| { | |
| "best_metric": 2.442666530609131, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.021500752526338422, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014333835017558947, | |
| "grad_norm": 4.095588207244873, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 6.7525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014333835017558947, | |
| "eval_loss": 6.518734931945801, | |
| "eval_runtime": 4.4502, | |
| "eval_samples_per_second": 11.235, | |
| "eval_steps_per_second": 1.573, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028667670035117894, | |
| "grad_norm": 3.9740452766418457, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 6.4827, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00043001505052676843, | |
| "grad_norm": 4.090057373046875, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 6.803, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005733534007023579, | |
| "grad_norm": 4.096340656280518, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 6.3331, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007166917508779474, | |
| "grad_norm": 3.8779053688049316, | |
| "learning_rate": 0.00015, | |
| "loss": 5.8767, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008600301010535369, | |
| "grad_norm": 3.677866220474243, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 5.0901, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010033684512291263, | |
| "grad_norm": 3.940865993499756, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 4.4307, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011467068014047158, | |
| "grad_norm": 3.4478397369384766, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 3.9003, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012900451515803052, | |
| "grad_norm": 1.962295651435852, | |
| "learning_rate": 0.00027, | |
| "loss": 3.133, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014333835017558947, | |
| "grad_norm": 2.3240482807159424, | |
| "learning_rate": 0.0003, | |
| "loss": 2.9516, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015767218519314842, | |
| "grad_norm": 1.8678102493286133, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 2.8182, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0017200602021070737, | |
| "grad_norm": 1.6835949420928955, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 2.6626, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0018633985522826632, | |
| "grad_norm": 1.4440191984176636, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 2.6, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0020067369024582525, | |
| "grad_norm": 3.3333661556243896, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 2.6397, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0021500752526338422, | |
| "grad_norm": 2.430225372314453, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 2.7674, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0022934136028094315, | |
| "grad_norm": 1.6387251615524292, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 2.5239, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002436751952985021, | |
| "grad_norm": 1.1381381750106812, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 2.5054, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0025800903031606105, | |
| "grad_norm": 1.326271414756775, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 2.5822, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0027234286533362, | |
| "grad_norm": 1.0840177536010742, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 2.4767, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0028667670035117895, | |
| "grad_norm": 1.4158834218978882, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 2.484, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003010105353687379, | |
| "grad_norm": 1.3069770336151123, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 2.4704, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0031534437038629685, | |
| "grad_norm": 0.8556431531906128, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 2.5037, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003296782054038558, | |
| "grad_norm": 0.8674086332321167, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 2.5533, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0034401204042141475, | |
| "grad_norm": 0.8356068134307861, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 2.5738, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003583458754389737, | |
| "grad_norm": 1.8884528875350952, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 2.4843, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003583458754389737, | |
| "eval_loss": 2.4727981090545654, | |
| "eval_runtime": 4.572, | |
| "eval_samples_per_second": 10.936, | |
| "eval_steps_per_second": 1.531, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0037267971045653265, | |
| "grad_norm": 0.7543926239013672, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 2.4307, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0038701354547409157, | |
| "grad_norm": 0.5183073282241821, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 2.4546, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004013473804916505, | |
| "grad_norm": 2.17268443107605, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 2.4966, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004156812155092095, | |
| "grad_norm": 0.5066993236541748, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 2.4952, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0043001505052676844, | |
| "grad_norm": 0.4776642918586731, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 2.5126, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004443488855443274, | |
| "grad_norm": 0.6363259553909302, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 2.5075, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004586827205618863, | |
| "grad_norm": 0.4743508994579315, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 2.4578, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004730165555794453, | |
| "grad_norm": 0.3669068217277527, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 2.4547, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004873503905970042, | |
| "grad_norm": 0.48330530524253845, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 2.6293, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005016842256145632, | |
| "grad_norm": 0.44809746742248535, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 2.4301, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005160180606321221, | |
| "grad_norm": 0.5167154669761658, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 2.5549, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005303518956496811, | |
| "grad_norm": 0.5323503613471985, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 2.4602, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0054468573066724, | |
| "grad_norm": 0.49367713928222656, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 2.3723, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.005590195656847989, | |
| "grad_norm": 0.4007982909679413, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 2.404, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.005733534007023579, | |
| "grad_norm": 0.5526387095451355, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 2.5208, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005876872357199169, | |
| "grad_norm": 0.6063050627708435, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 2.5084, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006020210707374758, | |
| "grad_norm": 0.5957720875740051, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 2.4823, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006163549057550347, | |
| "grad_norm": 0.4266456663608551, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 2.4275, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006306887407725937, | |
| "grad_norm": 0.6097196340560913, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 2.4463, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.006450225757901527, | |
| "grad_norm": 0.4464048445224762, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 2.441, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006593564108077116, | |
| "grad_norm": 0.7037805914878845, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 2.5366, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.006736902458252705, | |
| "grad_norm": 0.5217775702476501, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 2.4081, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006880240808428295, | |
| "grad_norm": 0.4792337417602539, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 2.5082, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007023579158603885, | |
| "grad_norm": 0.3848729729652405, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 2.5108, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.007166917508779474, | |
| "grad_norm": 0.4266701638698578, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 2.4282, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007166917508779474, | |
| "eval_loss": 2.515470027923584, | |
| "eval_runtime": 4.5689, | |
| "eval_samples_per_second": 10.944, | |
| "eval_steps_per_second": 1.532, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007310255858955063, | |
| "grad_norm": 0.4437111020088196, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 2.3658, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.007453594209130653, | |
| "grad_norm": 0.3480053246021271, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 2.4018, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.007596932559306243, | |
| "grad_norm": 0.45664915442466736, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 2.4212, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0077402709094818315, | |
| "grad_norm": 0.30473992228507996, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 2.3651, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.007883609259657422, | |
| "grad_norm": 0.3738688826560974, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 2.3824, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.00802694760983301, | |
| "grad_norm": 0.4079970717430115, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 2.5106, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0081702859600086, | |
| "grad_norm": 0.6227981448173523, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 2.5133, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.00831362431018419, | |
| "grad_norm": 0.5902373194694519, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 2.4108, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.00845696266035978, | |
| "grad_norm": 0.3553559482097626, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 2.4769, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.008600301010535369, | |
| "grad_norm": 0.30603644251823425, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 2.3449, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.008743639360710959, | |
| "grad_norm": 0.38652244210243225, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 2.4605, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.008886977710886548, | |
| "grad_norm": 0.8515211939811707, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 2.5039, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.009030316061062138, | |
| "grad_norm": 0.48116958141326904, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 2.4173, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.009173654411237726, | |
| "grad_norm": 0.394767701625824, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 2.4306, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.009316992761413316, | |
| "grad_norm": 0.3945147693157196, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 2.4364, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.009460331111588905, | |
| "grad_norm": 3.018016815185547, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 2.458, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.009603669461764495, | |
| "grad_norm": 0.4277852773666382, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 2.5136, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.009747007811940085, | |
| "grad_norm": 0.4447251856327057, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 2.4805, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.009890346162115675, | |
| "grad_norm": 0.48989495635032654, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 2.4012, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.010033684512291264, | |
| "grad_norm": 1.8352046012878418, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 2.5, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.010177022862466852, | |
| "grad_norm": 0.4361478388309479, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 2.3609, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.010320361212642442, | |
| "grad_norm": 0.3762364387512207, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 2.4299, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.010463699562818032, | |
| "grad_norm": 0.5353628993034363, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 2.4636, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.010607037912993621, | |
| "grad_norm": 0.4717017710208893, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 2.3873, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.010750376263169211, | |
| "grad_norm": 0.4951079189777374, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 2.3833, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.010750376263169211, | |
| "eval_loss": 2.5027923583984375, | |
| "eval_runtime": 4.575, | |
| "eval_samples_per_second": 10.929, | |
| "eval_steps_per_second": 1.53, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0108937146133448, | |
| "grad_norm": 1.1163285970687866, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 2.4308, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.01103705296352039, | |
| "grad_norm": 0.5007464289665222, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 2.4557, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.011180391313695979, | |
| "grad_norm": 0.48471787571907043, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 2.4868, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.011323729663871568, | |
| "grad_norm": 0.4553197920322418, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 2.4538, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.011467068014047158, | |
| "grad_norm": 0.49402543902397156, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 2.4061, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.011610406364222748, | |
| "grad_norm": 0.43397530913352966, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 2.5284, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.011753744714398337, | |
| "grad_norm": 0.39252761006355286, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 2.4795, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.011897083064573927, | |
| "grad_norm": 0.4337272644042969, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 2.4098, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.012040421414749517, | |
| "grad_norm": 0.5519135594367981, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 2.4282, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.012183759764925106, | |
| "grad_norm": 0.46673280000686646, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 2.483, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.012327098115100694, | |
| "grad_norm": 0.42640626430511475, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 2.5023, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.012470436465276284, | |
| "grad_norm": 0.4718412458896637, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 2.5087, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.012613774815451874, | |
| "grad_norm": 0.5302379727363586, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 2.4402, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.012757113165627464, | |
| "grad_norm": 0.3727835416793823, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 2.4963, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.012900451515803053, | |
| "grad_norm": 0.9599354863166809, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 2.437, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.013043789865978643, | |
| "grad_norm": 0.40621206164360046, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 2.3686, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.013187128216154233, | |
| "grad_norm": 0.40959206223487854, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 2.4784, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.01333046656632982, | |
| "grad_norm": 0.4783549904823303, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 2.5026, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.01347380491650541, | |
| "grad_norm": 0.4089532792568207, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 2.4641, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.013617143266681, | |
| "grad_norm": 0.40697500109672546, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 2.4023, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.01376048161685659, | |
| "grad_norm": 0.44492053985595703, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 2.4689, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.01390381996703218, | |
| "grad_norm": 0.4386192560195923, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 2.3685, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.01404715831720777, | |
| "grad_norm": 0.9035962820053101, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 2.434, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.014190496667383359, | |
| "grad_norm": 0.5646589994430542, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 2.5078, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.014333835017558949, | |
| "grad_norm": 0.6752585172653198, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 2.3888, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.014333835017558949, | |
| "eval_loss": 2.4761135578155518, | |
| "eval_runtime": 4.5655, | |
| "eval_samples_per_second": 10.952, | |
| "eval_steps_per_second": 1.533, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.014477173367734537, | |
| "grad_norm": 0.6777223348617554, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 2.4187, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.014620511717910126, | |
| "grad_norm": 0.6800750494003296, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 2.4502, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.014763850068085716, | |
| "grad_norm": 0.52974534034729, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 2.4709, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.014907188418261306, | |
| "grad_norm": 0.502795934677124, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 2.3035, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.015050526768436896, | |
| "grad_norm": 0.6192975044250488, | |
| "learning_rate": 0.00015, | |
| "loss": 2.6338, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.015193865118612485, | |
| "grad_norm": 0.4301483929157257, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 2.3471, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.015337203468788075, | |
| "grad_norm": 0.4026905596256256, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 2.4869, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.015480541818963663, | |
| "grad_norm": 0.33096885681152344, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 2.3908, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.015623880169139253, | |
| "grad_norm": 0.3435579836368561, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 2.4443, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.015767218519314844, | |
| "grad_norm": 0.5849462151527405, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 2.357, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.015910556869490434, | |
| "grad_norm": 0.415574848651886, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 2.4204, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.01605389521966602, | |
| "grad_norm": 0.5506088137626648, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 2.4529, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.01619723356984161, | |
| "grad_norm": 0.4681348204612732, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 2.4031, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.0163405719200172, | |
| "grad_norm": 0.33748188614845276, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 2.3714, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.01648391027019279, | |
| "grad_norm": 0.36723262071609497, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 2.4555, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.01662724862036838, | |
| "grad_norm": 0.454904168844223, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 2.4527, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.01677058697054397, | |
| "grad_norm": 0.4296797215938568, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 2.4918, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.01691392532071956, | |
| "grad_norm": 0.433634877204895, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 2.5004, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.017057263670895148, | |
| "grad_norm": 0.3770894706249237, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 2.4621, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.017200602021070738, | |
| "grad_norm": 0.44861501455307007, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 2.3952, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.017343940371246327, | |
| "grad_norm": 0.4860612154006958, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 2.3897, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.017487278721421917, | |
| "grad_norm": 0.3798341751098633, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 2.4805, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.017630617071597507, | |
| "grad_norm": 0.3528059720993042, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 2.3983, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.017773955421773097, | |
| "grad_norm": 0.37472400069236755, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 2.3448, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.017917293771948686, | |
| "grad_norm": 0.450785756111145, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 2.4047, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.017917293771948686, | |
| "eval_loss": 2.4208545684814453, | |
| "eval_runtime": 4.5669, | |
| "eval_samples_per_second": 10.948, | |
| "eval_steps_per_second": 1.533, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.018060632122124276, | |
| "grad_norm": 0.42055612802505493, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 2.3805, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.018203970472299862, | |
| "grad_norm": 0.4635365605354309, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 2.3714, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.018347308822475452, | |
| "grad_norm": 0.36117833852767944, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 2.4163, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.01849064717265104, | |
| "grad_norm": 0.3636980950832367, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 2.362, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.01863398552282663, | |
| "grad_norm": 0.4152284860610962, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 2.4751, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01877732387300222, | |
| "grad_norm": 0.5936709642410278, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 2.4146, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.01892066222317781, | |
| "grad_norm": 0.43432939052581787, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 2.3515, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.0190640005733534, | |
| "grad_norm": 0.5816676020622253, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 2.4006, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.01920733892352899, | |
| "grad_norm": 0.4577726423740387, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 2.4041, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.01935067727370458, | |
| "grad_norm": 0.5329848527908325, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 2.4021, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.01949401562388017, | |
| "grad_norm": 0.4278225302696228, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 2.3308, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.01963735397405576, | |
| "grad_norm": 0.42905911803245544, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 2.4348, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.01978069232423135, | |
| "grad_norm": 0.4884713292121887, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 2.3535, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.01992403067440694, | |
| "grad_norm": 0.5074369311332703, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 2.4361, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.02006736902458253, | |
| "grad_norm": 0.5184245109558105, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 2.48, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02021070737475812, | |
| "grad_norm": 0.4724279046058655, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 2.3833, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.020354045724933705, | |
| "grad_norm": 0.42493098974227905, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 2.4109, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.020497384075109294, | |
| "grad_norm": 0.46368831396102905, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 2.403, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.020640722425284884, | |
| "grad_norm": 0.5204209685325623, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 2.4407, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.020784060775460474, | |
| "grad_norm": 0.5628048777580261, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 2.4423, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.020927399125636063, | |
| "grad_norm": 0.43388831615448, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 2.4248, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.021070737475811653, | |
| "grad_norm": 0.43663108348846436, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 2.4316, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.021214075825987243, | |
| "grad_norm": 0.4974912703037262, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 2.4239, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.021357414176162832, | |
| "grad_norm": 0.48720306158065796, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 2.4115, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.021500752526338422, | |
| "grad_norm": 0.4307795763015747, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 2.4406, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.021500752526338422, | |
| "eval_loss": 2.442666530609131, | |
| "eval_runtime": 4.5664, | |
| "eval_samples_per_second": 10.95, | |
| "eval_steps_per_second": 1.533, | |
| "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": 1.04954557759488e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |