| { | |
| "best_global_step": 270, | |
| "best_metric": 0.049386873841285706, | |
| "best_model_checkpoint": "saves_multiple/lora/llama-3-8b-instruct/train_copa_123_1760637647/checkpoint-270", | |
| "epoch": 20.0, | |
| "eval_steps": 90, | |
| "global_step": 1800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 6.789999008178711, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.5541, | |
| "num_input_tokens_seen": 1536, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 7.779562473297119, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.6289, | |
| "num_input_tokens_seen": 3168, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 8.509727478027344, | |
| "learning_rate": 3.888888888888889e-06, | |
| "loss": 0.6272, | |
| "num_input_tokens_seen": 4736, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 7.644496917724609, | |
| "learning_rate": 5.277777777777778e-06, | |
| "loss": 0.5206, | |
| "num_input_tokens_seen": 6304, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 9.357715606689453, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.4139, | |
| "num_input_tokens_seen": 7840, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 3.1048409938812256, | |
| "learning_rate": 8.055555555555557e-06, | |
| "loss": 0.2302, | |
| "num_input_tokens_seen": 9408, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 1.0679281949996948, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 0.1964, | |
| "num_input_tokens_seen": 10912, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.09823791682720184, | |
| "learning_rate": 1.0833333333333334e-05, | |
| "loss": 0.0729, | |
| "num_input_tokens_seen": 12448, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 3.5450246334075928, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.0817, | |
| "num_input_tokens_seen": 14016, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 1.9195407629013062, | |
| "learning_rate": 1.3611111111111111e-05, | |
| "loss": 0.1063, | |
| "num_input_tokens_seen": 15584, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6111111111111112, | |
| "grad_norm": 0.0481027290225029, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.1592, | |
| "num_input_tokens_seen": 17184, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 8.088793754577637, | |
| "learning_rate": 1.638888888888889e-05, | |
| "loss": 0.0727, | |
| "num_input_tokens_seen": 18752, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7222222222222222, | |
| "grad_norm": 8.712606430053711, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.1737, | |
| "num_input_tokens_seen": 20352, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.16313442587852478, | |
| "learning_rate": 1.9166666666666667e-05, | |
| "loss": 0.0748, | |
| "num_input_tokens_seen": 21952, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 3.10784912109375, | |
| "learning_rate": 2.0555555555555555e-05, | |
| "loss": 0.0681, | |
| "num_input_tokens_seen": 23456, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.9675333499908447, | |
| "learning_rate": 2.1944444444444445e-05, | |
| "loss": 0.2123, | |
| "num_input_tokens_seen": 25056, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9444444444444444, | |
| "grad_norm": 0.1685405969619751, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.0523, | |
| "num_input_tokens_seen": 26560, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.16481925547122955, | |
| "learning_rate": 2.4722222222222223e-05, | |
| "loss": 0.2088, | |
| "num_input_tokens_seen": 28096, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.10734311491250992, | |
| "eval_runtime": 0.5645, | |
| "eval_samples_per_second": 70.865, | |
| "eval_steps_per_second": 17.716, | |
| "num_input_tokens_seen": 28096, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0555555555555556, | |
| "grad_norm": 3.626086711883545, | |
| "learning_rate": 2.6111111111111114e-05, | |
| "loss": 0.1457, | |
| "num_input_tokens_seen": 29696, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.6382214426994324, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 0.067, | |
| "num_input_tokens_seen": 31232, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1666666666666667, | |
| "grad_norm": 2.1307806968688965, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.0487, | |
| "num_input_tokens_seen": 32768, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 0.009251438081264496, | |
| "learning_rate": 3.0277777777777776e-05, | |
| "loss": 0.018, | |
| "num_input_tokens_seen": 34304, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2777777777777777, | |
| "grad_norm": 0.1958739161491394, | |
| "learning_rate": 3.1666666666666666e-05, | |
| "loss": 0.0233, | |
| "num_input_tokens_seen": 35872, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.5844274163246155, | |
| "learning_rate": 3.3055555555555553e-05, | |
| "loss": 0.0637, | |
| "num_input_tokens_seen": 37408, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3888888888888888, | |
| "grad_norm": 4.012423515319824, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.0801, | |
| "num_input_tokens_seen": 38976, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4444444444444444, | |
| "grad_norm": 0.25129589438438416, | |
| "learning_rate": 3.5833333333333335e-05, | |
| "loss": 0.0595, | |
| "num_input_tokens_seen": 40576, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.25138014554977417, | |
| "learning_rate": 3.722222222222222e-05, | |
| "loss": 0.0981, | |
| "num_input_tokens_seen": 42144, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": 0.23504316806793213, | |
| "learning_rate": 3.8611111111111116e-05, | |
| "loss": 0.0162, | |
| "num_input_tokens_seen": 43680, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.6111111111111112, | |
| "grad_norm": 0.11203597486019135, | |
| "learning_rate": 4e-05, | |
| "loss": 0.1252, | |
| "num_input_tokens_seen": 45248, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 0.008327925577759743, | |
| "learning_rate": 4.138888888888889e-05, | |
| "loss": 0.0015, | |
| "num_input_tokens_seen": 46816, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.7222222222222223, | |
| "grad_norm": 8.659642219543457, | |
| "learning_rate": 4.277777777777778e-05, | |
| "loss": 0.0737, | |
| "num_input_tokens_seen": 48384, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.004384965635836124, | |
| "learning_rate": 4.4166666666666665e-05, | |
| "loss": 0.0032, | |
| "num_input_tokens_seen": 49952, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.8333333333333335, | |
| "grad_norm": 0.0038665200117975473, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.0359, | |
| "num_input_tokens_seen": 51520, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 0.055430274456739426, | |
| "learning_rate": 4.6944444444444446e-05, | |
| "loss": 0.0417, | |
| "num_input_tokens_seen": 53024, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.9444444444444444, | |
| "grad_norm": 10.347187042236328, | |
| "learning_rate": 4.8333333333333334e-05, | |
| "loss": 0.0596, | |
| "num_input_tokens_seen": 54592, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.16169339418411255, | |
| "learning_rate": 4.972222222222223e-05, | |
| "loss": 0.1251, | |
| "num_input_tokens_seen": 56128, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.054428666830062866, | |
| "eval_runtime": 0.5758, | |
| "eval_samples_per_second": 69.463, | |
| "eval_steps_per_second": 17.366, | |
| "num_input_tokens_seen": 56128, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.0555555555555554, | |
| "grad_norm": 0.003600924974307418, | |
| "learning_rate": 4.9999247861994194e-05, | |
| "loss": 0.0027, | |
| "num_input_tokens_seen": 57696, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.111111111111111, | |
| "grad_norm": 0.22451426088809967, | |
| "learning_rate": 4.9996192378909786e-05, | |
| "loss": 0.0797, | |
| "num_input_tokens_seen": 59264, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.1666666666666665, | |
| "grad_norm": 0.002265199786052108, | |
| "learning_rate": 4.999078682916774e-05, | |
| "loss": 0.0007, | |
| "num_input_tokens_seen": 60864, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.09307070076465607, | |
| "learning_rate": 4.998303172098155e-05, | |
| "loss": 0.0012, | |
| "num_input_tokens_seen": 62464, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.2777777777777777, | |
| "grad_norm": 8.190011978149414, | |
| "learning_rate": 4.997292778346312e-05, | |
| "loss": 0.0603, | |
| "num_input_tokens_seen": 64032, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.3333333333333335, | |
| "grad_norm": 0.0016131828306242824, | |
| "learning_rate": 4.996047596655418e-05, | |
| "loss": 0.0008, | |
| "num_input_tokens_seen": 65568, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.388888888888889, | |
| "grad_norm": 1.7446612119674683, | |
| "learning_rate": 4.994567744093703e-05, | |
| "loss": 0.0018, | |
| "num_input_tokens_seen": 67104, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.4444444444444446, | |
| "grad_norm": 0.005552974529564381, | |
| "learning_rate": 4.992853359792444e-05, | |
| "loss": 0.0008, | |
| "num_input_tokens_seen": 68704, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.030915070325136185, | |
| "learning_rate": 4.9909046049328846e-05, | |
| "loss": 0.0027, | |
| "num_input_tokens_seen": 70272, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.5555555555555554, | |
| "grad_norm": 0.04200270026922226, | |
| "learning_rate": 4.988721662731083e-05, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 71808, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.611111111111111, | |
| "grad_norm": 0.07620513439178467, | |
| "learning_rate": 4.9863047384206835e-05, | |
| "loss": 0.0178, | |
| "num_input_tokens_seen": 73408, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 12.79358959197998, | |
| "learning_rate": 4.983654059233626e-05, | |
| "loss": 0.0572, | |
| "num_input_tokens_seen": 74912, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.7222222222222223, | |
| "grad_norm": 14.908279418945312, | |
| "learning_rate": 4.9807698743787744e-05, | |
| "loss": 0.0489, | |
| "num_input_tokens_seen": 76544, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.7777777777777777, | |
| "grad_norm": 1.689833164215088, | |
| "learning_rate": 4.9776524550184965e-05, | |
| "loss": 0.0016, | |
| "num_input_tokens_seen": 78112, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.8333333333333335, | |
| "grad_norm": 0.0040872106328606606, | |
| "learning_rate": 4.974302094243164e-05, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 79712, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.888888888888889, | |
| "grad_norm": 0.3981519341468811, | |
| "learning_rate": 4.970719107043595e-05, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 81280, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.9444444444444446, | |
| "grad_norm": 0.006680743768811226, | |
| "learning_rate": 4.966903830281449e-05, | |
| "loss": 0.0026, | |
| "num_input_tokens_seen": 82848, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.009416918270289898, | |
| "learning_rate": 4.962856622657541e-05, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 84352, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.049386873841285706, | |
| "eval_runtime": 0.5802, | |
| "eval_samples_per_second": 68.945, | |
| "eval_steps_per_second": 17.236, | |
| "num_input_tokens_seen": 84352, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.0555555555555554, | |
| "grad_norm": 0.0032377338502556086, | |
| "learning_rate": 4.9585778646781364e-05, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 85920, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.111111111111111, | |
| "grad_norm": 0.05717380344867706, | |
| "learning_rate": 4.9540679586191605e-05, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 87520, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.1666666666666665, | |
| "grad_norm": 0.002666266169399023, | |
| "learning_rate": 4.9493273284883854e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 89088, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.2222222222222223, | |
| "grad_norm": 0.0013854223070666194, | |
| "learning_rate": 4.9443564199855666e-05, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 90688, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.2777777777777777, | |
| "grad_norm": 0.005427713971585035, | |
| "learning_rate": 4.939155700460536e-05, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 92160, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.00847073458135128, | |
| "learning_rate": 4.933725658869267e-05, | |
| "loss": 0.0014, | |
| "num_input_tokens_seen": 93760, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.388888888888889, | |
| "grad_norm": 0.0007094600587151945, | |
| "learning_rate": 4.9280668057279014e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 95360, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.4444444444444446, | |
| "grad_norm": 0.0010639664251357317, | |
| "learning_rate": 4.9221796730647516e-05, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 96928, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 0.000602278218138963, | |
| "learning_rate": 4.916064814370287e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 98464, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.02681981958448887, | |
| "learning_rate": 4.9097228045450864e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 100064, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.611111111111111, | |
| "grad_norm": 0.0007119868532754481, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 101600, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 3.6666666666666665, | |
| "grad_norm": 0.0006003398448228836, | |
| "learning_rate": 4.896359737829071e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 103200, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.7222222222222223, | |
| "grad_norm": 0.0007283531012944877, | |
| "learning_rate": 4.889339937293508e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 104768, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 3.7777777777777777, | |
| "grad_norm": 0.0006814614171162248, | |
| "learning_rate": 4.8820954982195905e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 106304, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.8333333333333335, | |
| "grad_norm": 0.0007484639063477516, | |
| "learning_rate": 4.874627101707644e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 107904, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 3.888888888888889, | |
| "grad_norm": 0.00047610857291147113, | |
| "learning_rate": 4.8669354499137955e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 109408, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.9444444444444446, | |
| "grad_norm": 0.0015788902528584003, | |
| "learning_rate": 4.859021265983959e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 111008, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.0005128057091496885, | |
| "learning_rate": 4.850885293985853e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 112576, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.07271323353052139, | |
| "eval_runtime": 0.5614, | |
| "eval_samples_per_second": 71.256, | |
| "eval_steps_per_second": 17.814, | |
| "num_input_tokens_seen": 112576, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.055555555555555, | |
| "grad_norm": 0.004134467337280512, | |
| "learning_rate": 4.8425282988390376e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 114144, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 4.111111111111111, | |
| "grad_norm": 0.0006652507581748068, | |
| "learning_rate": 4.8339510662430046e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 115712, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.166666666666667, | |
| "grad_norm": 0.0005224759224802256, | |
| "learning_rate": 4.825154402603308e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 117216, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.222222222222222, | |
| "grad_norm": 0.0005001591052860022, | |
| "learning_rate": 4.816139134955746e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 118816, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.277777777777778, | |
| "grad_norm": 0.003746587550267577, | |
| "learning_rate": 4.806906110888606e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 120352, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 4.333333333333333, | |
| "grad_norm": 0.0004284741298761219, | |
| "learning_rate": 4.797456198462979e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 121920, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.388888888888889, | |
| "grad_norm": 0.00041507682180963457, | |
| "learning_rate": 4.7877902861311446e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 123456, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 0.0008518180111423135, | |
| "learning_rate": 4.777909282653042e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 125056, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 0.0006696592317894101, | |
| "learning_rate": 4.7678141170108345e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 126624, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 4.555555555555555, | |
| "grad_norm": 0.00264886487275362, | |
| "learning_rate": 4.757505738321563e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 128224, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.611111111111111, | |
| "grad_norm": 0.0005462790140882134, | |
| "learning_rate": 4.7469851157479177e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 129728, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 0.0016746792243793607, | |
| "learning_rate": 4.736253238407119e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 131328, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.722222222222222, | |
| "grad_norm": 0.04117045924067497, | |
| "learning_rate": 4.725311115277924e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 132896, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 4.777777777777778, | |
| "grad_norm": 0.0004282867012079805, | |
| "learning_rate": 4.714159775105765e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 134496, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.833333333333333, | |
| "grad_norm": 0.00029444749816320837, | |
| "learning_rate": 4.70280026630603e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 136064, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 4.888888888888889, | |
| "grad_norm": 0.0007262208382599056, | |
| "learning_rate": 4.6912336568654925e-05, | |
| "loss": 0.0087, | |
| "num_input_tokens_seen": 137664, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.944444444444445, | |
| "grad_norm": 0.0003021281154360622, | |
| "learning_rate": 4.679461034241906e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 139232, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.0004039698978886008, | |
| "learning_rate": 4.667483505261762e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 140832, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.05871295928955078, | |
| "eval_runtime": 0.562, | |
| "eval_samples_per_second": 71.174, | |
| "eval_steps_per_second": 17.793, | |
| "num_input_tokens_seen": 140832, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.055555555555555, | |
| "grad_norm": 0.00045824242988601327, | |
| "learning_rate": 4.655302196016228e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 142368, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 5.111111111111111, | |
| "grad_norm": 0.0005962659488432109, | |
| "learning_rate": 4.642918251755281e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 144000, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.166666666666667, | |
| "grad_norm": 0.0003970380639657378, | |
| "learning_rate": 4.6303328367800284e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 145632, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 5.222222222222222, | |
| "grad_norm": 0.006841136142611504, | |
| "learning_rate": 4.6175471343332485e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 147168, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.277777777777778, | |
| "grad_norm": 0.0031192798633128405, | |
| "learning_rate": 4.604562346488144e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 148736, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.0004989643348380923, | |
| "learning_rate": 4.591379694035325e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 150304, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.388888888888889, | |
| "grad_norm": 0.0024625184014439583, | |
| "learning_rate": 4.5780004163680365e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 151872, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 5.444444444444445, | |
| "grad_norm": 0.00024677850888110697, | |
| "learning_rate": 4.5644257713656356e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 153472, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "grad_norm": 0.0003723811241798103, | |
| "learning_rate": 4.550657035275323e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 154976, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 0.00028403528267517686, | |
| "learning_rate": 4.536695502592162e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 156544, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.611111111111111, | |
| "grad_norm": 0.00019704698934219778, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 158112, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 5.666666666666667, | |
| "grad_norm": 0.000786281656473875, | |
| "learning_rate": 4.5081993159349056e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 159680, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.722222222222222, | |
| "grad_norm": 0.00035128253512084484, | |
| "learning_rate": 4.493667341086379e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 161312, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 5.777777777777778, | |
| "grad_norm": 0.00020992198551539332, | |
| "learning_rate": 4.478947927644258e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 162880, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.833333333333333, | |
| "grad_norm": 0.00020310768741182983, | |
| "learning_rate": 4.464042459483425e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 164448, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 5.888888888888889, | |
| "grad_norm": 0.0003243352985009551, | |
| "learning_rate": 4.448952337971064e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 166016, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.944444444444445, | |
| "grad_norm": 0.0016284942394122481, | |
| "learning_rate": 4.43367898183491e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 167552, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.0002892577613238245, | |
| "learning_rate": 4.418223827029867e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 169056, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.059852443635463715, | |
| "eval_runtime": 0.5663, | |
| "eval_samples_per_second": 70.637, | |
| "eval_steps_per_second": 17.659, | |
| "num_input_tokens_seen": 169056, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.055555555555555, | |
| "grad_norm": 0.00021687305707018822, | |
| "learning_rate": 4.402588326603002e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 170592, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 6.111111111111111, | |
| "grad_norm": 0.0002662682381924242, | |
| "learning_rate": 4.386773950556931e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 172192, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.166666666666667, | |
| "grad_norm": 0.00038944167317822576, | |
| "learning_rate": 4.3707821857116176e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 173792, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 6.222222222222222, | |
| "grad_norm": 0.0002498209069017321, | |
| "learning_rate": 4.354614535564588e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 175360, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.277777777777778, | |
| "grad_norm": 0.00025446133804507554, | |
| "learning_rate": 4.3382725201495723e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 176992, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 6.333333333333333, | |
| "grad_norm": 0.00037459548912011087, | |
| "learning_rate": 4.321757675893596e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 178592, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.388888888888889, | |
| "grad_norm": 0.00022485433146357536, | |
| "learning_rate": 4.305071555472534e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 180128, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 6.444444444444445, | |
| "grad_norm": 0.0002987268380820751, | |
| "learning_rate": 4.288215727665129e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 181632, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "grad_norm": 0.006031045224517584, | |
| "learning_rate": 4.2711917772055e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 183200, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 6.555555555555555, | |
| "grad_norm": 0.00022710718621965498, | |
| "learning_rate": 4.254001304634151e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 184800, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.611111111111111, | |
| "grad_norm": 0.00025921486667357385, | |
| "learning_rate": 4.2366459261474933e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 186336, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.0001979801309062168, | |
| "learning_rate": 4.2191272734458955e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 187904, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.722222222222222, | |
| "grad_norm": 0.00027331634191796184, | |
| "learning_rate": 4.201446993580276e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 189472, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 6.777777777777778, | |
| "grad_norm": 0.002444098237901926, | |
| "learning_rate": 4.183606748797251e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 191072, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.833333333333333, | |
| "grad_norm": 0.00016314823005814105, | |
| "learning_rate": 4.1656082163828566e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 192608, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 6.888888888888889, | |
| "grad_norm": 0.0011963454307988286, | |
| "learning_rate": 4.147453088504854e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 194208, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.944444444444445, | |
| "grad_norm": 0.00018900283612310886, | |
| "learning_rate": 4.129143072053638e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 195776, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.00016874237917363644, | |
| "learning_rate": 4.110679888481763e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 197344, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.05574069172143936, | |
| "eval_runtime": 0.5676, | |
| "eval_samples_per_second": 70.474, | |
| "eval_steps_per_second": 17.618, | |
| "num_input_tokens_seen": 197344, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.055555555555555, | |
| "grad_norm": 0.00022347709455061704, | |
| "learning_rate": 4.09206527364209e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 198944, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 7.111111111111111, | |
| "grad_norm": 0.0005306162056513131, | |
| "learning_rate": 4.073300977624594e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 200512, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 7.166666666666667, | |
| "grad_norm": 0.0002005905262194574, | |
| "learning_rate": 4.054388764591822e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 202016, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 7.222222222222222, | |
| "grad_norm": 0.0004567239375319332, | |
| "learning_rate": 4.035330412613035e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 203648, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.277777777777778, | |
| "grad_norm": 0.0001239487755810842, | |
| "learning_rate": 4.0161277134970345e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 205184, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 7.333333333333333, | |
| "grad_norm": 0.00017524670693092048, | |
| "learning_rate": 3.996782472623705e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 206720, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 7.388888888888889, | |
| "grad_norm": 0.0013641855912283063, | |
| "learning_rate": 3.977296508774278e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 208320, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 7.444444444444445, | |
| "grad_norm": 0.00021721921802964061, | |
| "learning_rate": 3.957671653960337e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 209856, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 0.0001712629309622571, | |
| "learning_rate": 3.9379097532515725e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 211392, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 7.555555555555555, | |
| "grad_norm": 0.00018687936244532466, | |
| "learning_rate": 3.918012664602317e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 212960, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 7.611111111111111, | |
| "grad_norm": 0.00018690628348849714, | |
| "learning_rate": 3.897982258676867e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 214528, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 7.666666666666667, | |
| "grad_norm": 0.0001528603897895664, | |
| "learning_rate": 3.8778204186736076e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 216000, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.722222222222222, | |
| "grad_norm": 0.00011578315024962649, | |
| "learning_rate": 3.8575290401479586e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 217632, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 7.777777777777778, | |
| "grad_norm": 0.00014238100266084075, | |
| "learning_rate": 3.837110030834161e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 219232, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.833333333333333, | |
| "grad_norm": 0.00017715182912070304, | |
| "learning_rate": 3.8165653104659185e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 220800, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 7.888888888888889, | |
| "grad_norm": 0.00023851884179748595, | |
| "learning_rate": 3.79589681059591e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 222368, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 7.944444444444445, | |
| "grad_norm": 0.0002256816951557994, | |
| "learning_rate": 3.775106474414188e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 223968, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.00014826786355115473, | |
| "learning_rate": 3.75419625656549e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 225536, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.05764114111661911, | |
| "eval_runtime": 0.5712, | |
| "eval_samples_per_second": 70.027, | |
| "eval_steps_per_second": 17.507, | |
| "num_input_tokens_seen": 225536, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 8.055555555555555, | |
| "grad_norm": 0.0011612845119088888, | |
| "learning_rate": 3.7331681229654635e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 227168, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 8.11111111111111, | |
| "grad_norm": 0.00012414316006470472, | |
| "learning_rate": 3.712024050615843e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 228704, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 8.166666666666666, | |
| "grad_norm": 0.0001734651013975963, | |
| "learning_rate": 3.690766027418573e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 230336, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 8.222222222222221, | |
| "grad_norm": 0.00023135766969062388, | |
| "learning_rate": 3.6693960519889106e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 231936, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 8.277777777777779, | |
| "grad_norm": 0.0001898543123388663, | |
| "learning_rate": 3.6479161334675296e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 233472, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 8.333333333333334, | |
| "grad_norm": 0.0001656882668612525, | |
| "learning_rate": 3.626328291331618e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 235040, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.38888888888889, | |
| "grad_norm": 0.00011843425454571843, | |
| "learning_rate": 3.60463455520502e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 236608, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 8.444444444444445, | |
| "grad_norm": 0.00012032144149998203, | |
| "learning_rate": 3.582836964667408e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 238144, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "grad_norm": 0.00025458575692027807, | |
| "learning_rate": 3.560937569062538e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 239680, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 8.555555555555555, | |
| "grad_norm": 0.00014700254541821778, | |
| "learning_rate": 3.538938427305573e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 241280, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 8.61111111111111, | |
| "grad_norm": 0.0014986986061558127, | |
| "learning_rate": 3.516841607689501e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 242816, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 8.666666666666666, | |
| "grad_norm": 0.00013900574413128197, | |
| "learning_rate": 3.494649187690695e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 244352, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 8.722222222222221, | |
| "grad_norm": 0.00010932795703411102, | |
| "learning_rate": 3.4723632537735846e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 245856, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 8.777777777777779, | |
| "grad_norm": 0.0010112106101587415, | |
| "learning_rate": 3.449985901194498e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 247456, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.833333333333334, | |
| "grad_norm": 0.00037229876033961773, | |
| "learning_rate": 3.427519233804667e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 248992, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 0.00012429196794983, | |
| "learning_rate": 3.404965363852437e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 250528, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.944444444444445, | |
| "grad_norm": 0.00014521834964398295, | |
| "learning_rate": 3.382326411784672e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 252128, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.00011761845962610096, | |
| "learning_rate": 3.359604506047403e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 253696, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.058425940573215485, | |
| "eval_runtime": 0.5832, | |
| "eval_samples_per_second": 68.589, | |
| "eval_steps_per_second": 17.147, | |
| "num_input_tokens_seen": 253696, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 9.055555555555555, | |
| "grad_norm": 0.00013218300591688603, | |
| "learning_rate": 3.336801782885712e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 255296, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 9.11111111111111, | |
| "grad_norm": 0.00012462653103284538, | |
| "learning_rate": 3.313920386142892e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 256896, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 9.166666666666666, | |
| "grad_norm": 0.00011541874846443534, | |
| "learning_rate": 3.290962467058891e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 258432, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 9.222222222222221, | |
| "grad_norm": 0.000133588895550929, | |
| "learning_rate": 3.267930184068057e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 260000, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 9.277777777777779, | |
| "grad_norm": 0.0007571254973299801, | |
| "learning_rate": 3.244825702596205e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 261568, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 9.333333333333334, | |
| "grad_norm": 0.00012214199523441494, | |
| "learning_rate": 3.2216511948570374e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 263200, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.38888888888889, | |
| "grad_norm": 0.00034574948949739337, | |
| "learning_rate": 3.198408839647911e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 264736, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 9.444444444444445, | |
| "grad_norm": 0.00012473238166421652, | |
| "learning_rate": 3.1751008221450025e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 266304, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "grad_norm": 0.00017391557048540562, | |
| "learning_rate": 3.151729333697854e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 267840, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 9.555555555555555, | |
| "grad_norm": 9.685044642537832e-05, | |
| "learning_rate": 3.1282965716233594e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 269376, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 9.61111111111111, | |
| "grad_norm": 0.00015366339357569814, | |
| "learning_rate": 3.104804738999169e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 270944, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 9.666666666666666, | |
| "grad_norm": 0.00019679054094012827, | |
| "learning_rate": 3.0812560444565745e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 272448, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 9.722222222222221, | |
| "grad_norm": 8.669628005009145e-05, | |
| "learning_rate": 3.057652701972848e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 273984, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 9.777777777777779, | |
| "grad_norm": 0.00011901947436854243, | |
| "learning_rate": 3.0339969306631005e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 275520, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 9.833333333333334, | |
| "grad_norm": 0.00011127805191790685, | |
| "learning_rate": 3.0102909545716396e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 277152, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 9.88888888888889, | |
| "grad_norm": 0.00024032880901359022, | |
| "learning_rate": 2.9865370024628775e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 278688, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 9.944444444444445, | |
| "grad_norm": 0.00016350630903616548, | |
| "learning_rate": 2.9627373076117863e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 280256, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.0001469360286137089, | |
| "learning_rate": 2.9388941075939334e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 281856, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.057220689952373505, | |
| "eval_runtime": 0.5629, | |
| "eval_samples_per_second": 71.054, | |
| "eval_steps_per_second": 17.764, | |
| "num_input_tokens_seen": 281856, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.055555555555555, | |
| "grad_norm": 0.00017346425738651305, | |
| "learning_rate": 2.9150096440751107e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 283424, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 10.11111111111111, | |
| "grad_norm": 0.0001567457220517099, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 284960, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 10.166666666666666, | |
| "grad_norm": 9.789296018425375e-05, | |
| "learning_rate": 2.8671259123839472e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 286496, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 10.222222222222221, | |
| "grad_norm": 8.570841600885615e-05, | |
| "learning_rate": 2.843131146095719e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 288064, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 10.277777777777779, | |
| "grad_norm": 8.610450458945706e-05, | |
| "learning_rate": 2.8191041196514873e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 289664, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 10.333333333333334, | |
| "grad_norm": 0.0001053861269610934, | |
| "learning_rate": 2.795047091999849e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 291264, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 10.38888888888889, | |
| "grad_norm": 0.00012966361828148365, | |
| "learning_rate": 2.770962324910027e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 292896, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 10.444444444444445, | |
| "grad_norm": 9.642139775678515e-05, | |
| "learning_rate": 2.7468520827592197e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 294464, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "grad_norm": 0.0001299332652706653, | |
| "learning_rate": 2.7227186323197162e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 296064, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 10.555555555555555, | |
| "grad_norm": 0.0005338926566764712, | |
| "learning_rate": 2.6985642425457757e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 297600, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 10.61111111111111, | |
| "grad_norm": 0.00010388505324954167, | |
| "learning_rate": 2.674391184360313e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 299200, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 10.666666666666666, | |
| "grad_norm": 0.00028984990785829723, | |
| "learning_rate": 2.650201730441392e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 300704, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 10.722222222222221, | |
| "grad_norm": 8.54739555506967e-05, | |
| "learning_rate": 2.6259981550085504e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 302240, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 10.777777777777779, | |
| "grad_norm": 8.299310866277665e-05, | |
| "learning_rate": 2.60178273360899e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 303776, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 10.833333333333334, | |
| "grad_norm": 0.000137448834720999, | |
| "learning_rate": 2.5775577429036345e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 305344, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 10.88888888888889, | |
| "grad_norm": 0.00014663035108242184, | |
| "learning_rate": 2.553325460453086e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 306912, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 10.944444444444445, | |
| "grad_norm": 9.246973058907315e-05, | |
| "learning_rate": 2.5290881645034932e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 308512, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 0.0015313805779442191, | |
| "learning_rate": 2.504848133772358e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 310080, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.05834006518125534, | |
| "eval_runtime": 0.5668, | |
| "eval_samples_per_second": 70.568, | |
| "eval_steps_per_second": 17.642, | |
| "num_input_tokens_seen": 310080, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 11.055555555555555, | |
| "grad_norm": 0.00010421316255815327, | |
| "learning_rate": 2.4806076472342997e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 311616, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "grad_norm": 0.00010182010737480596, | |
| "learning_rate": 2.4563689839067913e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 313184, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.166666666666666, | |
| "grad_norm": 9.944899647962302e-05, | |
| "learning_rate": 2.432134422635893e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 314816, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 11.222222222222221, | |
| "grad_norm": 0.00019097872427664697, | |
| "learning_rate": 2.4079062418820002e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 316384, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 11.277777777777779, | |
| "grad_norm": 0.0001159649618784897, | |
| "learning_rate": 2.3836867195056335e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 317952, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 11.333333333333334, | |
| "grad_norm": 0.00015391121269203722, | |
| "learning_rate": 2.3594781325532784e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 319488, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 11.38888888888889, | |
| "grad_norm": 8.917111699702218e-05, | |
| "learning_rate": 2.3352827570433036e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 321024, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 11.444444444444445, | |
| "grad_norm": 6.387962639564648e-05, | |
| "learning_rate": 2.3111028677519804e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 322560, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "grad_norm": 0.0002676509029697627, | |
| "learning_rate": 2.2869407379996088e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 324128, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 11.555555555555555, | |
| "grad_norm": 9.826622408581898e-05, | |
| "learning_rate": 2.2627986394367938e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 325696, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 11.61111111111111, | |
| "grad_norm": 0.0010710059432312846, | |
| "learning_rate": 2.238678841830867e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 327232, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 11.666666666666666, | |
| "grad_norm": 0.00029537943191826344, | |
| "learning_rate": 2.2145836128524902e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 328768, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 11.722222222222221, | |
| "grad_norm": 9.056083945324644e-05, | |
| "learning_rate": 2.1905152178624595e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 330336, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 11.777777777777779, | |
| "grad_norm": 0.00011236572754569352, | |
| "learning_rate": 2.1664759196987182e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 331904, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 11.833333333333334, | |
| "grad_norm": 0.0004642836865969002, | |
| "learning_rate": 2.1424679784636144e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 333472, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 11.88888888888889, | |
| "grad_norm": 0.00019974906172137707, | |
| "learning_rate": 2.118493651311413e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 335104, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 11.944444444444445, | |
| "grad_norm": 8.024062117328867e-05, | |
| "learning_rate": 2.0945551922360818e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 336608, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.0011347675463184714, | |
| "learning_rate": 2.070654851859383e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 338144, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.06123088672757149, | |
| "eval_runtime": 0.567, | |
| "eval_samples_per_second": 70.546, | |
| "eval_steps_per_second": 17.637, | |
| "num_input_tokens_seen": 338144, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 12.055555555555555, | |
| "grad_norm": 0.00010703336010919884, | |
| "learning_rate": 2.0467948772192713e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 339712, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 12.11111111111111, | |
| "grad_norm": 9.349647734779865e-05, | |
| "learning_rate": 2.022977511558638e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 341184, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 12.166666666666666, | |
| "grad_norm": 0.0002747257531154901, | |
| "learning_rate": 1.9992049941144066e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 342752, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 12.222222222222221, | |
| "grad_norm": 0.0002023014531005174, | |
| "learning_rate": 1.9754795599070068e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 344352, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.277777777777779, | |
| "grad_norm": 7.600725803058594e-05, | |
| "learning_rate": 1.9518034395302414e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 345952, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 12.333333333333334, | |
| "grad_norm": 7.663488213438541e-05, | |
| "learning_rate": 1.9281788589415804e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 347520, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 12.38888888888889, | |
| "grad_norm": 0.0003221962251700461, | |
| "learning_rate": 1.9046080392528735e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 349056, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 12.444444444444445, | |
| "grad_norm": 9.53532726271078e-05, | |
| "learning_rate": 1.8810931965215356e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 350656, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "grad_norm": 0.001182821812108159, | |
| "learning_rate": 1.857636541542195e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 352192, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 12.555555555555555, | |
| "grad_norm": 8.245109347626567e-05, | |
| "learning_rate": 1.8342402796388445e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 353792, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 12.61111111111111, | |
| "grad_norm": 8.608192001702264e-05, | |
| "learning_rate": 1.8109066104575023e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 355360, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 12.666666666666666, | |
| "grad_norm": 0.00015417281247209758, | |
| "learning_rate": 1.7876377277594053e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 356896, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 12.722222222222221, | |
| "grad_norm": 8.806315599940717e-05, | |
| "learning_rate": 1.764435819214762e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 358432, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 12.777777777777779, | |
| "grad_norm": 8.2114536780864e-05, | |
| "learning_rate": 1.7413030661970742e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 360032, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 12.833333333333334, | |
| "grad_norm": 0.00013416571891866624, | |
| "learning_rate": 1.7182416435780454e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 361600, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 12.88888888888889, | |
| "grad_norm": 8.659192826598883e-05, | |
| "learning_rate": 1.695253719523115e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 363200, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 12.944444444444445, | |
| "grad_norm": 7.594122143927962e-05, | |
| "learning_rate": 1.672341455287605e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 364768, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 0.00010253726941300556, | |
| "learning_rate": 1.649507005013532e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 366336, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.06028003618121147, | |
| "eval_runtime": 0.5703, | |
| "eval_samples_per_second": 70.134, | |
| "eval_steps_per_second": 17.533, | |
| "num_input_tokens_seen": 366336, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 13.055555555555555, | |
| "grad_norm": 6.942445907043293e-05, | |
| "learning_rate": 1.6267525155270773e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 367936, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 13.11111111111111, | |
| "grad_norm": 7.962655945448205e-05, | |
| "learning_rate": 1.6040801261367493e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 369504, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 13.166666666666666, | |
| "grad_norm": 0.0008303570793941617, | |
| "learning_rate": 1.5814919684322545e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 371072, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 13.222222222222221, | |
| "grad_norm": 0.00016059121116995811, | |
| "learning_rate": 1.5589901660840896e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 372544, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 13.277777777777779, | |
| "grad_norm": 0.0002665589563548565, | |
| "learning_rate": 1.5365768346438797e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 374144, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 8.724022336537018e-05, | |
| "learning_rate": 1.5142540813454836e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 375712, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 13.38888888888889, | |
| "grad_norm": 0.00020796518947463483, | |
| "learning_rate": 1.4920240049068748e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 377280, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 13.444444444444445, | |
| "grad_norm": 0.00040108204120770097, | |
| "learning_rate": 1.4698886953328292e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 378848, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "grad_norm": 7.436677697114646e-05, | |
| "learning_rate": 1.4478502337184274e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 380416, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 13.555555555555555, | |
| "grad_norm": 8.718096796656027e-05, | |
| "learning_rate": 1.4259106920533955e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 381984, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 13.61111111111111, | |
| "grad_norm": 0.0003644956450443715, | |
| "learning_rate": 1.4040721330273062e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 383552, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 13.666666666666666, | |
| "grad_norm": 0.000904978602193296, | |
| "learning_rate": 1.3823366098356487e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 385120, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 13.722222222222221, | |
| "grad_norm": 8.087969035841525e-05, | |
| "learning_rate": 1.3607061659867892e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 386720, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 13.777777777777779, | |
| "grad_norm": 8.791658183326945e-05, | |
| "learning_rate": 1.3391828351098578e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 388352, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 13.833333333333334, | |
| "grad_norm": 9.417907131137326e-05, | |
| "learning_rate": 1.3177686407635417e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 389952, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 13.88888888888889, | |
| "grad_norm": 9.294843766838312e-05, | |
| "learning_rate": 1.29646559624584e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 391488, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 13.944444444444445, | |
| "grad_norm": 7.596422801725566e-05, | |
| "learning_rate": 1.2752757044047827e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 392992, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 7.548478606622666e-05, | |
| "learning_rate": 1.2542009574501246e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 394464, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.059927672147750854, | |
| "eval_runtime": 0.567, | |
| "eval_samples_per_second": 70.552, | |
| "eval_steps_per_second": 17.638, | |
| "num_input_tokens_seen": 394464, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 14.055555555555555, | |
| "grad_norm": 9.789010800886899e-05, | |
| "learning_rate": 1.2332433367660442e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 396064, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 14.11111111111111, | |
| "grad_norm": 0.00019279788830317557, | |
| "learning_rate": 1.2124048127248644e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 397664, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 14.166666666666666, | |
| "grad_norm": 6.73854083288461e-05, | |
| "learning_rate": 1.1916873445017982e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 399200, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 14.222222222222221, | |
| "grad_norm": 5.7943623687606305e-05, | |
| "learning_rate": 1.1710928798907556e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 400768, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 14.277777777777779, | |
| "grad_norm": 6.305468559730798e-05, | |
| "learning_rate": 1.1506233551212186e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 402368, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 14.333333333333334, | |
| "grad_norm": 5.6103599490597844e-05, | |
| "learning_rate": 1.1302806946762004e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 403968, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 14.38888888888889, | |
| "grad_norm": 0.0001022622745949775, | |
| "learning_rate": 1.1100668111113166e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 405632, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 14.444444444444445, | |
| "grad_norm": 6.696353375446051e-05, | |
| "learning_rate": 1.0899836048749645e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 407200, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "grad_norm": 7.400691538350657e-05, | |
| "learning_rate": 1.0700329641296541e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 408768, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 14.555555555555555, | |
| "grad_norm": 0.0001052492661983706, | |
| "learning_rate": 1.0502167645744895e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 410304, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 14.61111111111111, | |
| "grad_norm": 7.36311703803949e-05, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 411808, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 14.666666666666666, | |
| "grad_norm": 9.574962314218283e-05, | |
| "learning_rate": 1.01099512845707e-05, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 413312, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 14.722222222222221, | |
| "grad_norm": 0.00047046531108208, | |
| "learning_rate": 9.91593379394811e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 414880, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 14.777777777777779, | |
| "grad_norm": 6.915190169820562e-05, | |
| "learning_rate": 9.723334461760006e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 416448, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 14.833333333333334, | |
| "grad_norm": 7.118436769815162e-05, | |
| "learning_rate": 9.532171395615036e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 417952, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 14.88888888888889, | |
| "grad_norm": 0.00014990368799772114, | |
| "learning_rate": 9.342462568088416e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 419488, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 14.944444444444445, | |
| "grad_norm": 9.729703015182167e-05, | |
| "learning_rate": 9.154225815032242e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 421024, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 6.560924521181732e-05, | |
| "learning_rate": 8.967478833898612e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 422592, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.06016644090414047, | |
| "eval_runtime": 0.5654, | |
| "eval_samples_per_second": 70.75, | |
| "eval_steps_per_second": 17.688, | |
| "num_input_tokens_seen": 422592, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 15.055555555555555, | |
| "grad_norm": 0.0003535063879098743, | |
| "learning_rate": 8.78223918207575e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 424128, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 15.11111111111111, | |
| "grad_norm": 8.165565668605268e-05, | |
| "learning_rate": 8.598524275237322e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 425728, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 15.166666666666666, | |
| "grad_norm": 7.119782821973786e-05, | |
| "learning_rate": 8.41635138570507e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 427232, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 15.222222222222221, | |
| "grad_norm": 7.306595944100991e-05, | |
| "learning_rate": 8.235737640824908e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 428800, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 15.277777777777779, | |
| "grad_norm": 0.0001902810181491077, | |
| "learning_rate": 8.056700021356694e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 430304, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 15.333333333333334, | |
| "grad_norm": 9.805179433897138e-05, | |
| "learning_rate": 7.879255359877705e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 431872, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 15.38888888888889, | |
| "grad_norm": 7.695959357079118e-05, | |
| "learning_rate": 7.703420339200101e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 433472, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 15.444444444444445, | |
| "grad_norm": 0.0006804478471167386, | |
| "learning_rate": 7.529211490802498e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 435040, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "grad_norm": 0.00012610004341695458, | |
| "learning_rate": 7.3566451932756744e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 436640, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 15.555555555555555, | |
| "grad_norm": 0.00024432086502201855, | |
| "learning_rate": 7.185737670782727e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 438208, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 15.61111111111111, | |
| "grad_norm": 8.168560452759266e-05, | |
| "learning_rate": 7.016504991533726e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 439776, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 15.666666666666666, | |
| "grad_norm": 0.00010157758515561, | |
| "learning_rate": 6.848963066275027e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 441376, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 15.722222222222221, | |
| "grad_norm": 7.143231778172776e-05, | |
| "learning_rate": 6.683127646793411e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 442944, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 15.777777777777779, | |
| "grad_norm": 5.990841964376159e-05, | |
| "learning_rate": 6.519014324435102e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 444448, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 15.833333333333334, | |
| "grad_norm": 7.705487951170653e-05, | |
| "learning_rate": 6.356638528639955e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 446048, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 15.88888888888889, | |
| "grad_norm": 0.00013360765296965837, | |
| "learning_rate": 6.196015525490825e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 447584, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 15.944444444444445, | |
| "grad_norm": 7.184409332694486e-05, | |
| "learning_rate": 6.037160416278278e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 449088, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 9.036972187459469e-05, | |
| "learning_rate": 5.880088136080814e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 450624, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.05732058361172676, | |
| "eval_runtime": 0.5671, | |
| "eval_samples_per_second": 70.539, | |
| "eval_steps_per_second": 17.635, | |
| "num_input_tokens_seen": 450624, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 16.055555555555557, | |
| "grad_norm": 7.997118518687785e-05, | |
| "learning_rate": 5.724813452360736e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 452224, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 16.11111111111111, | |
| "grad_norm": 6.394545926013961e-05, | |
| "learning_rate": 5.571350963575728e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 453760, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 16.166666666666668, | |
| "grad_norm": 0.0005251752445474267, | |
| "learning_rate": 5.4197150978063965e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 455296, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 16.22222222222222, | |
| "grad_norm": 7.18560695531778e-05, | |
| "learning_rate": 5.269920111399732e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 456832, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 16.27777777777778, | |
| "grad_norm": 7.281131547642872e-05, | |
| "learning_rate": 5.121980087628803e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 458368, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 16.333333333333332, | |
| "grad_norm": 0.00026419578352943063, | |
| "learning_rate": 4.975908935368701e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 459968, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 16.38888888888889, | |
| "grad_norm": 5.6553020840510726e-05, | |
| "learning_rate": 4.831720387788827e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 461536, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 16.444444444444443, | |
| "grad_norm": 7.871593697927892e-05, | |
| "learning_rate": 4.689428001061774e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 463136, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "grad_norm": 7.420869951602072e-05, | |
| "learning_rate": 4.549045153088813e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 464704, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 16.555555555555557, | |
| "grad_norm": 8.026656723814085e-05, | |
| "learning_rate": 4.410585042242124e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 466240, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 16.61111111111111, | |
| "grad_norm": 7.508454291382805e-05, | |
| "learning_rate": 4.274060686123959e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 467744, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 16.666666666666668, | |
| "grad_norm": 7.217785605462268e-05, | |
| "learning_rate": 4.1394849203427284e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 469344, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 16.72222222222222, | |
| "grad_norm": 7.678229303564876e-05, | |
| "learning_rate": 4.006870397306256e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 470944, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 16.77777777777778, | |
| "grad_norm": 7.560567610198632e-05, | |
| "learning_rate": 3.876229585032245e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 472448, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 16.833333333333332, | |
| "grad_norm": 8.564609015593305e-05, | |
| "learning_rate": 3.7475747659760502e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 474048, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 16.88888888888889, | |
| "grad_norm": 0.0011284402571618557, | |
| "learning_rate": 3.6209180358759394e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 475616, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 16.944444444444443, | |
| "grad_norm": 7.446792733389884e-05, | |
| "learning_rate": 3.4962713026158694e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 477152, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "grad_norm": 0.00015556522703263909, | |
| "learning_rate": 3.373646285105958e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 478720, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.060616035014390945, | |
| "eval_runtime": 0.5691, | |
| "eval_samples_per_second": 70.283, | |
| "eval_steps_per_second": 17.571, | |
| "num_input_tokens_seen": 478720, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 17.055555555555557, | |
| "grad_norm": 6.409982597688213e-05, | |
| "learning_rate": 3.2530545121807145e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 480288, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 17.11111111111111, | |
| "grad_norm": 0.00011296469892840832, | |
| "learning_rate": 3.1345073215151066e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 481952, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 17.166666666666668, | |
| "grad_norm": 0.00011994578380836174, | |
| "learning_rate": 3.0180158585586397e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 483520, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 17.22222222222222, | |
| "grad_norm": 0.0003533689596224576, | |
| "learning_rate": 2.9035910754875136e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 485120, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 17.27777777777778, | |
| "grad_norm": 0.0018058677669614553, | |
| "learning_rate": 2.7912437301749026e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 486688, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 17.333333333333332, | |
| "grad_norm": 0.00022105852258391678, | |
| "learning_rate": 2.6809843851795357e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 488288, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 17.38888888888889, | |
| "grad_norm": 7.555070624221116e-05, | |
| "learning_rate": 2.57282340675267e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 489856, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 17.444444444444443, | |
| "grad_norm": 7.020117482170463e-05, | |
| "learning_rate": 2.4667709638634434e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 491456, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "grad_norm": 6.069065420888364e-05, | |
| "learning_rate": 2.3628370272428564e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 493024, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 17.555555555555557, | |
| "grad_norm": 0.00012904888717457652, | |
| "learning_rate": 2.2610313684463177e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 494624, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 17.61111111111111, | |
| "grad_norm": 0.0008163969032466412, | |
| "learning_rate": 2.1613635589349756e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 496192, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 17.666666666666668, | |
| "grad_norm": 0.00023050674644764513, | |
| "learning_rate": 2.063842969175847e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 497792, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 17.72222222222222, | |
| "grad_norm": 8.906696893973276e-05, | |
| "learning_rate": 1.968478767760812e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 499360, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "grad_norm": 0.0005315204616636038, | |
| "learning_rate": 1.8752799205445982e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 500896, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 17.833333333333332, | |
| "grad_norm": 7.400880713248625e-05, | |
| "learning_rate": 1.784255189801895e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 502464, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 17.88888888888889, | |
| "grad_norm": 7.668589387321845e-05, | |
| "learning_rate": 1.6954131334034922e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 504000, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 17.944444444444443, | |
| "grad_norm": 7.471307617379352e-05, | |
| "learning_rate": 1.6087621040117157e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 505472, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 6.372728967107832e-05, | |
| "learning_rate": 1.524310248295152e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 507008, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.06168604642152786, | |
| "eval_runtime": 0.5734, | |
| "eval_samples_per_second": 69.759, | |
| "eval_steps_per_second": 17.44, | |
| "num_input_tokens_seen": 507008, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 18.055555555555557, | |
| "grad_norm": 0.00010615726205287501, | |
| "learning_rate": 1.4420655061626932e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 508544, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 18.11111111111111, | |
| "grad_norm": 0.00012012007209705189, | |
| "learning_rate": 1.362035610017079e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 510112, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 18.166666666666668, | |
| "grad_norm": 6.778270471841097e-05, | |
| "learning_rate": 1.2842280840278997e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 511680, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 18.22222222222222, | |
| "grad_norm": 0.00015255736070685089, | |
| "learning_rate": 1.2086502434241865e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 513152, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 18.27777777777778, | |
| "grad_norm": 7.007623935351148e-05, | |
| "learning_rate": 1.1353091938067023e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 514752, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 18.333333333333332, | |
| "grad_norm": 6.782880518585443e-05, | |
| "learning_rate": 1.0642118304798442e-06, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 516320, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 18.38888888888889, | |
| "grad_norm": 8.764761878410354e-05, | |
| "learning_rate": 9.95364837803392e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 517888, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 18.444444444444443, | |
| "grad_norm": 7.796359568601474e-05, | |
| "learning_rate": 9.287746885640603e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 519456, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 18.5, | |
| "grad_norm": 5.415067062131129e-05, | |
| "learning_rate": 8.64447643366953e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 521056, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 18.555555555555557, | |
| "grad_norm": 0.0002548769407439977, | |
| "learning_rate": 8.023897500469391e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 522528, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 18.61111111111111, | |
| "grad_norm": 0.00014372621080838144, | |
| "learning_rate": 7.426068431000882e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 524064, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 18.666666666666668, | |
| "grad_norm": 6.587236566701904e-05, | |
| "learning_rate": 6.851045431350927e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 525664, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 18.72222222222222, | |
| "grad_norm": 7.173832273110747e-05, | |
| "learning_rate": 6.298882563448599e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 527200, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 18.77777777777778, | |
| "grad_norm": 8.011311001610011e-05, | |
| "learning_rate": 5.769631739982267e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 528800, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 18.833333333333332, | |
| "grad_norm": 8.217350114136934e-05, | |
| "learning_rate": 5.263342719518921e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 530432, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 18.88888888888889, | |
| "grad_norm": 9.386655437992886e-05, | |
| "learning_rate": 4.780063101826132e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 532032, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 18.944444444444443, | |
| "grad_norm": 6.237599882297218e-05, | |
| "learning_rate": 4.319838323396691e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 533568, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "grad_norm": 7.45798388379626e-05, | |
| "learning_rate": 3.88271165317694e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 535136, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.06235629320144653, | |
| "eval_runtime": 0.577, | |
| "eval_samples_per_second": 69.324, | |
| "eval_steps_per_second": 17.331, | |
| "num_input_tokens_seen": 535136, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 19.055555555555557, | |
| "grad_norm": 9.331930050393566e-05, | |
| "learning_rate": 3.468724188498751e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 536768, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 19.11111111111111, | |
| "grad_norm": 0.00018884560267906636, | |
| "learning_rate": 3.077914851215585e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 538336, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 19.166666666666668, | |
| "grad_norm": 7.731603545835242e-05, | |
| "learning_rate": 2.71032038404323e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 539872, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 19.22222222222222, | |
| "grad_norm": 6.86842467985116e-05, | |
| "learning_rate": 2.365975347105448e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 541472, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 19.27777777777778, | |
| "grad_norm": 0.0001771255483618006, | |
| "learning_rate": 2.0449121146845774e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 543008, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 19.333333333333332, | |
| "grad_norm": 6.131475674919784e-05, | |
| "learning_rate": 1.747160872177883e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 544608, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 19.38888888888889, | |
| "grad_norm": 6.204837700352073e-05, | |
| "learning_rate": 1.472749613259661e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 546112, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 19.444444444444443, | |
| "grad_norm": 0.00011867362627526745, | |
| "learning_rate": 1.22170413724923e-07, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 547616, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 19.5, | |
| "grad_norm": 7.326277409447357e-05, | |
| "learning_rate": 9.940480466855417e-08, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 549216, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 19.555555555555557, | |
| "grad_norm": 0.0002606595808174461, | |
| "learning_rate": 7.898027451078982e-08, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 550752, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 19.61111111111111, | |
| "grad_norm": 8.589470235165209e-05, | |
| "learning_rate": 6.089874350439506e-08, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 552352, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 19.666666666666668, | |
| "grad_norm": 8.599411376053467e-05, | |
| "learning_rate": 4.516191162040051e-08, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 553920, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 19.72222222222222, | |
| "grad_norm": 7.854592695366591e-05, | |
| "learning_rate": 3.177125838830786e-08, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 555552, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 19.77777777777778, | |
| "grad_norm": 7.356789865298197e-05, | |
| "learning_rate": 2.0728042756967824e-08, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 557056, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 19.833333333333332, | |
| "grad_norm": 0.00010882453352678567, | |
| "learning_rate": 1.2033302976222071e-08, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 558688, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 19.88888888888889, | |
| "grad_norm": 8.214359695557505e-05, | |
| "learning_rate": 5.687856499297928e-09, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 560224, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 19.944444444444443, | |
| "grad_norm": 0.00022446394723374397, | |
| "learning_rate": 1.692299905944883e-09, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 561728, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 6.955169374123216e-05, | |
| "learning_rate": 4.700884634611935e-11, | |
| "loss": 0.0, | |
| "num_input_tokens_seen": 563328, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.06306867301464081, | |
| "eval_runtime": 0.5735, | |
| "eval_samples_per_second": 69.752, | |
| "eval_steps_per_second": 17.438, | |
| "num_input_tokens_seen": 563328, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "num_input_tokens_seen": 563328, | |
| "step": 1800, | |
| "total_flos": 2.541602338032845e+16, | |
| "train_loss": 0.016203932911047457, | |
| "train_runtime": 382.257, | |
| "train_samples_per_second": 18.835, | |
| "train_steps_per_second": 4.709 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1800, | |
| "num_input_tokens_seen": 563328, | |
| "num_train_epochs": 20, | |
| "save_steps": 90, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.541602338032845e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |