| { | |
| "best_metric": 10.3283109664917, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.16703786191536749, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011135857461024498, | |
| "grad_norm": 0.021220365539193153, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 10.3743, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011135857461024498, | |
| "eval_loss": 10.371726036071777, | |
| "eval_runtime": 0.0507, | |
| "eval_samples_per_second": 985.944, | |
| "eval_steps_per_second": 39.438, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022271714922048997, | |
| "grad_norm": 0.02089685946702957, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 10.3748, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0033407572383073497, | |
| "grad_norm": 0.022434862330555916, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 10.3751, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004454342984409799, | |
| "grad_norm": 0.022230561822652817, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 10.3744, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005567928730512249, | |
| "grad_norm": 0.022404590621590614, | |
| "learning_rate": 0.00015, | |
| "loss": 10.3725, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0066815144766146995, | |
| "grad_norm": 0.023340720683336258, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 10.3725, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0077951002227171495, | |
| "grad_norm": 0.02542109414935112, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 10.3724, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008908685968819599, | |
| "grad_norm": 0.027613935992121696, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 10.3733, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01002227171492205, | |
| "grad_norm": 0.027721751481294632, | |
| "learning_rate": 0.00027, | |
| "loss": 10.3718, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011135857461024499, | |
| "grad_norm": 0.031006429344415665, | |
| "learning_rate": 0.0003, | |
| "loss": 10.3713, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012249443207126948, | |
| "grad_norm": 0.03272189199924469, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 10.3694, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013363028953229399, | |
| "grad_norm": 0.03870847821235657, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 10.3682, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014476614699331848, | |
| "grad_norm": 0.026634380221366882, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 10.3716, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015590200445434299, | |
| "grad_norm": 0.030647795647382736, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 10.3724, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01670378619153675, | |
| "grad_norm": 0.03259807825088501, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 10.3729, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017817371937639197, | |
| "grad_norm": 0.03251082822680473, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 10.3723, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01893095768374165, | |
| "grad_norm": 0.03374587371945381, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 10.3709, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0200445434298441, | |
| "grad_norm": 0.03536859527230263, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 10.3695, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021158129175946547, | |
| "grad_norm": 0.04094082862138748, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 10.3676, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.022271714922048998, | |
| "grad_norm": 0.04486091434955597, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 10.3681, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02338530066815145, | |
| "grad_norm": 0.04667678475379944, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 10.3666, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.024498886414253896, | |
| "grad_norm": 0.049042511731386185, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 10.3668, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025612472160356347, | |
| "grad_norm": 0.05766143649816513, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 10.364, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.026726057906458798, | |
| "grad_norm": 0.063766248524189, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 10.362, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02783964365256125, | |
| "grad_norm": 0.06413163244724274, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 10.3616, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02783964365256125, | |
| "eval_loss": 10.362093925476074, | |
| "eval_runtime": 0.0468, | |
| "eval_samples_per_second": 1068.689, | |
| "eval_steps_per_second": 42.748, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028953229398663696, | |
| "grad_norm": 0.05297641456127167, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 10.3688, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.030066815144766147, | |
| "grad_norm": 0.059603746980428696, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 10.3657, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.031180400890868598, | |
| "grad_norm": 0.05739077180624008, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 10.3648, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03229398663697105, | |
| "grad_norm": 0.06212243810296059, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 10.3629, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0334075723830735, | |
| "grad_norm": 0.0610235333442688, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 10.3626, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.034521158129175944, | |
| "grad_norm": 0.05962621048092842, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 10.3607, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.035634743875278395, | |
| "grad_norm": 0.06733676046133041, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 10.3592, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.036748329621380846, | |
| "grad_norm": 0.06607528775930405, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 10.3575, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0378619153674833, | |
| "grad_norm": 0.06120593473315239, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 10.3574, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03897550111358575, | |
| "grad_norm": 0.06261507421731949, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 10.3548, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0400890868596882, | |
| "grad_norm": 0.05739546939730644, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 10.3533, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04120267260579064, | |
| "grad_norm": 0.05693826824426651, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 10.3503, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.042316258351893093, | |
| "grad_norm": 0.05451498553156853, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 10.3581, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.043429844097995544, | |
| "grad_norm": 0.055710602551698685, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 10.3566, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.044543429844097995, | |
| "grad_norm": 0.05021951347589493, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 10.3548, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.045657015590200446, | |
| "grad_norm": 0.04118210822343826, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 10.3563, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0467706013363029, | |
| "grad_norm": 0.03563275188207626, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 10.3531, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04788418708240535, | |
| "grad_norm": 0.036302387714385986, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 10.3524, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04899777282850779, | |
| "grad_norm": 0.03217688947916031, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 10.3522, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05011135857461024, | |
| "grad_norm": 0.035605840384960175, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 10.3514, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.051224944320712694, | |
| "grad_norm": 0.03646039217710495, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 10.3483, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.052338530066815145, | |
| "grad_norm": 0.03975389897823334, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 10.3468, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.053452115812917596, | |
| "grad_norm": 0.04297318309545517, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 10.3462, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05456570155902005, | |
| "grad_norm": 0.05375898629426956, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 10.3476, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0556792873051225, | |
| "grad_norm": 0.06830257922410965, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 10.3447, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0556792873051225, | |
| "eval_loss": 10.347752571105957, | |
| "eval_runtime": 0.0506, | |
| "eval_samples_per_second": 988.519, | |
| "eval_steps_per_second": 39.541, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05679287305122494, | |
| "grad_norm": 0.036631014198064804, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 10.3538, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.05790645879732739, | |
| "grad_norm": 0.03295717015862465, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 10.3509, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.05902004454342984, | |
| "grad_norm": 0.033492058515548706, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 10.351, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.060133630289532294, | |
| "grad_norm": 0.031195539981126785, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 10.3488, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.061247216035634745, | |
| "grad_norm": 0.034528084099292755, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 10.348, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.062360801781737196, | |
| "grad_norm": 0.03689737245440483, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 10.3479, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.06347438752783964, | |
| "grad_norm": 0.040240008383989334, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 10.346, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0645879732739421, | |
| "grad_norm": 0.035155221819877625, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 10.3445, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.06570155902004454, | |
| "grad_norm": 0.04302839934825897, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 10.3426, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.066815144766147, | |
| "grad_norm": 0.04797535389661789, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 10.3419, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06792873051224944, | |
| "grad_norm": 0.05042591318488121, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 10.3424, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.06904231625835189, | |
| "grad_norm": 0.06060624122619629, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 10.3386, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.07015590200445435, | |
| "grad_norm": 0.03394079953432083, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 10.3505, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.07126948775055679, | |
| "grad_norm": 0.03250078111886978, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 10.3476, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.07238307349665925, | |
| "grad_norm": 0.03402571752667427, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 10.3451, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07349665924276169, | |
| "grad_norm": 0.03165813162922859, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 10.3455, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.07461024498886415, | |
| "grad_norm": 0.033986710011959076, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 10.3431, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0757238307349666, | |
| "grad_norm": 0.03550755977630615, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 10.3431, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.07683741648106904, | |
| "grad_norm": 0.03433714807033539, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 10.3426, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0779510022271715, | |
| "grad_norm": 0.03356612101197243, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 10.3421, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07906458797327394, | |
| "grad_norm": 0.03245285525918007, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 10.3419, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0801781737193764, | |
| "grad_norm": 0.035388920456171036, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 10.3396, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.08129175946547884, | |
| "grad_norm": 0.038405828177928925, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 10.3362, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.08240534521158129, | |
| "grad_norm": 0.04556138068437576, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 10.3345, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.08351893095768374, | |
| "grad_norm": 0.05725998058915138, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 10.3327, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08351893095768374, | |
| "eval_loss": 10.338118553161621, | |
| "eval_runtime": 0.0504, | |
| "eval_samples_per_second": 991.693, | |
| "eval_steps_per_second": 39.668, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08463251670378619, | |
| "grad_norm": 0.03490576148033142, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 10.3483, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.08574610244988864, | |
| "grad_norm": 0.03555111214518547, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 10.3443, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.08685968819599109, | |
| "grad_norm": 0.0329761877655983, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 10.3436, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.08797327394209355, | |
| "grad_norm": 0.03092610463500023, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 10.3443, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.08908685968819599, | |
| "grad_norm": 0.03112075664103031, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 10.3411, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09020044543429843, | |
| "grad_norm": 0.028758404776453972, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 10.3401, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.09131403118040089, | |
| "grad_norm": 0.023690655827522278, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 10.3377, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.09242761692650334, | |
| "grad_norm": 0.02615417167544365, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 10.339, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.0935412026726058, | |
| "grad_norm": 0.02577822096645832, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 10.3357, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.09465478841870824, | |
| "grad_norm": 0.032399583607912064, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 10.3349, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0957683741648107, | |
| "grad_norm": 0.03822220861911774, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 10.3314, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.09688195991091314, | |
| "grad_norm": 0.05163590610027313, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 10.3299, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.09799554565701558, | |
| "grad_norm": 0.038402412086725235, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 10.3455, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.09910913140311804, | |
| "grad_norm": 0.03179153427481651, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 10.3438, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.10022271714922049, | |
| "grad_norm": 0.031388312578201294, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 10.343, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.10133630289532294, | |
| "grad_norm": 0.025438381358981133, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 10.3417, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.10244988864142539, | |
| "grad_norm": 0.025364622473716736, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 10.3393, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.10356347438752785, | |
| "grad_norm": 0.024232415482401848, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 10.337, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.10467706013363029, | |
| "grad_norm": 0.028822433203458786, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 10.3379, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.10579064587973273, | |
| "grad_norm": 0.022030413150787354, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 10.337, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.10690423162583519, | |
| "grad_norm": 0.0319385826587677, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 10.3355, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.10801781737193764, | |
| "grad_norm": 0.029396483674645424, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 10.3319, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.1091314031180401, | |
| "grad_norm": 0.03641531616449356, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 10.3319, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.11024498886414254, | |
| "grad_norm": 0.045224692672491074, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 10.3314, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.111358574610245, | |
| "grad_norm": 0.05978056415915489, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 10.3267, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.111358574610245, | |
| "eval_loss": 10.334311485290527, | |
| "eval_runtime": 0.0448, | |
| "eval_samples_per_second": 1116.397, | |
| "eval_steps_per_second": 44.656, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11247216035634744, | |
| "grad_norm": 0.04336141422390938, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 10.3448, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.11358574610244988, | |
| "grad_norm": 0.029405318200588226, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 10.3418, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.11469933184855234, | |
| "grad_norm": 0.024563252925872803, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 10.3404, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.11581291759465479, | |
| "grad_norm": 0.032005004584789276, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 10.3378, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.11692650334075724, | |
| "grad_norm": 0.027886446565389633, | |
| "learning_rate": 0.00015, | |
| "loss": 10.3384, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.11804008908685969, | |
| "grad_norm": 0.027392663061618805, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 10.3359, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.11915367483296214, | |
| "grad_norm": 0.029057586565613747, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 10.3357, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.12026726057906459, | |
| "grad_norm": 0.02602003701031208, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 10.334, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.12138084632516703, | |
| "grad_norm": 0.025092778727412224, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 10.3295, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.12249443207126949, | |
| "grad_norm": 0.0306704044342041, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 10.3304, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12360801781737193, | |
| "grad_norm": 0.03935825452208519, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 10.3302, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.12472160356347439, | |
| "grad_norm": 0.05053841695189476, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 10.3247, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.12583518930957685, | |
| "grad_norm": 0.03532646968960762, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 10.3419, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.12694877505567928, | |
| "grad_norm": 0.03398346155881882, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 10.341, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.12806236080178174, | |
| "grad_norm": 0.031128259375691414, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 10.3399, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.1291759465478842, | |
| "grad_norm": 0.02975599467754364, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 10.3378, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.13028953229398663, | |
| "grad_norm": 0.025660140439867973, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 10.3369, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.13140311804008908, | |
| "grad_norm": 0.023060623556375504, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 10.3345, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.13251670378619154, | |
| "grad_norm": 0.02799002081155777, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 10.3328, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.133630289532294, | |
| "grad_norm": 0.024050775915384293, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 10.3321, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.13474387527839643, | |
| "grad_norm": 0.02656245231628418, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 10.3342, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.1358574610244989, | |
| "grad_norm": 0.02685682475566864, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 10.3297, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.13697104677060135, | |
| "grad_norm": 0.03605301305651665, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 10.3265, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.13808463251670378, | |
| "grad_norm": 0.04310872033238411, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 10.325, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.13919821826280623, | |
| "grad_norm": 0.052310604602098465, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 10.3216, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.13919821826280623, | |
| "eval_loss": 10.330706596374512, | |
| "eval_runtime": 0.0484, | |
| "eval_samples_per_second": 1033.941, | |
| "eval_steps_per_second": 41.358, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1403118040089087, | |
| "grad_norm": 0.03873632475733757, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 10.343, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.14142538975501115, | |
| "grad_norm": 0.03256813436746597, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 10.3388, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.14253897550111358, | |
| "grad_norm": 0.026527272537350655, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 10.3378, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.14365256124721604, | |
| "grad_norm": 0.022660735994577408, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 10.3365, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.1447661469933185, | |
| "grad_norm": 0.0257252287119627, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 10.3343, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.14587973273942093, | |
| "grad_norm": 0.02294372208416462, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 10.3345, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.14699331848552338, | |
| "grad_norm": 0.022150015458464622, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 10.33, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.14810690423162584, | |
| "grad_norm": 0.023904934525489807, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 10.3325, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.1492204899777283, | |
| "grad_norm": 0.025626808404922485, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 10.329, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.15033407572383073, | |
| "grad_norm": 0.031538087874650955, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 10.3266, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.1514476614699332, | |
| "grad_norm": 0.03154623880982399, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 10.3253, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.15256124721603564, | |
| "grad_norm": 0.04129767417907715, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 10.3231, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.15367483296213807, | |
| "grad_norm": 0.03668758645653725, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 10.3407, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.15478841870824053, | |
| "grad_norm": 0.03435783460736275, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 10.3408, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.155902004454343, | |
| "grad_norm": 0.03316853567957878, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 10.3389, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.15701559020044542, | |
| "grad_norm": 0.025575635954737663, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 10.3364, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.15812917594654788, | |
| "grad_norm": 0.021810244768857956, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 10.3354, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.15924276169265034, | |
| "grad_norm": 0.021209685131907463, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 10.3342, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.1603563474387528, | |
| "grad_norm": 0.02310410887002945, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 10.3325, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.16146993318485522, | |
| "grad_norm": 0.021886780858039856, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 10.3306, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.16258351893095768, | |
| "grad_norm": 0.025645460933446884, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 10.3291, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.16369710467706014, | |
| "grad_norm": 0.028998544439673424, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 10.3274, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.16481069042316257, | |
| "grad_norm": 0.03274320811033249, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 10.3251, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.16592427616926503, | |
| "grad_norm": 0.041816357523202896, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 10.3252, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.16703786191536749, | |
| "grad_norm": 0.05579761043190956, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 10.321, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16703786191536749, | |
| "eval_loss": 10.3283109664917, | |
| "eval_runtime": 0.0477, | |
| "eval_samples_per_second": 1048.482, | |
| "eval_steps_per_second": 41.939, | |
| "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": 69380829872128.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |