655, | |
| "step": 244500 | |
| }, | |
| { | |
| "epoch": 31.31, | |
| "learning_rate": 0.0007476038338658147, | |
| "loss": 6.1675, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 31.37, | |
| "learning_rate": 0.0007450479233226837, | |
| "loss": 6.1714, | |
| "step": 245500 | |
| }, | |
| { | |
| "epoch": 31.44, | |
| "learning_rate": 0.0007424920127795527, | |
| "loss": 6.1628, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 31.5, | |
| "learning_rate": 0.0007399361022364218, | |
| "loss": 6.1674, | |
| "step": 246500 | |
| }, | |
| { | |
| "epoch": 31.57, | |
| "learning_rate": 0.0007373801916932907, | |
| "loss": 6.1589, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 31.63, | |
| "learning_rate": 0.0007348242811501597, | |
| "loss": 6.1727, | |
| "step": 247500 | |
| }, | |
| { | |
| "epoch": 31.69, | |
| "learning_rate": 0.0007322683706070288, | |
| "loss": 6.1688, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 31.76, | |
| "learning_rate": 0.0007297124600638978, | |
| "loss": 6.1678, | |
| "step": 248500 | |
| }, | |
| { | |
| "epoch": 31.82, | |
| "learning_rate": 0.0007271565495207669, | |
| "loss": 6.162, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 31.88, | |
| "learning_rate": 0.0007246006389776358, | |
| "loss": 6.1671, | |
| "step": 249500 | |
| }, | |
| { | |
| "epoch": 31.95, | |
| "learning_rate": 0.0007220447284345049, | |
| "loss": 6.1686, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 6.110647201538086, | |
| "eval_runtime": 6.86, | |
| "eval_samples_per_second": 36.589, | |
| "eval_steps_per_second": 1.166, | |
| "step": 250400 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 0.0007194888178913738, | |
| "loss": 6.1651, | |
| "step": 250500 | |
| }, | |
| { | |
| "epoch": 32.08, | |
| "learning_rate": 0.0007169329073482428, | |
| "loss": 6.1736, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 32.14, | |
| "learning_rate": 0.0007143769968051118, | |
| "loss": 6.1687, | |
| "step": 251500 | |
| }, | |
| { | |
| "epoch": 32.2, | |
| "learning_rate": 0.0007118210862619808, | |
| "loss": 6.1646, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 32.27, | |
| "learning_rate": 0.0007092651757188499, | |
| "loss": 6.1676, | |
| "step": 252500 | |
| }, | |
| { | |
| "epoch": 32.33, | |
| "learning_rate": 0.0007067092651757189, | |
| "loss": 6.1536, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 32.4, | |
| "learning_rate": 0.0007041533546325878, | |
| "loss": 6.1628, | |
| "step": 253500 | |
| }, | |
| { | |
| "epoch": 32.46, | |
| "learning_rate": 0.0007015974440894569, | |
| "loss": 6.1662, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 32.52, | |
| "learning_rate": 0.0006990415335463259, | |
| "loss": 6.171, | |
| "step": 254500 | |
| }, | |
| { | |
| "epoch": 32.59, | |
| "learning_rate": 0.000696485623003195, | |
| "loss": 6.1691, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 32.65, | |
| "learning_rate": 0.0006939297124600638, | |
| "loss": 6.1668, | |
| "step": 255500 | |
| }, | |
| { | |
| "epoch": 32.72, | |
| "learning_rate": 0.0006913738019169329, | |
| "loss": 6.1738, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 32.78, | |
| "learning_rate": 0.0006888178913738019, | |
| "loss": 6.1652, | |
| "step": 256500 | |
| }, | |
| { | |
| "epoch": 32.84, | |
| "learning_rate": 0.0006862619808306709, | |
| "loss": 6.164, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 32.91, | |
| "learning_rate": 0.00068370607028754, | |
| "loss": 6.1592, | |
| "step": 257500 | |
| }, | |
| { | |
| "epoch": 32.97, | |
| "learning_rate": 0.0006811501597444089, | |
| "loss": 6.167, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 6.110122203826904, | |
| "eval_runtime": 6.8168, | |
| "eval_samples_per_second": 36.821, | |
| "eval_steps_per_second": 1.174, | |
| "step": 258225 | |
| }, | |
| { | |
| "epoch": 33.04, | |
| "learning_rate": 0.000678594249201278, | |
| "loss": 6.1653, | |
| "step": 258500 | |
| }, | |
| { | |
| "epoch": 33.1, | |
| "learning_rate": 0.000676038338658147, | |
| "loss": 6.1616, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 33.16, | |
| "learning_rate": 0.0006734824281150161, | |
| "loss": 6.1651, | |
| "step": 259500 | |
| }, | |
| { | |
| "epoch": 33.23, | |
| "learning_rate": 0.0006709265175718851, | |
| "loss": 6.1698, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 33.29, | |
| "learning_rate": 0.0006683706070287539, | |
| "loss": 6.1654, | |
| "step": 260500 | |
| }, | |
| { | |
| "epoch": 33.35, | |
| "learning_rate": 0.000665814696485623, | |
| "loss": 6.1634, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 33.42, | |
| "learning_rate": 0.000663258785942492, | |
| "loss": 6.1647, | |
| "step": 261500 | |
| }, | |
| { | |
| "epoch": 33.48, | |
| "learning_rate": 0.0006607028753993611, | |
| "loss": 6.1584, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 33.55, | |
| "learning_rate": 0.00065814696485623, | |
| "loss": 6.1657, | |
| "step": 262500 | |
| }, | |
| { | |
| "epoch": 33.61, | |
| "learning_rate": 0.000655591054313099, | |
| "loss": 6.1676, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 33.67, | |
| "learning_rate": 0.0006530351437699681, | |
| "loss": 6.1595, | |
| "step": 263500 | |
| }, | |
| { | |
| "epoch": 33.74, | |
| "learning_rate": 0.0006504792332268371, | |
| "loss": 6.1643, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 33.8, | |
| "learning_rate": 0.0006479233226837062, | |
| "loss": 6.1737, | |
| "step": 264500 | |
| }, | |
| { | |
| "epoch": 33.87, | |
| "learning_rate": 0.000645367412140575, | |
| "loss": 6.1674, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 33.93, | |
| "learning_rate": 0.0006428115015974441, | |
| "loss": 6.1719, | |
| "step": 265500 | |
| }, | |
| { | |
| "epoch": 33.99, | |
| "learning_rate": 0.0006402555910543131, | |
| "loss": 6.1695, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 6.110330104827881, | |
| "eval_runtime": 6.7957, | |
| "eval_samples_per_second": 36.935, | |
| "eval_steps_per_second": 1.177, | |
| "step": 266050 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 391250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 4.575802027758605e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |