| { | |
| "best_metric": 0.4293454885482788, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.21344717182497333, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001422981145499822, | |
| "grad_norm": 0.8191930651664734, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.8579, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001422981145499822, | |
| "eval_loss": 2.6855461597442627, | |
| "eval_runtime": 2.0671, | |
| "eval_samples_per_second": 24.188, | |
| "eval_steps_per_second": 3.386, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002845962290999644, | |
| "grad_norm": 0.9729381799697876, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.0766, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004268943436499467, | |
| "grad_norm": 0.8968315124511719, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.5414, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005691924581999288, | |
| "grad_norm": 0.882707417011261, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.5339, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007114905727499111, | |
| "grad_norm": 0.916093647480011, | |
| "learning_rate": 0.00015, | |
| "loss": 2.5088, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008537886872998933, | |
| "grad_norm": 0.9488129615783691, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.385, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009960868018498754, | |
| "grad_norm": 1.007516860961914, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.2796, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011383849163998577, | |
| "grad_norm": 1.0053644180297852, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.0712, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012806830309498399, | |
| "grad_norm": 0.915839433670044, | |
| "learning_rate": 0.00027, | |
| "loss": 1.998, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014229811454998222, | |
| "grad_norm": 0.7682165503501892, | |
| "learning_rate": 0.0003, | |
| "loss": 1.8872, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015652792600498042, | |
| "grad_norm": 0.8641461133956909, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 1.7376, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.017075773745997867, | |
| "grad_norm": 0.8075277805328369, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 1.632, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.018498754891497687, | |
| "grad_norm": 0.762394905090332, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 1.347, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.019921736036997508, | |
| "grad_norm": 0.7908850312232971, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 1.1928, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.021344717182497332, | |
| "grad_norm": 0.8413186073303223, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 1.0229, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022767698327997153, | |
| "grad_norm": 0.8821457028388977, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 1.019, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.024190679473496977, | |
| "grad_norm": 0.9173251986503601, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 1.0191, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.025613660618996798, | |
| "grad_norm": 0.7435721755027771, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.9497, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02703664176449662, | |
| "grad_norm": 0.7625381350517273, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.8573, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.028459622909996443, | |
| "grad_norm": 0.8063183426856995, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.9115, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029882604055496264, | |
| "grad_norm": 0.6584380269050598, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.7548, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.031305585200996085, | |
| "grad_norm": 0.6741005182266235, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.8572, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03272856634649591, | |
| "grad_norm": 0.6349349617958069, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.7942, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03415154749199573, | |
| "grad_norm": 0.5690104961395264, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.7952, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03557452863749555, | |
| "grad_norm": 0.5119650363922119, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.8102, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03557452863749555, | |
| "eval_loss": 0.8686224222183228, | |
| "eval_runtime": 1.5871, | |
| "eval_samples_per_second": 31.505, | |
| "eval_steps_per_second": 4.411, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.036997509782995375, | |
| "grad_norm": 0.6452613472938538, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.9172, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0384204909284952, | |
| "grad_norm": 0.5750677585601807, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.8096, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.039843472073995016, | |
| "grad_norm": 0.493135005235672, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.6532, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04126645321949484, | |
| "grad_norm": 0.566339373588562, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.7725, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.042689434364994665, | |
| "grad_norm": 0.4760490655899048, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.8217, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04411241551049449, | |
| "grad_norm": 0.4571889340877533, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.746, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.045535396655994306, | |
| "grad_norm": 0.4935093820095062, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.7695, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04695837780149413, | |
| "grad_norm": 0.4788101315498352, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.7196, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.048381358946993955, | |
| "grad_norm": 0.4659596383571625, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.6524, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04980434009249377, | |
| "grad_norm": 0.4702892005443573, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.7084, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.051227321237993596, | |
| "grad_norm": 0.43953150510787964, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.6571, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05265030238349342, | |
| "grad_norm": 0.48017436265945435, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.6499, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05407328352899324, | |
| "grad_norm": 0.4220162034034729, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.6256, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05549626467449306, | |
| "grad_norm": 0.45973941683769226, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.6496, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.056919245819992886, | |
| "grad_norm": 0.49031051993370056, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.7017, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05834222696549271, | |
| "grad_norm": 0.50996333360672, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.646, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05976520811099253, | |
| "grad_norm": 0.49370792508125305, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.6681, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06118818925649235, | |
| "grad_norm": 0.6224830746650696, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.7153, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06261117040199217, | |
| "grad_norm": 0.47643178701400757, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.7022, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.064034151547492, | |
| "grad_norm": 0.5734248757362366, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.7246, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06545713269299182, | |
| "grad_norm": 0.6396843194961548, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.6551, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06688011383849164, | |
| "grad_norm": 0.7682932019233704, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.7881, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06830309498399147, | |
| "grad_norm": 0.5934016704559326, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.6506, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06972607612949129, | |
| "grad_norm": 1.0871713161468506, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.8281, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0711490572749911, | |
| "grad_norm": 0.8507772088050842, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.8056, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0711490572749911, | |
| "eval_loss": 0.6373523473739624, | |
| "eval_runtime": 1.5884, | |
| "eval_samples_per_second": 31.477, | |
| "eval_steps_per_second": 4.407, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07257203842049093, | |
| "grad_norm": 1.044948697090149, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 0.8342, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.07399501956599075, | |
| "grad_norm": 1.0066823959350586, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 1.0176, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.07541800071149057, | |
| "grad_norm": 0.8357412815093994, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 0.5818, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0768409818569904, | |
| "grad_norm": 0.5974358320236206, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.5231, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.07826396300249022, | |
| "grad_norm": 0.4712371826171875, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.5346, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.07968694414799003, | |
| "grad_norm": 0.48890915513038635, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.6215, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.08110992529348986, | |
| "grad_norm": 0.5396881699562073, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.57, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.08253290643898968, | |
| "grad_norm": 0.5231046080589294, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.525, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0839558875844895, | |
| "grad_norm": 0.5166378617286682, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.535, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.08537886872998933, | |
| "grad_norm": 0.4543461203575134, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.5265, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08680184987548915, | |
| "grad_norm": 0.4526726305484772, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.5463, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.08822483102098898, | |
| "grad_norm": 0.4510972201824188, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.5163, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.08964781216648879, | |
| "grad_norm": 0.3307866156101227, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.4868, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.09107079331198861, | |
| "grad_norm": 0.47421735525131226, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.4633, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.09249377445748844, | |
| "grad_norm": 0.37198832631111145, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.484, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.09391675560298826, | |
| "grad_norm": 0.492297500371933, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.5477, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.09533973674848809, | |
| "grad_norm": 0.46712058782577515, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.566, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.09676271789398791, | |
| "grad_norm": 0.395457923412323, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.4635, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.09818569903948772, | |
| "grad_norm": 0.49724629521369934, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.501, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.09960868018498754, | |
| "grad_norm": 0.4556506872177124, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.4758, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.10103166133048737, | |
| "grad_norm": 0.488097220659256, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.5382, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.10245464247598719, | |
| "grad_norm": 0.5412923693656921, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.6215, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.10387762362148702, | |
| "grad_norm": 0.431452214717865, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.5064, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.10530060476698684, | |
| "grad_norm": 0.6141003966331482, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.4909, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.10672358591248667, | |
| "grad_norm": 0.46321696043014526, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.4664, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.10672358591248667, | |
| "eval_loss": 0.5455062389373779, | |
| "eval_runtime": 1.5894, | |
| "eval_samples_per_second": 31.459, | |
| "eval_steps_per_second": 4.404, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.10814656705798648, | |
| "grad_norm": 0.5080518126487732, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.525, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.1095695482034863, | |
| "grad_norm": 0.3996676802635193, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.4702, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.11099252934898612, | |
| "grad_norm": 0.4271460175514221, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.5, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.11241551049448595, | |
| "grad_norm": 0.46124765276908875, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 0.4972, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.11383849163998577, | |
| "grad_norm": 0.4041891098022461, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.5017, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1152614727854856, | |
| "grad_norm": 0.43278566002845764, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.4823, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.11668445393098542, | |
| "grad_norm": 0.49185311794281006, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 0.4747, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.11810743507648523, | |
| "grad_norm": 0.4809925854206085, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 0.5292, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.11953041622198506, | |
| "grad_norm": 0.4222284257411957, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 0.5157, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.12095339736748488, | |
| "grad_norm": 0.46804237365722656, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 0.5094, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1223763785129847, | |
| "grad_norm": 0.4556009769439697, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.5129, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.12379935965848453, | |
| "grad_norm": 0.458716481924057, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.4831, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.12522234080398434, | |
| "grad_norm": 0.4597315788269043, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.4613, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.12664532194948416, | |
| "grad_norm": 0.5253174901008606, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.5142, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.128068303094984, | |
| "grad_norm": 0.5549522638320923, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.5332, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1294912842404838, | |
| "grad_norm": 0.4502198100090027, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.4298, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.13091426538598364, | |
| "grad_norm": 0.38060614466667175, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.4558, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.13233724653148346, | |
| "grad_norm": 0.52518630027771, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.4687, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.13376022767698328, | |
| "grad_norm": 0.5193655490875244, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.4809, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.1351832088224831, | |
| "grad_norm": 0.5254992842674255, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.4535, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.13660618996798293, | |
| "grad_norm": 0.46708381175994873, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.5143, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.13802917111348276, | |
| "grad_norm": 0.5062940716743469, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.5421, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.13945215225898258, | |
| "grad_norm": 0.5772467255592346, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.5691, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.14087513340448238, | |
| "grad_norm": 0.7562189102172852, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.5696, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.1422981145499822, | |
| "grad_norm": 0.7072889804840088, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.6114, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1422981145499822, | |
| "eval_loss": 0.48794320225715637, | |
| "eval_runtime": 1.5895, | |
| "eval_samples_per_second": 31.457, | |
| "eval_steps_per_second": 4.404, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14372109569548203, | |
| "grad_norm": 0.5918603539466858, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 0.6081, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.14514407684098185, | |
| "grad_norm": 0.814773440361023, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 0.7945, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.14656705798648167, | |
| "grad_norm": 0.5480428338050842, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 0.4602, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.1479900391319815, | |
| "grad_norm": 0.4311855435371399, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 0.3792, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.14941302027748132, | |
| "grad_norm": 0.5230007171630859, | |
| "learning_rate": 0.00015, | |
| "loss": 0.4123, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.15083600142298115, | |
| "grad_norm": 0.4562471807003021, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 0.4171, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.15225898256848097, | |
| "grad_norm": 0.464626282453537, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 0.3999, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.1536819637139808, | |
| "grad_norm": 0.4413895606994629, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 0.4036, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.15510494485948062, | |
| "grad_norm": 0.4271002411842346, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 0.4165, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.15652792600498044, | |
| "grad_norm": 0.4437054395675659, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 0.385, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.15795090715048027, | |
| "grad_norm": 0.6215757727622986, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 0.4807, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.15937388829598007, | |
| "grad_norm": 0.6023930311203003, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 0.4458, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.1607968694414799, | |
| "grad_norm": 0.5075235366821289, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 0.4103, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.1622198505869797, | |
| "grad_norm": 0.4037129580974579, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 0.4037, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.16364283173247954, | |
| "grad_norm": 0.4262774884700775, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 0.3738, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.16506581287797936, | |
| "grad_norm": 0.38689273595809937, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 0.4016, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.1664887940234792, | |
| "grad_norm": 0.45144420862197876, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 0.4268, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.167911775168979, | |
| "grad_norm": 0.35227862000465393, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 0.3679, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.16933475631447883, | |
| "grad_norm": 0.4991707503795624, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 0.4614, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.17075773745997866, | |
| "grad_norm": 0.37295737862586975, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 0.4173, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17218071860547848, | |
| "grad_norm": 0.3991025686264038, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 0.4005, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.1736036997509783, | |
| "grad_norm": 0.444135844707489, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 0.3766, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.17502668089647813, | |
| "grad_norm": 0.45515337586402893, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 0.3954, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.17644966204197796, | |
| "grad_norm": 0.5047637820243835, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.427, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.17787264318747775, | |
| "grad_norm": 0.4614162743091583, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 0.4422, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.17787264318747775, | |
| "eval_loss": 0.4491093158721924, | |
| "eval_runtime": 1.5932, | |
| "eval_samples_per_second": 31.383, | |
| "eval_steps_per_second": 4.394, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.17929562433297758, | |
| "grad_norm": 0.39532631635665894, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 0.3954, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.1807186054784774, | |
| "grad_norm": 0.4130837321281433, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 0.3957, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.18214158662397723, | |
| "grad_norm": 0.4563869833946228, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 0.4121, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.18356456776947705, | |
| "grad_norm": 0.4387674629688263, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 0.3886, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.18498754891497687, | |
| "grad_norm": 0.49771103262901306, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 0.3902, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1864105300604767, | |
| "grad_norm": 0.5475918650627136, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 0.4373, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.18783351120597652, | |
| "grad_norm": 0.49682438373565674, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 0.4013, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.18925649235147635, | |
| "grad_norm": 0.4471288025379181, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 0.4139, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.19067947349697617, | |
| "grad_norm": 0.41703081130981445, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 0.4089, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.192102454642476, | |
| "grad_norm": 0.5421717166900635, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 0.4213, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.19352543578797582, | |
| "grad_norm": 0.3587832450866699, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 0.3714, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.19494841693347564, | |
| "grad_norm": 0.42268967628479004, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 0.391, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.19637139807897544, | |
| "grad_norm": 0.45539185404777527, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 0.3907, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.19779437922447526, | |
| "grad_norm": 0.5193498134613037, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 0.4293, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.1992173603699751, | |
| "grad_norm": 0.49450474977493286, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 0.3975, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2006403415154749, | |
| "grad_norm": 0.5141414403915405, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.3932, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.20206332266097474, | |
| "grad_norm": 0.5565205216407776, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.4097, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.20348630380647456, | |
| "grad_norm": 0.5086135864257812, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.4553, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.20490928495197439, | |
| "grad_norm": 0.43909886479377747, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.4142, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.2063322660974742, | |
| "grad_norm": 0.4421076774597168, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.3916, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.20775524724297403, | |
| "grad_norm": 0.5867587327957153, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.4844, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.20917822838847386, | |
| "grad_norm": 0.4880177080631256, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.4324, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.21060120953397368, | |
| "grad_norm": 0.5578730702400208, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.4769, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.2120241906794735, | |
| "grad_norm": 0.5823155045509338, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.5011, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.21344717182497333, | |
| "grad_norm": 1.0556669235229492, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.6444, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.21344717182497333, | |
| "eval_loss": 0.4293454885482788, | |
| "eval_runtime": 1.5889, | |
| "eval_samples_per_second": 31.468, | |
| "eval_steps_per_second": 4.406, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.292050004063027e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |