| { |
| "best_global_step": 1530, |
| "best_metric": 0.05843701213598251, |
| "best_model_checkpoint": "saves_multiple/ia3/llama-3-8b-instruct/train_copa_789_1760637877/checkpoint-1530", |
| "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": 4.65092658996582, |
| "learning_rate": 1.1111111111111112e-06, |
| "loss": 0.5534, |
| "num_input_tokens_seen": 1632, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1111111111111111, |
| "grad_norm": 4.095375061035156, |
| "learning_rate": 2.5e-06, |
| "loss": 0.6235, |
| "num_input_tokens_seen": 3232, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.16666666666666666, |
| "grad_norm": 4.756162166595459, |
| "learning_rate": 3.888888888888889e-06, |
| "loss": 0.6425, |
| "num_input_tokens_seen": 4832, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 4.172198295593262, |
| "learning_rate": 5.277777777777778e-06, |
| "loss": 0.7387, |
| "num_input_tokens_seen": 6432, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2777777777777778, |
| "grad_norm": 4.3731584548950195, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.681, |
| "num_input_tokens_seen": 7968, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 4.341258525848389, |
| "learning_rate": 8.055555555555557e-06, |
| "loss": 0.518, |
| "num_input_tokens_seen": 9504, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.3888888888888889, |
| "grad_norm": 3.7260754108428955, |
| "learning_rate": 9.444444444444445e-06, |
| "loss": 0.6923, |
| "num_input_tokens_seen": 11104, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 3.8928024768829346, |
| "learning_rate": 1.0833333333333334e-05, |
| "loss": 0.8366, |
| "num_input_tokens_seen": 12704, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 3.961286783218384, |
| "learning_rate": 1.2222222222222222e-05, |
| "loss": 0.5993, |
| "num_input_tokens_seen": 14240, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 4.945498943328857, |
| "learning_rate": 1.3611111111111111e-05, |
| "loss": 0.6052, |
| "num_input_tokens_seen": 15808, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6111111111111112, |
| "grad_norm": 4.686919689178467, |
| "learning_rate": 1.5e-05, |
| "loss": 0.72, |
| "num_input_tokens_seen": 17344, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 4.145110130310059, |
| "learning_rate": 1.638888888888889e-05, |
| "loss": 0.5328, |
| "num_input_tokens_seen": 18912, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7222222222222222, |
| "grad_norm": 4.903788089752197, |
| "learning_rate": 1.777777777777778e-05, |
| "loss": 0.6527, |
| "num_input_tokens_seen": 20448, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.7777777777777778, |
| "grad_norm": 3.0253090858459473, |
| "learning_rate": 1.9166666666666667e-05, |
| "loss": 0.5486, |
| "num_input_tokens_seen": 21984, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 3.5490806102752686, |
| "learning_rate": 2.0555555555555555e-05, |
| "loss": 0.6792, |
| "num_input_tokens_seen": 23552, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 4.2691826820373535, |
| "learning_rate": 2.1944444444444445e-05, |
| "loss": 0.6004, |
| "num_input_tokens_seen": 25120, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.9444444444444444, |
| "grad_norm": 4.216991901397705, |
| "learning_rate": 2.3333333333333336e-05, |
| "loss": 0.5378, |
| "num_input_tokens_seen": 26656, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 5.902134895324707, |
| "learning_rate": 2.4722222222222223e-05, |
| "loss": 0.6696, |
| "num_input_tokens_seen": 28192, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.5326165556907654, |
| "eval_runtime": 0.5121, |
| "eval_samples_per_second": 78.105, |
| "eval_steps_per_second": 19.526, |
| "num_input_tokens_seen": 28192, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0555555555555556, |
| "grad_norm": 4.175025939941406, |
| "learning_rate": 2.6111111111111114e-05, |
| "loss": 0.5202, |
| "num_input_tokens_seen": 29792, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 3.9834649562835693, |
| "learning_rate": 2.7500000000000004e-05, |
| "loss": 0.5988, |
| "num_input_tokens_seen": 31328, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.1666666666666667, |
| "grad_norm": 5.505035877227783, |
| "learning_rate": 2.8888888888888888e-05, |
| "loss": 0.5913, |
| "num_input_tokens_seen": 32832, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.2222222222222223, |
| "grad_norm": 4.22908878326416, |
| "learning_rate": 3.0277777777777776e-05, |
| "loss": 0.548, |
| "num_input_tokens_seen": 34304, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.2777777777777777, |
| "grad_norm": 4.530610084533691, |
| "learning_rate": 3.1666666666666666e-05, |
| "loss": 0.7176, |
| "num_input_tokens_seen": 35840, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 4.503519058227539, |
| "learning_rate": 3.3055555555555553e-05, |
| "loss": 0.8881, |
| "num_input_tokens_seen": 37376, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.3888888888888888, |
| "grad_norm": 3.23877215385437, |
| "learning_rate": 3.444444444444445e-05, |
| "loss": 0.5414, |
| "num_input_tokens_seen": 38944, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.4444444444444444, |
| "grad_norm": 3.4258248805999756, |
| "learning_rate": 3.5833333333333335e-05, |
| "loss": 0.5146, |
| "num_input_tokens_seen": 40512, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 1.7767366170883179, |
| "learning_rate": 3.722222222222222e-05, |
| "loss": 0.2194, |
| "num_input_tokens_seen": 42080, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.5555555555555556, |
| "grad_norm": 2.1948487758636475, |
| "learning_rate": 3.8611111111111116e-05, |
| "loss": 0.345, |
| "num_input_tokens_seen": 43680, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.6111111111111112, |
| "grad_norm": 0.2988741099834442, |
| "learning_rate": 4e-05, |
| "loss": 0.0985, |
| "num_input_tokens_seen": 45216, |
| "step": 145 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 1.2166426181793213, |
| "learning_rate": 4.138888888888889e-05, |
| "loss": 0.3053, |
| "num_input_tokens_seen": 46720, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.7222222222222223, |
| "grad_norm": 0.09494301676750183, |
| "learning_rate": 4.277777777777778e-05, |
| "loss": 0.02, |
| "num_input_tokens_seen": 48288, |
| "step": 155 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 1.532537579536438, |
| "learning_rate": 4.4166666666666665e-05, |
| "loss": 0.1515, |
| "num_input_tokens_seen": 49888, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.8333333333333335, |
| "grad_norm": 0.09204932302236557, |
| "learning_rate": 4.555555555555556e-05, |
| "loss": 0.0452, |
| "num_input_tokens_seen": 51424, |
| "step": 165 |
| }, |
| { |
| "epoch": 1.8888888888888888, |
| "grad_norm": 2.5189366340637207, |
| "learning_rate": 4.6944444444444446e-05, |
| "loss": 0.2567, |
| "num_input_tokens_seen": 52992, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.9444444444444444, |
| "grad_norm": 0.16729450225830078, |
| "learning_rate": 4.8333333333333334e-05, |
| "loss": 0.0968, |
| "num_input_tokens_seen": 54592, |
| "step": 175 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.3235429525375366, |
| "learning_rate": 4.972222222222223e-05, |
| "loss": 0.1462, |
| "num_input_tokens_seen": 56192, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.06989195197820663, |
| "eval_runtime": 0.5163, |
| "eval_samples_per_second": 77.468, |
| "eval_steps_per_second": 19.367, |
| "num_input_tokens_seen": 56192, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.0555555555555554, |
| "grad_norm": 1.0239298343658447, |
| "learning_rate": 4.9999247861994194e-05, |
| "loss": 0.0372, |
| "num_input_tokens_seen": 57760, |
| "step": 185 |
| }, |
| { |
| "epoch": 2.111111111111111, |
| "grad_norm": 0.03282800316810608, |
| "learning_rate": 4.9996192378909786e-05, |
| "loss": 0.0526, |
| "num_input_tokens_seen": 59264, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.1666666666666665, |
| "grad_norm": 0.02693193219602108, |
| "learning_rate": 4.999078682916774e-05, |
| "loss": 0.1378, |
| "num_input_tokens_seen": 60768, |
| "step": 195 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 2.3027944564819336, |
| "learning_rate": 4.998303172098155e-05, |
| "loss": 0.1461, |
| "num_input_tokens_seen": 62272, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.2777777777777777, |
| "grad_norm": 0.21790486574172974, |
| "learning_rate": 4.997292778346312e-05, |
| "loss": 0.0839, |
| "num_input_tokens_seen": 63808, |
| "step": 205 |
| }, |
| { |
| "epoch": 2.3333333333333335, |
| "grad_norm": 1.9243621826171875, |
| "learning_rate": 4.996047596655418e-05, |
| "loss": 0.2373, |
| "num_input_tokens_seen": 65344, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.388888888888889, |
| "grad_norm": 0.5471611022949219, |
| "learning_rate": 4.994567744093703e-05, |
| "loss": 0.0171, |
| "num_input_tokens_seen": 66912, |
| "step": 215 |
| }, |
| { |
| "epoch": 2.4444444444444446, |
| "grad_norm": 1.6998534202575684, |
| "learning_rate": 4.992853359792444e-05, |
| "loss": 0.2556, |
| "num_input_tokens_seen": 68480, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.36938992142677307, |
| "learning_rate": 4.9909046049328846e-05, |
| "loss": 0.0088, |
| "num_input_tokens_seen": 70048, |
| "step": 225 |
| }, |
| { |
| "epoch": 2.5555555555555554, |
| "grad_norm": 0.2923737168312073, |
| "learning_rate": 4.988721662731083e-05, |
| "loss": 0.0252, |
| "num_input_tokens_seen": 71680, |
| "step": 230 |
| }, |
| { |
| "epoch": 2.611111111111111, |
| "grad_norm": 2.4089598655700684, |
| "learning_rate": 4.9863047384206835e-05, |
| "loss": 0.2822, |
| "num_input_tokens_seen": 73280, |
| "step": 235 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 0.03126000985503197, |
| "learning_rate": 4.983654059233626e-05, |
| "loss": 0.0374, |
| "num_input_tokens_seen": 74752, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.7222222222222223, |
| "grad_norm": 0.03382931277155876, |
| "learning_rate": 4.9807698743787744e-05, |
| "loss": 0.1257, |
| "num_input_tokens_seen": 76288, |
| "step": 245 |
| }, |
| { |
| "epoch": 2.7777777777777777, |
| "grad_norm": 0.024398092180490494, |
| "learning_rate": 4.9776524550184965e-05, |
| "loss": 0.1005, |
| "num_input_tokens_seen": 77888, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.8333333333333335, |
| "grad_norm": 0.1415417343378067, |
| "learning_rate": 4.974302094243164e-05, |
| "loss": 0.0065, |
| "num_input_tokens_seen": 79456, |
| "step": 255 |
| }, |
| { |
| "epoch": 2.888888888888889, |
| "grad_norm": 0.4479515552520752, |
| "learning_rate": 4.970719107043595e-05, |
| "loss": 0.1297, |
| "num_input_tokens_seen": 81088, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.9444444444444446, |
| "grad_norm": 0.5779532790184021, |
| "learning_rate": 4.966903830281449e-05, |
| "loss": 0.0452, |
| "num_input_tokens_seen": 82592, |
| "step": 265 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.6592082977294922, |
| "learning_rate": 4.962856622657541e-05, |
| "loss": 0.126, |
| "num_input_tokens_seen": 84192, |
| "step": 270 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.0657103881239891, |
| "eval_runtime": 0.5198, |
| "eval_samples_per_second": 76.956, |
| "eval_steps_per_second": 19.239, |
| "num_input_tokens_seen": 84192, |
| "step": 270 |
| }, |
| { |
| "epoch": 3.0555555555555554, |
| "grad_norm": 0.03279653564095497, |
| "learning_rate": 4.9585778646781364e-05, |
| "loss": 0.0746, |
| "num_input_tokens_seen": 85696, |
| "step": 275 |
| }, |
| { |
| "epoch": 3.111111111111111, |
| "grad_norm": 0.8626558184623718, |
| "learning_rate": 4.9540679586191605e-05, |
| "loss": 0.052, |
| "num_input_tokens_seen": 87296, |
| "step": 280 |
| }, |
| { |
| "epoch": 3.1666666666666665, |
| "grad_norm": 0.11952415108680725, |
| "learning_rate": 4.9493273284883854e-05, |
| "loss": 0.0361, |
| "num_input_tokens_seen": 88832, |
| "step": 285 |
| }, |
| { |
| "epoch": 3.2222222222222223, |
| "grad_norm": 0.023274501785635948, |
| "learning_rate": 4.9443564199855666e-05, |
| "loss": 0.0264, |
| "num_input_tokens_seen": 90368, |
| "step": 290 |
| }, |
| { |
| "epoch": 3.2777777777777777, |
| "grad_norm": 0.22339174151420593, |
| "learning_rate": 4.939155700460536e-05, |
| "loss": 0.0202, |
| "num_input_tokens_seen": 91968, |
| "step": 295 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 0.9900386333465576, |
| "learning_rate": 4.933725658869267e-05, |
| "loss": 0.0386, |
| "num_input_tokens_seen": 93568, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.388888888888889, |
| "grad_norm": 0.02162184566259384, |
| "learning_rate": 4.9280668057279014e-05, |
| "loss": 0.0482, |
| "num_input_tokens_seen": 95168, |
| "step": 305 |
| }, |
| { |
| "epoch": 3.4444444444444446, |
| "grad_norm": 0.04586295410990715, |
| "learning_rate": 4.9221796730647516e-05, |
| "loss": 0.1022, |
| "num_input_tokens_seen": 96704, |
| "step": 310 |
| }, |
| { |
| "epoch": 3.5, |
| "grad_norm": 0.025104861706495285, |
| "learning_rate": 4.916064814370287e-05, |
| "loss": 0.1679, |
| "num_input_tokens_seen": 98304, |
| "step": 315 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.028672898188233376, |
| "learning_rate": 4.9097228045450864e-05, |
| "loss": 0.0053, |
| "num_input_tokens_seen": 99840, |
| "step": 320 |
| }, |
| { |
| "epoch": 3.611111111111111, |
| "grad_norm": 0.24982739984989166, |
| "learning_rate": 4.9031542398457974e-05, |
| "loss": 0.0527, |
| "num_input_tokens_seen": 101376, |
| "step": 325 |
| }, |
| { |
| "epoch": 3.6666666666666665, |
| "grad_norm": 0.42373406887054443, |
| "learning_rate": 4.896359737829071e-05, |
| "loss": 0.1674, |
| "num_input_tokens_seen": 102976, |
| "step": 330 |
| }, |
| { |
| "epoch": 3.7222222222222223, |
| "grad_norm": 1.0080994367599487, |
| "learning_rate": 4.889339937293508e-05, |
| "loss": 0.0776, |
| "num_input_tokens_seen": 104576, |
| "step": 335 |
| }, |
| { |
| "epoch": 3.7777777777777777, |
| "grad_norm": 0.6784046292304993, |
| "learning_rate": 4.8820954982195905e-05, |
| "loss": 0.2309, |
| "num_input_tokens_seen": 106112, |
| "step": 340 |
| }, |
| { |
| "epoch": 3.8333333333333335, |
| "grad_norm": 0.024361956864595413, |
| "learning_rate": 4.874627101707644e-05, |
| "loss": 0.1049, |
| "num_input_tokens_seen": 107712, |
| "step": 345 |
| }, |
| { |
| "epoch": 3.888888888888889, |
| "grad_norm": 0.15874440968036652, |
| "learning_rate": 4.8669354499137955e-05, |
| "loss": 0.129, |
| "num_input_tokens_seen": 109344, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.9444444444444446, |
| "grad_norm": 2.3382439613342285, |
| "learning_rate": 4.859021265983959e-05, |
| "loss": 0.1734, |
| "num_input_tokens_seen": 110944, |
| "step": 355 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.6307403445243835, |
| "learning_rate": 4.850885293985853e-05, |
| "loss": 0.0396, |
| "num_input_tokens_seen": 112544, |
| "step": 360 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.06675007939338684, |
| "eval_runtime": 0.5188, |
| "eval_samples_per_second": 77.097, |
| "eval_steps_per_second": 19.274, |
| "num_input_tokens_seen": 112544, |
| "step": 360 |
| }, |
| { |
| "epoch": 4.055555555555555, |
| "grad_norm": 0.09657640755176544, |
| "learning_rate": 4.8425282988390376e-05, |
| "loss": 0.0751, |
| "num_input_tokens_seen": 114144, |
| "step": 365 |
| }, |
| { |
| "epoch": 4.111111111111111, |
| "grad_norm": 0.8270570039749146, |
| "learning_rate": 4.8339510662430046e-05, |
| "loss": 0.0563, |
| "num_input_tokens_seen": 115712, |
| "step": 370 |
| }, |
| { |
| "epoch": 4.166666666666667, |
| "grad_norm": 0.6188746094703674, |
| "learning_rate": 4.825154402603308e-05, |
| "loss": 0.1947, |
| "num_input_tokens_seen": 117312, |
| "step": 375 |
| }, |
| { |
| "epoch": 4.222222222222222, |
| "grad_norm": 0.978348970413208, |
| "learning_rate": 4.816139134955746e-05, |
| "loss": 0.1331, |
| "num_input_tokens_seen": 118848, |
| "step": 380 |
| }, |
| { |
| "epoch": 4.277777777777778, |
| "grad_norm": 1.4264014959335327, |
| "learning_rate": 4.806906110888606e-05, |
| "loss": 0.0498, |
| "num_input_tokens_seen": 120416, |
| "step": 385 |
| }, |
| { |
| "epoch": 4.333333333333333, |
| "grad_norm": 0.5848916172981262, |
| "learning_rate": 4.797456198462979e-05, |
| "loss": 0.0876, |
| "num_input_tokens_seen": 122016, |
| "step": 390 |
| }, |
| { |
| "epoch": 4.388888888888889, |
| "grad_norm": 1.7021077871322632, |
| "learning_rate": 4.7877902861311446e-05, |
| "loss": 0.1327, |
| "num_input_tokens_seen": 123584, |
| "step": 395 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 0.02586347423493862, |
| "learning_rate": 4.777909282653042e-05, |
| "loss": 0.0162, |
| "num_input_tokens_seen": 125216, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.5, |
| "grad_norm": 0.7212857604026794, |
| "learning_rate": 4.7678141170108345e-05, |
| "loss": 0.0556, |
| "num_input_tokens_seen": 126784, |
| "step": 405 |
| }, |
| { |
| "epoch": 4.555555555555555, |
| "grad_norm": 0.12025772035121918, |
| "learning_rate": 4.757505738321563e-05, |
| "loss": 0.0259, |
| "num_input_tokens_seen": 128352, |
| "step": 410 |
| }, |
| { |
| "epoch": 4.611111111111111, |
| "grad_norm": 0.2885558009147644, |
| "learning_rate": 4.7469851157479177e-05, |
| "loss": 0.021, |
| "num_input_tokens_seen": 129920, |
| "step": 415 |
| }, |
| { |
| "epoch": 4.666666666666667, |
| "grad_norm": 0.09183027595281601, |
| "learning_rate": 4.736253238407119e-05, |
| "loss": 0.0269, |
| "num_input_tokens_seen": 131488, |
| "step": 420 |
| }, |
| { |
| "epoch": 4.722222222222222, |
| "grad_norm": 0.04295544698834419, |
| "learning_rate": 4.725311115277924e-05, |
| "loss": 0.1203, |
| "num_input_tokens_seen": 133056, |
| "step": 425 |
| }, |
| { |
| "epoch": 4.777777777777778, |
| "grad_norm": 0.2513387203216553, |
| "learning_rate": 4.714159775105765e-05, |
| "loss": 0.0552, |
| "num_input_tokens_seen": 134624, |
| "step": 430 |
| }, |
| { |
| "epoch": 4.833333333333333, |
| "grad_norm": 0.2819466292858124, |
| "learning_rate": 4.70280026630603e-05, |
| "loss": 0.0788, |
| "num_input_tokens_seen": 136192, |
| "step": 435 |
| }, |
| { |
| "epoch": 4.888888888888889, |
| "grad_norm": 0.02205601893365383, |
| "learning_rate": 4.6912336568654925e-05, |
| "loss": 0.0426, |
| "num_input_tokens_seen": 137824, |
| "step": 440 |
| }, |
| { |
| "epoch": 4.944444444444445, |
| "grad_norm": 0.248850479722023, |
| "learning_rate": 4.679461034241906e-05, |
| "loss": 0.0641, |
| "num_input_tokens_seen": 139392, |
| "step": 445 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.6842424273490906, |
| "learning_rate": 4.667483505261762e-05, |
| "loss": 0.1156, |
| "num_input_tokens_seen": 140960, |
| "step": 450 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.06348364055156708, |
| "eval_runtime": 0.5151, |
| "eval_samples_per_second": 77.651, |
| "eval_steps_per_second": 19.413, |
| "num_input_tokens_seen": 140960, |
| "step": 450 |
| }, |
| { |
| "epoch": 5.055555555555555, |
| "grad_norm": 0.03485225886106491, |
| "learning_rate": 4.655302196016228e-05, |
| "loss": 0.0857, |
| "num_input_tokens_seen": 142560, |
| "step": 455 |
| }, |
| { |
| "epoch": 5.111111111111111, |
| "grad_norm": 0.07330955564975739, |
| "learning_rate": 4.642918251755281e-05, |
| "loss": 0.0651, |
| "num_input_tokens_seen": 144096, |
| "step": 460 |
| }, |
| { |
| "epoch": 5.166666666666667, |
| "grad_norm": 0.15627992153167725, |
| "learning_rate": 4.6303328367800284e-05, |
| "loss": 0.0184, |
| "num_input_tokens_seen": 145632, |
| "step": 465 |
| }, |
| { |
| "epoch": 5.222222222222222, |
| "grad_norm": 1.0182912349700928, |
| "learning_rate": 4.6175471343332485e-05, |
| "loss": 0.085, |
| "num_input_tokens_seen": 147232, |
| "step": 470 |
| }, |
| { |
| "epoch": 5.277777777777778, |
| "grad_norm": 0.15309298038482666, |
| "learning_rate": 4.604562346488144e-05, |
| "loss": 0.1157, |
| "num_input_tokens_seen": 148864, |
| "step": 475 |
| }, |
| { |
| "epoch": 5.333333333333333, |
| "grad_norm": 0.08715078979730606, |
| "learning_rate": 4.591379694035325e-05, |
| "loss": 0.0295, |
| "num_input_tokens_seen": 150432, |
| "step": 480 |
| }, |
| { |
| "epoch": 5.388888888888889, |
| "grad_norm": 0.48800748586654663, |
| "learning_rate": 4.5780004163680365e-05, |
| "loss": 0.0973, |
| "num_input_tokens_seen": 152032, |
| "step": 485 |
| }, |
| { |
| "epoch": 5.444444444444445, |
| "grad_norm": 0.9018146395683289, |
| "learning_rate": 4.5644257713656356e-05, |
| "loss": 0.0468, |
| "num_input_tokens_seen": 153600, |
| "step": 490 |
| }, |
| { |
| "epoch": 5.5, |
| "grad_norm": 1.2570453882217407, |
| "learning_rate": 4.550657035275323e-05, |
| "loss": 0.0803, |
| "num_input_tokens_seen": 155200, |
| "step": 495 |
| }, |
| { |
| "epoch": 5.555555555555555, |
| "grad_norm": 0.04507768154144287, |
| "learning_rate": 4.536695502592162e-05, |
| "loss": 0.1479, |
| "num_input_tokens_seen": 156800, |
| "step": 500 |
| }, |
| { |
| "epoch": 5.611111111111111, |
| "grad_norm": 0.02345445193350315, |
| "learning_rate": 4.522542485937369e-05, |
| "loss": 0.0097, |
| "num_input_tokens_seen": 158336, |
| "step": 505 |
| }, |
| { |
| "epoch": 5.666666666666667, |
| "grad_norm": 0.13815099000930786, |
| "learning_rate": 4.5081993159349056e-05, |
| "loss": 0.0184, |
| "num_input_tokens_seen": 159904, |
| "step": 510 |
| }, |
| { |
| "epoch": 5.722222222222222, |
| "grad_norm": 1.6783974170684814, |
| "learning_rate": 4.493667341086379e-05, |
| "loss": 0.109, |
| "num_input_tokens_seen": 161504, |
| "step": 515 |
| }, |
| { |
| "epoch": 5.777777777777778, |
| "grad_norm": 0.03608032688498497, |
| "learning_rate": 4.478947927644258e-05, |
| "loss": 0.0146, |
| "num_input_tokens_seen": 163008, |
| "step": 520 |
| }, |
| { |
| "epoch": 5.833333333333333, |
| "grad_norm": 0.6085768342018127, |
| "learning_rate": 4.464042459483425e-05, |
| "loss": 0.0752, |
| "num_input_tokens_seen": 164512, |
| "step": 525 |
| }, |
| { |
| "epoch": 5.888888888888889, |
| "grad_norm": 0.6818676590919495, |
| "learning_rate": 4.448952337971064e-05, |
| "loss": 0.1839, |
| "num_input_tokens_seen": 166080, |
| "step": 530 |
| }, |
| { |
| "epoch": 5.944444444444445, |
| "grad_norm": 0.025021351873874664, |
| "learning_rate": 4.43367898183491e-05, |
| "loss": 0.0553, |
| "num_input_tokens_seen": 167680, |
| "step": 535 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.016283836215734482, |
| "learning_rate": 4.418223827029867e-05, |
| "loss": 0.0155, |
| "num_input_tokens_seen": 169216, |
| "step": 540 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.06451700627803802, |
| "eval_runtime": 0.5189, |
| "eval_samples_per_second": 77.089, |
| "eval_steps_per_second": 19.272, |
| "num_input_tokens_seen": 169216, |
| "step": 540 |
| }, |
| { |
| "epoch": 6.055555555555555, |
| "grad_norm": 0.04106647148728371, |
| "learning_rate": 4.402588326603002e-05, |
| "loss": 0.0236, |
| "num_input_tokens_seen": 170784, |
| "step": 545 |
| }, |
| { |
| "epoch": 6.111111111111111, |
| "grad_norm": 0.8891972303390503, |
| "learning_rate": 4.386773950556931e-05, |
| "loss": 0.0654, |
| "num_input_tokens_seen": 172352, |
| "step": 550 |
| }, |
| { |
| "epoch": 6.166666666666667, |
| "grad_norm": 0.3865717649459839, |
| "learning_rate": 4.3707821857116176e-05, |
| "loss": 0.0432, |
| "num_input_tokens_seen": 173920, |
| "step": 555 |
| }, |
| { |
| "epoch": 6.222222222222222, |
| "grad_norm": 0.35376498103141785, |
| "learning_rate": 4.354614535564588e-05, |
| "loss": 0.0359, |
| "num_input_tokens_seen": 175488, |
| "step": 560 |
| }, |
| { |
| "epoch": 6.277777777777778, |
| "grad_norm": 1.738903522491455, |
| "learning_rate": 4.3382725201495723e-05, |
| "loss": 0.0785, |
| "num_input_tokens_seen": 177024, |
| "step": 565 |
| }, |
| { |
| "epoch": 6.333333333333333, |
| "grad_norm": 0.38843443989753723, |
| "learning_rate": 4.321757675893596e-05, |
| "loss": 0.0491, |
| "num_input_tokens_seen": 178624, |
| "step": 570 |
| }, |
| { |
| "epoch": 6.388888888888889, |
| "grad_norm": 0.322394996881485, |
| "learning_rate": 4.305071555472534e-05, |
| "loss": 0.1942, |
| "num_input_tokens_seen": 180096, |
| "step": 575 |
| }, |
| { |
| "epoch": 6.444444444444445, |
| "grad_norm": 0.8024235963821411, |
| "learning_rate": 4.288215727665129e-05, |
| "loss": 0.056, |
| "num_input_tokens_seen": 181600, |
| "step": 580 |
| }, |
| { |
| "epoch": 6.5, |
| "grad_norm": 1.246673583984375, |
| "learning_rate": 4.2711917772055e-05, |
| "loss": 0.0492, |
| "num_input_tokens_seen": 183232, |
| "step": 585 |
| }, |
| { |
| "epoch": 6.555555555555555, |
| "grad_norm": 0.022138679400086403, |
| "learning_rate": 4.254001304634151e-05, |
| "loss": 0.0965, |
| "num_input_tokens_seen": 184768, |
| "step": 590 |
| }, |
| { |
| "epoch": 6.611111111111111, |
| "grad_norm": 0.013323606923222542, |
| "learning_rate": 4.2366459261474933e-05, |
| "loss": 0.0785, |
| "num_input_tokens_seen": 186208, |
| "step": 595 |
| }, |
| { |
| "epoch": 6.666666666666667, |
| "grad_norm": 0.017629526555538177, |
| "learning_rate": 4.2191272734458955e-05, |
| "loss": 0.0285, |
| "num_input_tokens_seen": 187776, |
| "step": 600 |
| }, |
| { |
| "epoch": 6.722222222222222, |
| "grad_norm": 1.184860110282898, |
| "learning_rate": 4.201446993580276e-05, |
| "loss": 0.0469, |
| "num_input_tokens_seen": 189344, |
| "step": 605 |
| }, |
| { |
| "epoch": 6.777777777777778, |
| "grad_norm": 0.07062964886426926, |
| "learning_rate": 4.183606748797251e-05, |
| "loss": 0.0205, |
| "num_input_tokens_seen": 190912, |
| "step": 610 |
| }, |
| { |
| "epoch": 6.833333333333333, |
| "grad_norm": 0.04091072455048561, |
| "learning_rate": 4.1656082163828566e-05, |
| "loss": 0.1118, |
| "num_input_tokens_seen": 192512, |
| "step": 615 |
| }, |
| { |
| "epoch": 6.888888888888889, |
| "grad_norm": 0.05158746615052223, |
| "learning_rate": 4.147453088504854e-05, |
| "loss": 0.0199, |
| "num_input_tokens_seen": 194112, |
| "step": 620 |
| }, |
| { |
| "epoch": 6.944444444444445, |
| "grad_norm": 0.7025681138038635, |
| "learning_rate": 4.129143072053638e-05, |
| "loss": 0.1499, |
| "num_input_tokens_seen": 195712, |
| "step": 625 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.13185453414916992, |
| "learning_rate": 4.110679888481763e-05, |
| "loss": 0.0091, |
| "num_input_tokens_seen": 197248, |
| "step": 630 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.06116596609354019, |
| "eval_runtime": 0.5186, |
| "eval_samples_per_second": 77.136, |
| "eval_steps_per_second": 19.284, |
| "num_input_tokens_seen": 197248, |
| "step": 630 |
| }, |
| { |
| "epoch": 7.055555555555555, |
| "grad_norm": 0.1526983231306076, |
| "learning_rate": 4.09206527364209e-05, |
| "loss": 0.0193, |
| "num_input_tokens_seen": 198784, |
| "step": 635 |
| }, |
| { |
| "epoch": 7.111111111111111, |
| "grad_norm": 1.433021903038025, |
| "learning_rate": 4.073300977624594e-05, |
| "loss": 0.092, |
| "num_input_tokens_seen": 200352, |
| "step": 640 |
| }, |
| { |
| "epoch": 7.166666666666667, |
| "grad_norm": 0.4112715721130371, |
| "learning_rate": 4.054388764591822e-05, |
| "loss": 0.0539, |
| "num_input_tokens_seen": 201856, |
| "step": 645 |
| }, |
| { |
| "epoch": 7.222222222222222, |
| "grad_norm": 0.022885221987962723, |
| "learning_rate": 4.035330412613035e-05, |
| "loss": 0.0623, |
| "num_input_tokens_seen": 203488, |
| "step": 650 |
| }, |
| { |
| "epoch": 7.277777777777778, |
| "grad_norm": 0.032947391271591187, |
| "learning_rate": 4.0161277134970345e-05, |
| "loss": 0.0238, |
| "num_input_tokens_seen": 205056, |
| "step": 655 |
| }, |
| { |
| "epoch": 7.333333333333333, |
| "grad_norm": 0.25257608294487, |
| "learning_rate": 3.996782472623705e-05, |
| "loss": 0.0829, |
| "num_input_tokens_seen": 206656, |
| "step": 660 |
| }, |
| { |
| "epoch": 7.388888888888889, |
| "grad_norm": 0.2931102216243744, |
| "learning_rate": 3.977296508774278e-05, |
| "loss": 0.0418, |
| "num_input_tokens_seen": 208288, |
| "step": 665 |
| }, |
| { |
| "epoch": 7.444444444444445, |
| "grad_norm": 1.5941400527954102, |
| "learning_rate": 3.957671653960337e-05, |
| "loss": 0.1037, |
| "num_input_tokens_seen": 209856, |
| "step": 670 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 1.2473227977752686, |
| "learning_rate": 3.9379097532515725e-05, |
| "loss": 0.0465, |
| "num_input_tokens_seen": 211424, |
| "step": 675 |
| }, |
| { |
| "epoch": 7.555555555555555, |
| "grad_norm": 0.053567372262477875, |
| "learning_rate": 3.918012664602317e-05, |
| "loss": 0.0115, |
| "num_input_tokens_seen": 212928, |
| "step": 680 |
| }, |
| { |
| "epoch": 7.611111111111111, |
| "grad_norm": 0.13769978284835815, |
| "learning_rate": 3.897982258676867e-05, |
| "loss": 0.0293, |
| "num_input_tokens_seen": 214496, |
| "step": 685 |
| }, |
| { |
| "epoch": 7.666666666666667, |
| "grad_norm": 0.046278007328510284, |
| "learning_rate": 3.8778204186736076e-05, |
| "loss": 0.0137, |
| "num_input_tokens_seen": 216064, |
| "step": 690 |
| }, |
| { |
| "epoch": 7.722222222222222, |
| "grad_norm": 0.03257855400443077, |
| "learning_rate": 3.8575290401479586e-05, |
| "loss": 0.125, |
| "num_input_tokens_seen": 217600, |
| "step": 695 |
| }, |
| { |
| "epoch": 7.777777777777778, |
| "grad_norm": 1.0644551515579224, |
| "learning_rate": 3.837110030834161e-05, |
| "loss": 0.0516, |
| "num_input_tokens_seen": 219136, |
| "step": 700 |
| }, |
| { |
| "epoch": 7.833333333333333, |
| "grad_norm": 0.1464487761259079, |
| "learning_rate": 3.8165653104659185e-05, |
| "loss": 0.0523, |
| "num_input_tokens_seen": 220704, |
| "step": 705 |
| }, |
| { |
| "epoch": 7.888888888888889, |
| "grad_norm": 0.7324170470237732, |
| "learning_rate": 3.79589681059591e-05, |
| "loss": 0.0839, |
| "num_input_tokens_seen": 222272, |
| "step": 710 |
| }, |
| { |
| "epoch": 7.944444444444445, |
| "grad_norm": 0.17301106452941895, |
| "learning_rate": 3.775106474414188e-05, |
| "loss": 0.0171, |
| "num_input_tokens_seen": 223872, |
| "step": 715 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.8065789937973022, |
| "learning_rate": 3.75419625656549e-05, |
| "loss": 0.1638, |
| "num_input_tokens_seen": 225440, |
| "step": 720 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.06141107156872749, |
| "eval_runtime": 0.5188, |
| "eval_samples_per_second": 77.108, |
| "eval_steps_per_second": 19.277, |
| "num_input_tokens_seen": 225440, |
| "step": 720 |
| }, |
| { |
| "epoch": 8.055555555555555, |
| "grad_norm": 1.6780734062194824, |
| "learning_rate": 3.7331681229654635e-05, |
| "loss": 0.063, |
| "num_input_tokens_seen": 226912, |
| "step": 725 |
| }, |
| { |
| "epoch": 8.11111111111111, |
| "grad_norm": 0.33701032400131226, |
| "learning_rate": 3.712024050615843e-05, |
| "loss": 0.0179, |
| "num_input_tokens_seen": 228512, |
| "step": 730 |
| }, |
| { |
| "epoch": 8.166666666666666, |
| "grad_norm": 0.5328055024147034, |
| "learning_rate": 3.690766027418573e-05, |
| "loss": 0.1383, |
| "num_input_tokens_seen": 230080, |
| "step": 735 |
| }, |
| { |
| "epoch": 8.222222222222221, |
| "grad_norm": 0.2738179564476013, |
| "learning_rate": 3.6693960519889106e-05, |
| "loss": 0.015, |
| "num_input_tokens_seen": 231616, |
| "step": 740 |
| }, |
| { |
| "epoch": 8.277777777777779, |
| "grad_norm": 0.012103931978344917, |
| "learning_rate": 3.6479161334675296e-05, |
| "loss": 0.0592, |
| "num_input_tokens_seen": 233184, |
| "step": 745 |
| }, |
| { |
| "epoch": 8.333333333333334, |
| "grad_norm": 0.6792635321617126, |
| "learning_rate": 3.626328291331618e-05, |
| "loss": 0.0447, |
| "num_input_tokens_seen": 234688, |
| "step": 750 |
| }, |
| { |
| "epoch": 8.38888888888889, |
| "grad_norm": 0.24234500527381897, |
| "learning_rate": 3.60463455520502e-05, |
| "loss": 0.1588, |
| "num_input_tokens_seen": 236256, |
| "step": 755 |
| }, |
| { |
| "epoch": 8.444444444444445, |
| "grad_norm": 0.2365965098142624, |
| "learning_rate": 3.582836964667408e-05, |
| "loss": 0.0256, |
| "num_input_tokens_seen": 237856, |
| "step": 760 |
| }, |
| { |
| "epoch": 8.5, |
| "grad_norm": 0.1399311125278473, |
| "learning_rate": 3.560937569062538e-05, |
| "loss": 0.0035, |
| "num_input_tokens_seen": 239392, |
| "step": 765 |
| }, |
| { |
| "epoch": 8.555555555555555, |
| "grad_norm": 0.1434163898229599, |
| "learning_rate": 3.538938427305573e-05, |
| "loss": 0.1312, |
| "num_input_tokens_seen": 240960, |
| "step": 770 |
| }, |
| { |
| "epoch": 8.61111111111111, |
| "grad_norm": 0.06928466260433197, |
| "learning_rate": 3.516841607689501e-05, |
| "loss": 0.0597, |
| "num_input_tokens_seen": 242496, |
| "step": 775 |
| }, |
| { |
| "epoch": 8.666666666666666, |
| "grad_norm": 0.7546709775924683, |
| "learning_rate": 3.494649187690695e-05, |
| "loss": 0.0451, |
| "num_input_tokens_seen": 244064, |
| "step": 780 |
| }, |
| { |
| "epoch": 8.722222222222221, |
| "grad_norm": 0.024969231337308884, |
| "learning_rate": 3.4723632537735846e-05, |
| "loss": 0.0154, |
| "num_input_tokens_seen": 245664, |
| "step": 785 |
| }, |
| { |
| "epoch": 8.777777777777779, |
| "grad_norm": 0.20347218215465546, |
| "learning_rate": 3.449985901194498e-05, |
| "loss": 0.0257, |
| "num_input_tokens_seen": 247264, |
| "step": 790 |
| }, |
| { |
| "epoch": 8.833333333333334, |
| "grad_norm": 0.28938475251197815, |
| "learning_rate": 3.427519233804667e-05, |
| "loss": 0.0679, |
| "num_input_tokens_seen": 248832, |
| "step": 795 |
| }, |
| { |
| "epoch": 8.88888888888889, |
| "grad_norm": 0.037665314972400665, |
| "learning_rate": 3.404965363852437e-05, |
| "loss": 0.1039, |
| "num_input_tokens_seen": 250432, |
| "step": 800 |
| }, |
| { |
| "epoch": 8.944444444444445, |
| "grad_norm": 0.040147844702005386, |
| "learning_rate": 3.382326411784672e-05, |
| "loss": 0.0276, |
| "num_input_tokens_seen": 252064, |
| "step": 805 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.014303365722298622, |
| "learning_rate": 3.359604506047403e-05, |
| "loss": 0.0195, |
| "num_input_tokens_seen": 253632, |
| "step": 810 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.06076971814036369, |
| "eval_runtime": 0.5198, |
| "eval_samples_per_second": 76.957, |
| "eval_steps_per_second": 19.239, |
| "num_input_tokens_seen": 253632, |
| "step": 810 |
| }, |
| { |
| "epoch": 9.055555555555555, |
| "grad_norm": 0.2893994450569153, |
| "learning_rate": 3.336801782885712e-05, |
| "loss": 0.1298, |
| "num_input_tokens_seen": 255232, |
| "step": 815 |
| }, |
| { |
| "epoch": 9.11111111111111, |
| "grad_norm": 0.035851139575242996, |
| "learning_rate": 3.313920386142892e-05, |
| "loss": 0.0098, |
| "num_input_tokens_seen": 256800, |
| "step": 820 |
| }, |
| { |
| "epoch": 9.166666666666666, |
| "grad_norm": 0.010133305564522743, |
| "learning_rate": 3.290962467058891e-05, |
| "loss": 0.1042, |
| "num_input_tokens_seen": 258368, |
| "step": 825 |
| }, |
| { |
| "epoch": 9.222222222222221, |
| "grad_norm": 0.06425736844539642, |
| "learning_rate": 3.267930184068057e-05, |
| "loss": 0.0088, |
| "num_input_tokens_seen": 259872, |
| "step": 830 |
| }, |
| { |
| "epoch": 9.277777777777779, |
| "grad_norm": 0.11569812148809433, |
| "learning_rate": 3.244825702596205e-05, |
| "loss": 0.0193, |
| "num_input_tokens_seen": 261376, |
| "step": 835 |
| }, |
| { |
| "epoch": 9.333333333333334, |
| "grad_norm": 0.671159029006958, |
| "learning_rate": 3.2216511948570374e-05, |
| "loss": 0.0403, |
| "num_input_tokens_seen": 262944, |
| "step": 840 |
| }, |
| { |
| "epoch": 9.38888888888889, |
| "grad_norm": 0.11181628704071045, |
| "learning_rate": 3.198408839647911e-05, |
| "loss": 0.0874, |
| "num_input_tokens_seen": 264544, |
| "step": 845 |
| }, |
| { |
| "epoch": 9.444444444444445, |
| "grad_norm": 0.47002896666526794, |
| "learning_rate": 3.1751008221450025e-05, |
| "loss": 0.0231, |
| "num_input_tokens_seen": 266080, |
| "step": 850 |
| }, |
| { |
| "epoch": 9.5, |
| "grad_norm": 0.45572900772094727, |
| "learning_rate": 3.151729333697854e-05, |
| "loss": 0.0398, |
| "num_input_tokens_seen": 267680, |
| "step": 855 |
| }, |
| { |
| "epoch": 9.555555555555555, |
| "grad_norm": 1.4050266742706299, |
| "learning_rate": 3.1282965716233594e-05, |
| "loss": 0.1802, |
| "num_input_tokens_seen": 269280, |
| "step": 860 |
| }, |
| { |
| "epoch": 9.61111111111111, |
| "grad_norm": 0.6737051010131836, |
| "learning_rate": 3.104804738999169e-05, |
| "loss": 0.032, |
| "num_input_tokens_seen": 270912, |
| "step": 865 |
| }, |
| { |
| "epoch": 9.666666666666666, |
| "grad_norm": 0.06566260010004044, |
| "learning_rate": 3.0812560444565745e-05, |
| "loss": 0.0392, |
| "num_input_tokens_seen": 272512, |
| "step": 870 |
| }, |
| { |
| "epoch": 9.722222222222221, |
| "grad_norm": 0.9122573137283325, |
| "learning_rate": 3.057652701972848e-05, |
| "loss": 0.0411, |
| "num_input_tokens_seen": 274048, |
| "step": 875 |
| }, |
| { |
| "epoch": 9.777777777777779, |
| "grad_norm": 1.3042923212051392, |
| "learning_rate": 3.0339969306631005e-05, |
| "loss": 0.0619, |
| "num_input_tokens_seen": 275648, |
| "step": 880 |
| }, |
| { |
| "epoch": 9.833333333333334, |
| "grad_norm": 0.04545683041214943, |
| "learning_rate": 3.0102909545716396e-05, |
| "loss": 0.0641, |
| "num_input_tokens_seen": 277248, |
| "step": 885 |
| }, |
| { |
| "epoch": 9.88888888888889, |
| "grad_norm": 0.19024275243282318, |
| "learning_rate": 2.9865370024628775e-05, |
| "loss": 0.036, |
| "num_input_tokens_seen": 278816, |
| "step": 890 |
| }, |
| { |
| "epoch": 9.944444444444445, |
| "grad_norm": 0.047417499125003815, |
| "learning_rate": 2.9627373076117863e-05, |
| "loss": 0.0168, |
| "num_input_tokens_seen": 280416, |
| "step": 895 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.0708514004945755, |
| "learning_rate": 2.9388941075939334e-05, |
| "loss": 0.0328, |
| "num_input_tokens_seen": 281984, |
| "step": 900 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.06215012073516846, |
| "eval_runtime": 0.517, |
| "eval_samples_per_second": 77.368, |
| "eval_steps_per_second": 19.342, |
| "num_input_tokens_seen": 281984, |
| "step": 900 |
| }, |
| { |
| "epoch": 10.055555555555555, |
| "grad_norm": 1.1088037490844727, |
| "learning_rate": 2.9150096440751107e-05, |
| "loss": 0.1483, |
| "num_input_tokens_seen": 283552, |
| "step": 905 |
| }, |
| { |
| "epoch": 10.11111111111111, |
| "grad_norm": 0.13920870423316956, |
| "learning_rate": 2.8910861626005776e-05, |
| "loss": 0.0159, |
| "num_input_tokens_seen": 285120, |
| "step": 910 |
| }, |
| { |
| "epoch": 10.166666666666666, |
| "grad_norm": 0.1359255462884903, |
| "learning_rate": 2.8671259123839472e-05, |
| "loss": 0.0437, |
| "num_input_tokens_seen": 286720, |
| "step": 915 |
| }, |
| { |
| "epoch": 10.222222222222221, |
| "grad_norm": 0.1851315051317215, |
| "learning_rate": 2.843131146095719e-05, |
| "loss": 0.0302, |
| "num_input_tokens_seen": 288288, |
| "step": 920 |
| }, |
| { |
| "epoch": 10.277777777777779, |
| "grad_norm": 0.017424006015062332, |
| "learning_rate": 2.8191041196514873e-05, |
| "loss": 0.0206, |
| "num_input_tokens_seen": 289856, |
| "step": 925 |
| }, |
| { |
| "epoch": 10.333333333333334, |
| "grad_norm": 1.307128667831421, |
| "learning_rate": 2.795047091999849e-05, |
| "loss": 0.1355, |
| "num_input_tokens_seen": 291392, |
| "step": 930 |
| }, |
| { |
| "epoch": 10.38888888888889, |
| "grad_norm": 0.016336191445589066, |
| "learning_rate": 2.770962324910027e-05, |
| "loss": 0.0174, |
| "num_input_tokens_seen": 292864, |
| "step": 935 |
| }, |
| { |
| "epoch": 10.444444444444445, |
| "grad_norm": 0.267801433801651, |
| "learning_rate": 2.7468520827592197e-05, |
| "loss": 0.0938, |
| "num_input_tokens_seen": 294496, |
| "step": 940 |
| }, |
| { |
| "epoch": 10.5, |
| "grad_norm": 0.007512570358812809, |
| "learning_rate": 2.7227186323197162e-05, |
| "loss": 0.0801, |
| "num_input_tokens_seen": 296096, |
| "step": 945 |
| }, |
| { |
| "epoch": 10.555555555555555, |
| "grad_norm": 0.40150490403175354, |
| "learning_rate": 2.6985642425457757e-05, |
| "loss": 0.0221, |
| "num_input_tokens_seen": 297632, |
| "step": 950 |
| }, |
| { |
| "epoch": 10.61111111111111, |
| "grad_norm": 0.025159059092402458, |
| "learning_rate": 2.674391184360313e-05, |
| "loss": 0.0133, |
| "num_input_tokens_seen": 299168, |
| "step": 955 |
| }, |
| { |
| "epoch": 10.666666666666666, |
| "grad_norm": 0.008369713090360165, |
| "learning_rate": 2.650201730441392e-05, |
| "loss": 0.0809, |
| "num_input_tokens_seen": 300736, |
| "step": 960 |
| }, |
| { |
| "epoch": 10.722222222222221, |
| "grad_norm": 1.6953821182250977, |
| "learning_rate": 2.6259981550085504e-05, |
| "loss": 0.057, |
| "num_input_tokens_seen": 302304, |
| "step": 965 |
| }, |
| { |
| "epoch": 10.777777777777779, |
| "grad_norm": 0.007949888706207275, |
| "learning_rate": 2.60178273360899e-05, |
| "loss": 0.0275, |
| "num_input_tokens_seen": 303936, |
| "step": 970 |
| }, |
| { |
| "epoch": 10.833333333333334, |
| "grad_norm": 0.9999786615371704, |
| "learning_rate": 2.5775577429036345e-05, |
| "loss": 0.0349, |
| "num_input_tokens_seen": 305504, |
| "step": 975 |
| }, |
| { |
| "epoch": 10.88888888888889, |
| "grad_norm": 0.0133050000295043, |
| "learning_rate": 2.553325460453086e-05, |
| "loss": 0.0128, |
| "num_input_tokens_seen": 307040, |
| "step": 980 |
| }, |
| { |
| "epoch": 10.944444444444445, |
| "grad_norm": 0.1516413390636444, |
| "learning_rate": 2.5290881645034932e-05, |
| "loss": 0.0584, |
| "num_input_tokens_seen": 308608, |
| "step": 985 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 0.009461171925067902, |
| "learning_rate": 2.504848133772358e-05, |
| "loss": 0.0279, |
| "num_input_tokens_seen": 310176, |
| "step": 990 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.06158857420086861, |
| "eval_runtime": 0.5197, |
| "eval_samples_per_second": 76.973, |
| "eval_steps_per_second": 19.243, |
| "num_input_tokens_seen": 310176, |
| "step": 990 |
| }, |
| { |
| "epoch": 11.055555555555555, |
| "grad_norm": 1.5115296840667725, |
| "learning_rate": 2.4806076472342997e-05, |
| "loss": 0.0621, |
| "num_input_tokens_seen": 311712, |
| "step": 995 |
| }, |
| { |
| "epoch": 11.11111111111111, |
| "grad_norm": 0.05599701404571533, |
| "learning_rate": 2.4563689839067913e-05, |
| "loss": 0.0141, |
| "num_input_tokens_seen": 313280, |
| "step": 1000 |
| }, |
| { |
| "epoch": 11.166666666666666, |
| "grad_norm": 0.10229451209306717, |
| "learning_rate": 2.432134422635893e-05, |
| "loss": 0.0907, |
| "num_input_tokens_seen": 314816, |
| "step": 1005 |
| }, |
| { |
| "epoch": 11.222222222222221, |
| "grad_norm": 0.2486252337694168, |
| "learning_rate": 2.4079062418820002e-05, |
| "loss": 0.015, |
| "num_input_tokens_seen": 316384, |
| "step": 1010 |
| }, |
| { |
| "epoch": 11.277777777777779, |
| "grad_norm": 0.03698575124144554, |
| "learning_rate": 2.3836867195056335e-05, |
| "loss": 0.0709, |
| "num_input_tokens_seen": 317984, |
| "step": 1015 |
| }, |
| { |
| "epoch": 11.333333333333334, |
| "grad_norm": 0.07409622520208359, |
| "learning_rate": 2.3594781325532784e-05, |
| "loss": 0.0857, |
| "num_input_tokens_seen": 319552, |
| "step": 1020 |
| }, |
| { |
| "epoch": 11.38888888888889, |
| "grad_norm": 0.5309990644454956, |
| "learning_rate": 2.3352827570433036e-05, |
| "loss": 0.0184, |
| "num_input_tokens_seen": 321184, |
| "step": 1025 |
| }, |
| { |
| "epoch": 11.444444444444445, |
| "grad_norm": 0.579908013343811, |
| "learning_rate": 2.3111028677519804e-05, |
| "loss": 0.0399, |
| "num_input_tokens_seen": 322688, |
| "step": 1030 |
| }, |
| { |
| "epoch": 11.5, |
| "grad_norm": 0.022151276469230652, |
| "learning_rate": 2.2869407379996088e-05, |
| "loss": 0.1395, |
| "num_input_tokens_seen": 324224, |
| "step": 1035 |
| }, |
| { |
| "epoch": 11.555555555555555, |
| "grad_norm": 1.0108978748321533, |
| "learning_rate": 2.2627986394367938e-05, |
| "loss": 0.0416, |
| "num_input_tokens_seen": 325760, |
| "step": 1040 |
| }, |
| { |
| "epoch": 11.61111111111111, |
| "grad_norm": 1.5363922119140625, |
| "learning_rate": 2.238678841830867e-05, |
| "loss": 0.0488, |
| "num_input_tokens_seen": 327264, |
| "step": 1045 |
| }, |
| { |
| "epoch": 11.666666666666666, |
| "grad_norm": 0.5866866111755371, |
| "learning_rate": 2.2145836128524902e-05, |
| "loss": 0.0255, |
| "num_input_tokens_seen": 328832, |
| "step": 1050 |
| }, |
| { |
| "epoch": 11.722222222222221, |
| "grad_norm": 0.2689912021160126, |
| "learning_rate": 2.1905152178624595e-05, |
| "loss": 0.0301, |
| "num_input_tokens_seen": 330464, |
| "step": 1055 |
| }, |
| { |
| "epoch": 11.777777777777779, |
| "grad_norm": 0.5232972502708435, |
| "learning_rate": 2.1664759196987182e-05, |
| "loss": 0.0164, |
| "num_input_tokens_seen": 332064, |
| "step": 1060 |
| }, |
| { |
| "epoch": 11.833333333333334, |
| "grad_norm": 0.07716183364391327, |
| "learning_rate": 2.1424679784636144e-05, |
| "loss": 0.0351, |
| "num_input_tokens_seen": 333664, |
| "step": 1065 |
| }, |
| { |
| "epoch": 11.88888888888889, |
| "grad_norm": 0.031836166977882385, |
| "learning_rate": 2.118493651311413e-05, |
| "loss": 0.063, |
| "num_input_tokens_seen": 335232, |
| "step": 1070 |
| }, |
| { |
| "epoch": 11.944444444444445, |
| "grad_norm": 0.04803520813584328, |
| "learning_rate": 2.0945551922360818e-05, |
| "loss": 0.0262, |
| "num_input_tokens_seen": 336800, |
| "step": 1075 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 1.2660475969314575, |
| "learning_rate": 2.070654851859383e-05, |
| "loss": 0.0731, |
| "num_input_tokens_seen": 338400, |
| "step": 1080 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.05893953889608383, |
| "eval_runtime": 0.5187, |
| "eval_samples_per_second": 77.115, |
| "eval_steps_per_second": 19.279, |
| "num_input_tokens_seen": 338400, |
| "step": 1080 |
| }, |
| { |
| "epoch": 12.055555555555555, |
| "grad_norm": 0.30764204263687134, |
| "learning_rate": 2.0467948772192713e-05, |
| "loss": 0.1018, |
| "num_input_tokens_seen": 339968, |
| "step": 1085 |
| }, |
| { |
| "epoch": 12.11111111111111, |
| "grad_norm": 0.33647072315216064, |
| "learning_rate": 2.022977511558638e-05, |
| "loss": 0.0977, |
| "num_input_tokens_seen": 341536, |
| "step": 1090 |
| }, |
| { |
| "epoch": 12.166666666666666, |
| "grad_norm": 0.13600827753543854, |
| "learning_rate": 1.9992049941144066e-05, |
| "loss": 0.01, |
| "num_input_tokens_seen": 343104, |
| "step": 1095 |
| }, |
| { |
| "epoch": 12.222222222222221, |
| "grad_norm": 0.48333939909935, |
| "learning_rate": 1.9754795599070068e-05, |
| "loss": 0.0303, |
| "num_input_tokens_seen": 344640, |
| "step": 1100 |
| }, |
| { |
| "epoch": 12.277777777777779, |
| "grad_norm": 0.03402300924062729, |
| "learning_rate": 1.9518034395302414e-05, |
| "loss": 0.1015, |
| "num_input_tokens_seen": 346272, |
| "step": 1105 |
| }, |
| { |
| "epoch": 12.333333333333334, |
| "grad_norm": 0.15194876492023468, |
| "learning_rate": 1.9281788589415804e-05, |
| "loss": 0.0407, |
| "num_input_tokens_seen": 347808, |
| "step": 1110 |
| }, |
| { |
| "epoch": 12.38888888888889, |
| "grad_norm": 0.19185632467269897, |
| "learning_rate": 1.9046080392528735e-05, |
| "loss": 0.0237, |
| "num_input_tokens_seen": 349344, |
| "step": 1115 |
| }, |
| { |
| "epoch": 12.444444444444445, |
| "grad_norm": 0.250827431678772, |
| "learning_rate": 1.8810931965215356e-05, |
| "loss": 0.0122, |
| "num_input_tokens_seen": 350912, |
| "step": 1120 |
| }, |
| { |
| "epoch": 12.5, |
| "grad_norm": 0.19316622614860535, |
| "learning_rate": 1.857636541542195e-05, |
| "loss": 0.0727, |
| "num_input_tokens_seen": 352480, |
| "step": 1125 |
| }, |
| { |
| "epoch": 12.555555555555555, |
| "grad_norm": 0.9355464577674866, |
| "learning_rate": 1.8342402796388445e-05, |
| "loss": 0.0253, |
| "num_input_tokens_seen": 354048, |
| "step": 1130 |
| }, |
| { |
| "epoch": 12.61111111111111, |
| "grad_norm": 0.007416177541017532, |
| "learning_rate": 1.8109066104575023e-05, |
| "loss": 0.0045, |
| "num_input_tokens_seen": 355648, |
| "step": 1135 |
| }, |
| { |
| "epoch": 12.666666666666666, |
| "grad_norm": 0.9557670950889587, |
| "learning_rate": 1.7876377277594053e-05, |
| "loss": 0.033, |
| "num_input_tokens_seen": 357248, |
| "step": 1140 |
| }, |
| { |
| "epoch": 12.722222222222221, |
| "grad_norm": 0.011720170266926289, |
| "learning_rate": 1.764435819214762e-05, |
| "loss": 0.0273, |
| "num_input_tokens_seen": 358752, |
| "step": 1145 |
| }, |
| { |
| "epoch": 12.777777777777779, |
| "grad_norm": 0.2780408561229706, |
| "learning_rate": 1.7413030661970742e-05, |
| "loss": 0.0187, |
| "num_input_tokens_seen": 360288, |
| "step": 1150 |
| }, |
| { |
| "epoch": 12.833333333333334, |
| "grad_norm": 0.01299345213919878, |
| "learning_rate": 1.7182416435780454e-05, |
| "loss": 0.0163, |
| "num_input_tokens_seen": 361920, |
| "step": 1155 |
| }, |
| { |
| "epoch": 12.88888888888889, |
| "grad_norm": 0.010123813524842262, |
| "learning_rate": 1.695253719523115e-05, |
| "loss": 0.146, |
| "num_input_tokens_seen": 363520, |
| "step": 1160 |
| }, |
| { |
| "epoch": 12.944444444444445, |
| "grad_norm": 1.4064712524414062, |
| "learning_rate": 1.672341455287605e-05, |
| "loss": 0.0515, |
| "num_input_tokens_seen": 365088, |
| "step": 1165 |
| }, |
| { |
| "epoch": 13.0, |
| "grad_norm": 0.013315699063241482, |
| "learning_rate": 1.649507005013532e-05, |
| "loss": 0.0441, |
| "num_input_tokens_seen": 366688, |
| "step": 1170 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 0.05899040028452873, |
| "eval_runtime": 0.5203, |
| "eval_samples_per_second": 76.873, |
| "eval_steps_per_second": 19.218, |
| "num_input_tokens_seen": 366688, |
| "step": 1170 |
| }, |
| { |
| "epoch": 13.055555555555555, |
| "grad_norm": 1.644558310508728, |
| "learning_rate": 1.6267525155270773e-05, |
| "loss": 0.0723, |
| "num_input_tokens_seen": 368192, |
| "step": 1175 |
| }, |
| { |
| "epoch": 13.11111111111111, |
| "grad_norm": 0.33990561962127686, |
| "learning_rate": 1.6040801261367493e-05, |
| "loss": 0.1022, |
| "num_input_tokens_seen": 369792, |
| "step": 1180 |
| }, |
| { |
| "epoch": 13.166666666666666, |
| "grad_norm": 0.10223418474197388, |
| "learning_rate": 1.5814919684322545e-05, |
| "loss": 0.0832, |
| "num_input_tokens_seen": 371360, |
| "step": 1185 |
| }, |
| { |
| "epoch": 13.222222222222221, |
| "grad_norm": 0.014776123687624931, |
| "learning_rate": 1.5589901660840896e-05, |
| "loss": 0.0552, |
| "num_input_tokens_seen": 372928, |
| "step": 1190 |
| }, |
| { |
| "epoch": 13.277777777777779, |
| "grad_norm": 0.13640986382961273, |
| "learning_rate": 1.5365768346438797e-05, |
| "loss": 0.0299, |
| "num_input_tokens_seen": 374528, |
| "step": 1195 |
| }, |
| { |
| "epoch": 13.333333333333334, |
| "grad_norm": 0.2882007956504822, |
| "learning_rate": 1.5142540813454836e-05, |
| "loss": 0.0198, |
| "num_input_tokens_seen": 376000, |
| "step": 1200 |
| }, |
| { |
| "epoch": 13.38888888888889, |
| "grad_norm": 0.2431965470314026, |
| "learning_rate": 1.4920240049068748e-05, |
| "loss": 0.0179, |
| "num_input_tokens_seen": 377600, |
| "step": 1205 |
| }, |
| { |
| "epoch": 13.444444444444445, |
| "grad_norm": 0.20751990377902985, |
| "learning_rate": 1.4698886953328292e-05, |
| "loss": 0.0664, |
| "num_input_tokens_seen": 379200, |
| "step": 1210 |
| }, |
| { |
| "epoch": 13.5, |
| "grad_norm": 0.022774390876293182, |
| "learning_rate": 1.4478502337184274e-05, |
| "loss": 0.0527, |
| "num_input_tokens_seen": 380704, |
| "step": 1215 |
| }, |
| { |
| "epoch": 13.555555555555555, |
| "grad_norm": 0.11283931881189346, |
| "learning_rate": 1.4259106920533955e-05, |
| "loss": 0.0598, |
| "num_input_tokens_seen": 382272, |
| "step": 1220 |
| }, |
| { |
| "epoch": 13.61111111111111, |
| "grad_norm": 0.818737268447876, |
| "learning_rate": 1.4040721330273062e-05, |
| "loss": 0.0219, |
| "num_input_tokens_seen": 383776, |
| "step": 1225 |
| }, |
| { |
| "epoch": 13.666666666666666, |
| "grad_norm": 0.33635279536247253, |
| "learning_rate": 1.3823366098356487e-05, |
| "loss": 0.0543, |
| "num_input_tokens_seen": 385344, |
| "step": 1230 |
| }, |
| { |
| "epoch": 13.722222222222221, |
| "grad_norm": 0.5322341322898865, |
| "learning_rate": 1.3607061659867892e-05, |
| "loss": 0.015, |
| "num_input_tokens_seen": 386912, |
| "step": 1235 |
| }, |
| { |
| "epoch": 13.777777777777779, |
| "grad_norm": 0.007620496675372124, |
| "learning_rate": 1.3391828351098578e-05, |
| "loss": 0.0776, |
| "num_input_tokens_seen": 388480, |
| "step": 1240 |
| }, |
| { |
| "epoch": 13.833333333333334, |
| "grad_norm": 0.013653988018631935, |
| "learning_rate": 1.3177686407635417e-05, |
| "loss": 0.0359, |
| "num_input_tokens_seen": 390048, |
| "step": 1245 |
| }, |
| { |
| "epoch": 13.88888888888889, |
| "grad_norm": 0.031345516443252563, |
| "learning_rate": 1.29646559624584e-05, |
| "loss": 0.0188, |
| "num_input_tokens_seen": 391584, |
| "step": 1250 |
| }, |
| { |
| "epoch": 13.944444444444445, |
| "grad_norm": 0.10659394413232803, |
| "learning_rate": 1.2752757044047827e-05, |
| "loss": 0.0245, |
| "num_input_tokens_seen": 393184, |
| "step": 1255 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 0.27042534947395325, |
| "learning_rate": 1.2542009574501246e-05, |
| "loss": 0.0081, |
| "num_input_tokens_seen": 394752, |
| "step": 1260 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.060102712363004684, |
| "eval_runtime": 0.5256, |
| "eval_samples_per_second": 76.098, |
| "eval_steps_per_second": 19.024, |
| "num_input_tokens_seen": 394752, |
| "step": 1260 |
| }, |
| { |
| "epoch": 14.055555555555555, |
| "grad_norm": 0.10951791703701019, |
| "learning_rate": 1.2332433367660442e-05, |
| "loss": 0.0423, |
| "num_input_tokens_seen": 396320, |
| "step": 1265 |
| }, |
| { |
| "epoch": 14.11111111111111, |
| "grad_norm": 0.028836172074079514, |
| "learning_rate": 1.2124048127248644e-05, |
| "loss": 0.0312, |
| "num_input_tokens_seen": 397920, |
| "step": 1270 |
| }, |
| { |
| "epoch": 14.166666666666666, |
| "grad_norm": 0.01687157340347767, |
| "learning_rate": 1.1916873445017982e-05, |
| "loss": 0.0153, |
| "num_input_tokens_seen": 399552, |
| "step": 1275 |
| }, |
| { |
| "epoch": 14.222222222222221, |
| "grad_norm": 0.02062399312853813, |
| "learning_rate": 1.1710928798907556e-05, |
| "loss": 0.0118, |
| "num_input_tokens_seen": 401120, |
| "step": 1280 |
| }, |
| { |
| "epoch": 14.277777777777779, |
| "grad_norm": 1.0031055212020874, |
| "learning_rate": 1.1506233551212186e-05, |
| "loss": 0.0415, |
| "num_input_tokens_seen": 402720, |
| "step": 1285 |
| }, |
| { |
| "epoch": 14.333333333333334, |
| "grad_norm": 0.011867760680615902, |
| "learning_rate": 1.1302806946762004e-05, |
| "loss": 0.0264, |
| "num_input_tokens_seen": 404320, |
| "step": 1290 |
| }, |
| { |
| "epoch": 14.38888888888889, |
| "grad_norm": 0.024303486570715904, |
| "learning_rate": 1.1100668111113166e-05, |
| "loss": 0.0123, |
| "num_input_tokens_seen": 405824, |
| "step": 1295 |
| }, |
| { |
| "epoch": 14.444444444444445, |
| "grad_norm": 1.8085826635360718, |
| "learning_rate": 1.0899836048749645e-05, |
| "loss": 0.0914, |
| "num_input_tokens_seen": 407360, |
| "step": 1300 |
| }, |
| { |
| "epoch": 14.5, |
| "grad_norm": 1.3068459033966064, |
| "learning_rate": 1.0700329641296541e-05, |
| "loss": 0.1156, |
| "num_input_tokens_seen": 408928, |
| "step": 1305 |
| }, |
| { |
| "epoch": 14.555555555555555, |
| "grad_norm": 0.3057030141353607, |
| "learning_rate": 1.0502167645744895e-05, |
| "loss": 0.0315, |
| "num_input_tokens_seen": 410496, |
| "step": 1310 |
| }, |
| { |
| "epoch": 14.61111111111111, |
| "grad_norm": 0.23634877800941467, |
| "learning_rate": 1.0305368692688174e-05, |
| "loss": 0.0124, |
| "num_input_tokens_seen": 412032, |
| "step": 1315 |
| }, |
| { |
| "epoch": 14.666666666666666, |
| "grad_norm": 0.15040916204452515, |
| "learning_rate": 1.01099512845707e-05, |
| "loss": 0.0142, |
| "num_input_tokens_seen": 413536, |
| "step": 1320 |
| }, |
| { |
| "epoch": 14.722222222222221, |
| "grad_norm": 0.03269388899207115, |
| "learning_rate": 9.91593379394811e-06, |
| "loss": 0.0331, |
| "num_input_tokens_seen": 415136, |
| "step": 1325 |
| }, |
| { |
| "epoch": 14.777777777777779, |
| "grad_norm": 0.396207332611084, |
| "learning_rate": 9.723334461760006e-06, |
| "loss": 0.1666, |
| "num_input_tokens_seen": 416704, |
| "step": 1330 |
| }, |
| { |
| "epoch": 14.833333333333334, |
| "grad_norm": 0.46826860308647156, |
| "learning_rate": 9.532171395615036e-06, |
| "loss": 0.0218, |
| "num_input_tokens_seen": 418272, |
| "step": 1335 |
| }, |
| { |
| "epoch": 14.88888888888889, |
| "grad_norm": 0.05246613547205925, |
| "learning_rate": 9.342462568088416e-06, |
| "loss": 0.0856, |
| "num_input_tokens_seen": 419808, |
| "step": 1340 |
| }, |
| { |
| "epoch": 14.944444444444445, |
| "grad_norm": 0.008573368191719055, |
| "learning_rate": 9.154225815032242e-06, |
| "loss": 0.0261, |
| "num_input_tokens_seen": 421344, |
| "step": 1345 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 0.03231954202055931, |
| "learning_rate": 8.967478833898612e-06, |
| "loss": 0.0287, |
| "num_input_tokens_seen": 422912, |
| "step": 1350 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 0.05984850972890854, |
| "eval_runtime": 0.517, |
| "eval_samples_per_second": 77.37, |
| "eval_steps_per_second": 19.343, |
| "num_input_tokens_seen": 422912, |
| "step": 1350 |
| }, |
| { |
| "epoch": 15.055555555555555, |
| "grad_norm": 0.8410363793373108, |
| "learning_rate": 8.78223918207575e-06, |
| "loss": 0.0211, |
| "num_input_tokens_seen": 424480, |
| "step": 1355 |
| }, |
| { |
| "epoch": 15.11111111111111, |
| "grad_norm": 0.8376926183700562, |
| "learning_rate": 8.598524275237322e-06, |
| "loss": 0.0395, |
| "num_input_tokens_seen": 426048, |
| "step": 1360 |
| }, |
| { |
| "epoch": 15.166666666666666, |
| "grad_norm": 0.28883492946624756, |
| "learning_rate": 8.41635138570507e-06, |
| "loss": 0.0174, |
| "num_input_tokens_seen": 427648, |
| "step": 1365 |
| }, |
| { |
| "epoch": 15.222222222222221, |
| "grad_norm": 2.5785083770751953, |
| "learning_rate": 8.235737640824908e-06, |
| "loss": 0.1227, |
| "num_input_tokens_seen": 429216, |
| "step": 1370 |
| }, |
| { |
| "epoch": 15.277777777777779, |
| "grad_norm": 0.7716183066368103, |
| "learning_rate": 8.056700021356694e-06, |
| "loss": 0.0267, |
| "num_input_tokens_seen": 430720, |
| "step": 1375 |
| }, |
| { |
| "epoch": 15.333333333333334, |
| "grad_norm": 0.13386765122413635, |
| "learning_rate": 7.879255359877705e-06, |
| "loss": 0.0577, |
| "num_input_tokens_seen": 432320, |
| "step": 1380 |
| }, |
| { |
| "epoch": 15.38888888888889, |
| "grad_norm": 0.18355993926525116, |
| "learning_rate": 7.703420339200101e-06, |
| "loss": 0.0522, |
| "num_input_tokens_seen": 433888, |
| "step": 1385 |
| }, |
| { |
| "epoch": 15.444444444444445, |
| "grad_norm": 0.21487367153167725, |
| "learning_rate": 7.529211490802498e-06, |
| "loss": 0.0453, |
| "num_input_tokens_seen": 435456, |
| "step": 1390 |
| }, |
| { |
| "epoch": 15.5, |
| "grad_norm": 0.4584398567676544, |
| "learning_rate": 7.3566451932756744e-06, |
| "loss": 0.0124, |
| "num_input_tokens_seen": 437024, |
| "step": 1395 |
| }, |
| { |
| "epoch": 15.555555555555555, |
| "grad_norm": 0.16662505269050598, |
| "learning_rate": 7.185737670782727e-06, |
| "loss": 0.0052, |
| "num_input_tokens_seen": 438528, |
| "step": 1400 |
| }, |
| { |
| "epoch": 15.61111111111111, |
| "grad_norm": 0.3519705832004547, |
| "learning_rate": 7.016504991533726e-06, |
| "loss": 0.0061, |
| "num_input_tokens_seen": 440096, |
| "step": 1405 |
| }, |
| { |
| "epoch": 15.666666666666666, |
| "grad_norm": 0.2552229166030884, |
| "learning_rate": 6.848963066275027e-06, |
| "loss": 0.021, |
| "num_input_tokens_seen": 441632, |
| "step": 1410 |
| }, |
| { |
| "epoch": 15.722222222222221, |
| "grad_norm": 0.3842417895793915, |
| "learning_rate": 6.683127646793411e-06, |
| "loss": 0.0763, |
| "num_input_tokens_seen": 443136, |
| "step": 1415 |
| }, |
| { |
| "epoch": 15.777777777777779, |
| "grad_norm": 0.46216481924057007, |
| "learning_rate": 6.519014324435102e-06, |
| "loss": 0.0571, |
| "num_input_tokens_seen": 444736, |
| "step": 1420 |
| }, |
| { |
| "epoch": 15.833333333333334, |
| "grad_norm": 0.012727758847177029, |
| "learning_rate": 6.356638528639955e-06, |
| "loss": 0.009, |
| "num_input_tokens_seen": 446336, |
| "step": 1425 |
| }, |
| { |
| "epoch": 15.88888888888889, |
| "grad_norm": 0.027039675042033195, |
| "learning_rate": 6.196015525490825e-06, |
| "loss": 0.1455, |
| "num_input_tokens_seen": 447936, |
| "step": 1430 |
| }, |
| { |
| "epoch": 15.944444444444445, |
| "grad_norm": 1.3422183990478516, |
| "learning_rate": 6.037160416278278e-06, |
| "loss": 0.0474, |
| "num_input_tokens_seen": 449440, |
| "step": 1435 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 0.03860368952155113, |
| "learning_rate": 5.880088136080814e-06, |
| "loss": 0.0147, |
| "num_input_tokens_seen": 451008, |
| "step": 1440 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 0.05932573229074478, |
| "eval_runtime": 0.52, |
| "eval_samples_per_second": 76.927, |
| "eval_steps_per_second": 19.232, |
| "num_input_tokens_seen": 451008, |
| "step": 1440 |
| }, |
| { |
| "epoch": 16.055555555555557, |
| "grad_norm": 0.550543487071991, |
| "learning_rate": 5.724813452360736e-06, |
| "loss": 0.0636, |
| "num_input_tokens_seen": 452576, |
| "step": 1445 |
| }, |
| { |
| "epoch": 16.11111111111111, |
| "grad_norm": 1.2353315353393555, |
| "learning_rate": 5.571350963575728e-06, |
| "loss": 0.0968, |
| "num_input_tokens_seen": 454112, |
| "step": 1450 |
| }, |
| { |
| "epoch": 16.166666666666668, |
| "grad_norm": 0.019102858379483223, |
| "learning_rate": 5.4197150978063965e-06, |
| "loss": 0.014, |
| "num_input_tokens_seen": 455680, |
| "step": 1455 |
| }, |
| { |
| "epoch": 16.22222222222222, |
| "grad_norm": 0.14581513404846191, |
| "learning_rate": 5.269920111399732e-06, |
| "loss": 0.0105, |
| "num_input_tokens_seen": 457280, |
| "step": 1460 |
| }, |
| { |
| "epoch": 16.27777777777778, |
| "grad_norm": 0.0162353478372097, |
| "learning_rate": 5.121980087628803e-06, |
| "loss": 0.0084, |
| "num_input_tokens_seen": 458848, |
| "step": 1465 |
| }, |
| { |
| "epoch": 16.333333333333332, |
| "grad_norm": 0.17371828854084015, |
| "learning_rate": 4.975908935368701e-06, |
| "loss": 0.0291, |
| "num_input_tokens_seen": 460416, |
| "step": 1470 |
| }, |
| { |
| "epoch": 16.38888888888889, |
| "grad_norm": 0.4158192276954651, |
| "learning_rate": 4.831720387788827e-06, |
| "loss": 0.0344, |
| "num_input_tokens_seen": 462048, |
| "step": 1475 |
| }, |
| { |
| "epoch": 16.444444444444443, |
| "grad_norm": 0.0122003685683012, |
| "learning_rate": 4.689428001061774e-06, |
| "loss": 0.0166, |
| "num_input_tokens_seen": 463584, |
| "step": 1480 |
| }, |
| { |
| "epoch": 16.5, |
| "grad_norm": 0.004614563658833504, |
| "learning_rate": 4.549045153088813e-06, |
| "loss": 0.1125, |
| "num_input_tokens_seen": 465152, |
| "step": 1485 |
| }, |
| { |
| "epoch": 16.555555555555557, |
| "grad_norm": 0.48291656374931335, |
| "learning_rate": 4.410585042242124e-06, |
| "loss": 0.0491, |
| "num_input_tokens_seen": 466720, |
| "step": 1490 |
| }, |
| { |
| "epoch": 16.61111111111111, |
| "grad_norm": 0.3229008913040161, |
| "learning_rate": 4.274060686123959e-06, |
| "loss": 0.018, |
| "num_input_tokens_seen": 468256, |
| "step": 1495 |
| }, |
| { |
| "epoch": 16.666666666666668, |
| "grad_norm": 0.01832473650574684, |
| "learning_rate": 4.1394849203427284e-06, |
| "loss": 0.0542, |
| "num_input_tokens_seen": 469792, |
| "step": 1500 |
| }, |
| { |
| "epoch": 16.72222222222222, |
| "grad_norm": 0.07098887860774994, |
| "learning_rate": 4.006870397306256e-06, |
| "loss": 0.0182, |
| "num_input_tokens_seen": 471360, |
| "step": 1505 |
| }, |
| { |
| "epoch": 16.77777777777778, |
| "grad_norm": 0.02056993544101715, |
| "learning_rate": 3.876229585032245e-06, |
| "loss": 0.0149, |
| "num_input_tokens_seen": 472896, |
| "step": 1510 |
| }, |
| { |
| "epoch": 16.833333333333332, |
| "grad_norm": 0.3502405881881714, |
| "learning_rate": 3.7475747659760502e-06, |
| "loss": 0.0944, |
| "num_input_tokens_seen": 474496, |
| "step": 1515 |
| }, |
| { |
| "epoch": 16.88888888888889, |
| "grad_norm": 0.21067650616168976, |
| "learning_rate": 3.6209180358759394e-06, |
| "loss": 0.0155, |
| "num_input_tokens_seen": 476064, |
| "step": 1520 |
| }, |
| { |
| "epoch": 16.944444444444443, |
| "grad_norm": 0.05252571403980255, |
| "learning_rate": 3.4962713026158694e-06, |
| "loss": 0.0264, |
| "num_input_tokens_seen": 477600, |
| "step": 1525 |
| }, |
| { |
| "epoch": 17.0, |
| "grad_norm": 0.008412295952439308, |
| "learning_rate": 3.373646285105958e-06, |
| "loss": 0.0935, |
| "num_input_tokens_seen": 479104, |
| "step": 1530 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 0.05843701213598251, |
| "eval_runtime": 0.5198, |
| "eval_samples_per_second": 76.957, |
| "eval_steps_per_second": 19.239, |
| "num_input_tokens_seen": 479104, |
| "step": 1530 |
| }, |
| { |
| "epoch": 17.055555555555557, |
| "grad_norm": 0.21587851643562317, |
| "learning_rate": 3.2530545121807145e-06, |
| "loss": 0.0435, |
| "num_input_tokens_seen": 480736, |
| "step": 1535 |
| }, |
| { |
| "epoch": 17.11111111111111, |
| "grad_norm": 0.3278423547744751, |
| "learning_rate": 3.1345073215151066e-06, |
| "loss": 0.0471, |
| "num_input_tokens_seen": 482304, |
| "step": 1540 |
| }, |
| { |
| "epoch": 17.166666666666668, |
| "grad_norm": 0.10238057374954224, |
| "learning_rate": 3.0180158585586397e-06, |
| "loss": 0.0383, |
| "num_input_tokens_seen": 483872, |
| "step": 1545 |
| }, |
| { |
| "epoch": 17.22222222222222, |
| "grad_norm": 0.17296543717384338, |
| "learning_rate": 2.9035910754875136e-06, |
| "loss": 0.0238, |
| "num_input_tokens_seen": 485408, |
| "step": 1550 |
| }, |
| { |
| "epoch": 17.27777777777778, |
| "grad_norm": 0.052419859915971756, |
| "learning_rate": 2.7912437301749026e-06, |
| "loss": 0.0439, |
| "num_input_tokens_seen": 486944, |
| "step": 1555 |
| }, |
| { |
| "epoch": 17.333333333333332, |
| "grad_norm": 0.04378189891576767, |
| "learning_rate": 2.6809843851795357e-06, |
| "loss": 0.0293, |
| "num_input_tokens_seen": 488544, |
| "step": 1560 |
| }, |
| { |
| "epoch": 17.38888888888889, |
| "grad_norm": 0.1454276144504547, |
| "learning_rate": 2.57282340675267e-06, |
| "loss": 0.0335, |
| "num_input_tokens_seen": 490144, |
| "step": 1565 |
| }, |
| { |
| "epoch": 17.444444444444443, |
| "grad_norm": 0.029287101700901985, |
| "learning_rate": 2.4667709638634434e-06, |
| "loss": 0.0138, |
| "num_input_tokens_seen": 491680, |
| "step": 1570 |
| }, |
| { |
| "epoch": 17.5, |
| "grad_norm": 0.005346542689949274, |
| "learning_rate": 2.3628370272428564e-06, |
| "loss": 0.0756, |
| "num_input_tokens_seen": 493248, |
| "step": 1575 |
| }, |
| { |
| "epoch": 17.555555555555557, |
| "grad_norm": 0.03685900568962097, |
| "learning_rate": 2.2610313684463177e-06, |
| "loss": 0.0251, |
| "num_input_tokens_seen": 494816, |
| "step": 1580 |
| }, |
| { |
| "epoch": 17.61111111111111, |
| "grad_norm": 0.04156652092933655, |
| "learning_rate": 2.1613635589349756e-06, |
| "loss": 0.1015, |
| "num_input_tokens_seen": 496416, |
| "step": 1585 |
| }, |
| { |
| "epoch": 17.666666666666668, |
| "grad_norm": 0.8290051221847534, |
| "learning_rate": 2.063842969175847e-06, |
| "loss": 0.023, |
| "num_input_tokens_seen": 497952, |
| "step": 1590 |
| }, |
| { |
| "epoch": 17.72222222222222, |
| "grad_norm": 0.049550581723451614, |
| "learning_rate": 1.968478767760812e-06, |
| "loss": 0.0533, |
| "num_input_tokens_seen": 499520, |
| "step": 1595 |
| }, |
| { |
| "epoch": 17.77777777777778, |
| "grad_norm": 0.15296253561973572, |
| "learning_rate": 1.8752799205445982e-06, |
| "loss": 0.1171, |
| "num_input_tokens_seen": 501120, |
| "step": 1600 |
| }, |
| { |
| "epoch": 17.833333333333332, |
| "grad_norm": 0.030097996816039085, |
| "learning_rate": 1.784255189801895e-06, |
| "loss": 0.0103, |
| "num_input_tokens_seen": 502688, |
| "step": 1605 |
| }, |
| { |
| "epoch": 17.88888888888889, |
| "grad_norm": 0.13713747262954712, |
| "learning_rate": 1.6954131334034922e-06, |
| "loss": 0.0261, |
| "num_input_tokens_seen": 504224, |
| "step": 1610 |
| }, |
| { |
| "epoch": 17.944444444444443, |
| "grad_norm": 0.11297009140253067, |
| "learning_rate": 1.6087621040117157e-06, |
| "loss": 0.042, |
| "num_input_tokens_seen": 505824, |
| "step": 1615 |
| }, |
| { |
| "epoch": 18.0, |
| "grad_norm": 0.0667833760380745, |
| "learning_rate": 1.524310248295152e-06, |
| "loss": 0.0122, |
| "num_input_tokens_seen": 507392, |
| "step": 1620 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 0.06013888865709305, |
| "eval_runtime": 0.5215, |
| "eval_samples_per_second": 76.703, |
| "eval_steps_per_second": 19.176, |
| "num_input_tokens_seen": 507392, |
| "step": 1620 |
| }, |
| { |
| "epoch": 18.055555555555557, |
| "grad_norm": 0.12299990653991699, |
| "learning_rate": 1.4420655061626932e-06, |
| "loss": 0.0209, |
| "num_input_tokens_seen": 508928, |
| "step": 1625 |
| }, |
| { |
| "epoch": 18.11111111111111, |
| "grad_norm": 0.20416291058063507, |
| "learning_rate": 1.362035610017079e-06, |
| "loss": 0.0254, |
| "num_input_tokens_seen": 510496, |
| "step": 1630 |
| }, |
| { |
| "epoch": 18.166666666666668, |
| "grad_norm": 0.17090032994747162, |
| "learning_rate": 1.2842280840278997e-06, |
| "loss": 0.0594, |
| "num_input_tokens_seen": 512032, |
| "step": 1635 |
| }, |
| { |
| "epoch": 18.22222222222222, |
| "grad_norm": 0.1019781306385994, |
| "learning_rate": 1.2086502434241865e-06, |
| "loss": 0.0074, |
| "num_input_tokens_seen": 513504, |
| "step": 1640 |
| }, |
| { |
| "epoch": 18.27777777777778, |
| "grad_norm": 0.6727584600448608, |
| "learning_rate": 1.1353091938067023e-06, |
| "loss": 0.0281, |
| "num_input_tokens_seen": 515040, |
| "step": 1645 |
| }, |
| { |
| "epoch": 18.333333333333332, |
| "grad_norm": 0.01017342135310173, |
| "learning_rate": 1.0642118304798442e-06, |
| "loss": 0.0396, |
| "num_input_tokens_seen": 516640, |
| "step": 1650 |
| }, |
| { |
| "epoch": 18.38888888888889, |
| "grad_norm": 0.8693645000457764, |
| "learning_rate": 9.95364837803392e-07, |
| "loss": 0.0489, |
| "num_input_tokens_seen": 518208, |
| "step": 1655 |
| }, |
| { |
| "epoch": 18.444444444444443, |
| "grad_norm": 0.8891027569770813, |
| "learning_rate": 9.287746885640603e-07, |
| "loss": 0.0264, |
| "num_input_tokens_seen": 519776, |
| "step": 1660 |
| }, |
| { |
| "epoch": 18.5, |
| "grad_norm": 0.015380547381937504, |
| "learning_rate": 8.64447643366953e-07, |
| "loss": 0.0109, |
| "num_input_tokens_seen": 521344, |
| "step": 1665 |
| }, |
| { |
| "epoch": 18.555555555555557, |
| "grad_norm": 0.007733294274657965, |
| "learning_rate": 8.023897500469391e-07, |
| "loss": 0.1493, |
| "num_input_tokens_seen": 522976, |
| "step": 1670 |
| }, |
| { |
| "epoch": 18.61111111111111, |
| "grad_norm": 0.9056934714317322, |
| "learning_rate": 7.426068431000882e-07, |
| "loss": 0.0268, |
| "num_input_tokens_seen": 524544, |
| "step": 1675 |
| }, |
| { |
| "epoch": 18.666666666666668, |
| "grad_norm": 0.00778258265927434, |
| "learning_rate": 6.851045431350927e-07, |
| "loss": 0.0046, |
| "num_input_tokens_seen": 526112, |
| "step": 1680 |
| }, |
| { |
| "epoch": 18.72222222222222, |
| "grad_norm": 0.9855499267578125, |
| "learning_rate": 6.298882563448599e-07, |
| "loss": 0.041, |
| "num_input_tokens_seen": 527712, |
| "step": 1685 |
| }, |
| { |
| "epoch": 18.77777777777778, |
| "grad_norm": 1.730617642402649, |
| "learning_rate": 5.769631739982267e-07, |
| "loss": 0.0657, |
| "num_input_tokens_seen": 529280, |
| "step": 1690 |
| }, |
| { |
| "epoch": 18.833333333333332, |
| "grad_norm": 0.15165819227695465, |
| "learning_rate": 5.263342719518921e-07, |
| "loss": 0.0513, |
| "num_input_tokens_seen": 530816, |
| "step": 1695 |
| }, |
| { |
| "epoch": 18.88888888888889, |
| "grad_norm": 0.014716766774654388, |
| "learning_rate": 4.780063101826132e-07, |
| "loss": 0.0439, |
| "num_input_tokens_seen": 532448, |
| "step": 1700 |
| }, |
| { |
| "epoch": 18.944444444444443, |
| "grad_norm": 0.15044061839580536, |
| "learning_rate": 4.319838323396691e-07, |
| "loss": 0.0397, |
| "num_input_tokens_seen": 534016, |
| "step": 1705 |
| }, |
| { |
| "epoch": 19.0, |
| "grad_norm": 0.14136840403079987, |
| "learning_rate": 3.88271165317694e-07, |
| "loss": 0.0685, |
| "num_input_tokens_seen": 535584, |
| "step": 1710 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 0.06143023446202278, |
| "eval_runtime": 0.5205, |
| "eval_samples_per_second": 76.847, |
| "eval_steps_per_second": 19.212, |
| "num_input_tokens_seen": 535584, |
| "step": 1710 |
| }, |
| { |
| "epoch": 19.055555555555557, |
| "grad_norm": 0.21940721571445465, |
| "learning_rate": 3.468724188498751e-07, |
| "loss": 0.1495, |
| "num_input_tokens_seen": 537152, |
| "step": 1715 |
| }, |
| { |
| "epoch": 19.11111111111111, |
| "grad_norm": 0.17824964225292206, |
| "learning_rate": 3.077914851215585e-07, |
| "loss": 0.0176, |
| "num_input_tokens_seen": 538720, |
| "step": 1720 |
| }, |
| { |
| "epoch": 19.166666666666668, |
| "grad_norm": 0.67586749792099, |
| "learning_rate": 2.71032038404323e-07, |
| "loss": 0.0203, |
| "num_input_tokens_seen": 540256, |
| "step": 1725 |
| }, |
| { |
| "epoch": 19.22222222222222, |
| "grad_norm": 0.008334583602845669, |
| "learning_rate": 2.365975347105448e-07, |
| "loss": 0.008, |
| "num_input_tokens_seen": 541824, |
| "step": 1730 |
| }, |
| { |
| "epoch": 19.27777777777778, |
| "grad_norm": 0.030415670946240425, |
| "learning_rate": 2.0449121146845774e-07, |
| "loss": 0.0081, |
| "num_input_tokens_seen": 543424, |
| "step": 1735 |
| }, |
| { |
| "epoch": 19.333333333333332, |
| "grad_norm": 1.8074421882629395, |
| "learning_rate": 1.747160872177883e-07, |
| "loss": 0.0494, |
| "num_input_tokens_seen": 545024, |
| "step": 1740 |
| }, |
| { |
| "epoch": 19.38888888888889, |
| "grad_norm": 0.3716520071029663, |
| "learning_rate": 1.472749613259661e-07, |
| "loss": 0.0258, |
| "num_input_tokens_seen": 546560, |
| "step": 1745 |
| }, |
| { |
| "epoch": 19.444444444444443, |
| "grad_norm": 0.03234966844320297, |
| "learning_rate": 1.22170413724923e-07, |
| "loss": 0.0316, |
| "num_input_tokens_seen": 548096, |
| "step": 1750 |
| }, |
| { |
| "epoch": 19.5, |
| "grad_norm": 0.0194929838180542, |
| "learning_rate": 9.940480466855417e-08, |
| "loss": 0.0542, |
| "num_input_tokens_seen": 549664, |
| "step": 1755 |
| }, |
| { |
| "epoch": 19.555555555555557, |
| "grad_norm": 0.012016446329653263, |
| "learning_rate": 7.898027451078982e-08, |
| "loss": 0.0125, |
| "num_input_tokens_seen": 551264, |
| "step": 1760 |
| }, |
| { |
| "epoch": 19.61111111111111, |
| "grad_norm": 0.2182668149471283, |
| "learning_rate": 6.089874350439506e-08, |
| "loss": 0.0641, |
| "num_input_tokens_seen": 552800, |
| "step": 1765 |
| }, |
| { |
| "epoch": 19.666666666666668, |
| "grad_norm": 1.409957766532898, |
| "learning_rate": 4.516191162040051e-08, |
| "loss": 0.0581, |
| "num_input_tokens_seen": 554336, |
| "step": 1770 |
| }, |
| { |
| "epoch": 19.72222222222222, |
| "grad_norm": 0.10802645236253738, |
| "learning_rate": 3.177125838830786e-08, |
| "loss": 0.0233, |
| "num_input_tokens_seen": 555872, |
| "step": 1775 |
| }, |
| { |
| "epoch": 19.77777777777778, |
| "grad_norm": 0.21580937504768372, |
| "learning_rate": 2.0728042756967824e-08, |
| "loss": 0.0767, |
| "num_input_tokens_seen": 557504, |
| "step": 1780 |
| }, |
| { |
| "epoch": 19.833333333333332, |
| "grad_norm": 0.03298446908593178, |
| "learning_rate": 1.2033302976222071e-08, |
| "loss": 0.0158, |
| "num_input_tokens_seen": 559040, |
| "step": 1785 |
| }, |
| { |
| "epoch": 19.88888888888889, |
| "grad_norm": 0.00999500136822462, |
| "learning_rate": 5.687856499297928e-09, |
| "loss": 0.0513, |
| "num_input_tokens_seen": 560640, |
| "step": 1790 |
| }, |
| { |
| "epoch": 19.944444444444443, |
| "grad_norm": 1.7499030828475952, |
| "learning_rate": 1.692299905944883e-09, |
| "loss": 0.0649, |
| "num_input_tokens_seen": 562176, |
| "step": 1795 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 0.4583163857460022, |
| "learning_rate": 4.700884634611935e-11, |
| "loss": 0.0292, |
| "num_input_tokens_seen": 563744, |
| "step": 1800 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.060703717172145844, |
| "eval_runtime": 0.519, |
| "eval_samples_per_second": 77.074, |
| "eval_steps_per_second": 19.269, |
| "num_input_tokens_seen": 563744, |
| "step": 1800 |
| }, |
| { |
| "epoch": 20.0, |
| "num_input_tokens_seen": 563744, |
| "step": 1800, |
| "total_flos": 2.538580254523392e+16, |
| "train_loss": 0.10106630020671421, |
| "train_runtime": 280.5961, |
| "train_samples_per_second": 25.66, |
| "train_steps_per_second": 6.415 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1800, |
| "num_input_tokens_seen": 563744, |
| "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": 2.538580254523392e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
