| { | |
| "best_metric": 1.065322521753842e-06, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.22641509433962265, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015094339622641509, | |
| "grad_norm": 9.727989196777344, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.9383, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015094339622641509, | |
| "eval_loss": 5.682714939117432, | |
| "eval_runtime": 4.6749, | |
| "eval_samples_per_second": 10.695, | |
| "eval_steps_per_second": 1.497, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0030188679245283017, | |
| "grad_norm": 9.845698356628418, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.161, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004528301886792453, | |
| "grad_norm": 9.684377670288086, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.9913, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0060377358490566035, | |
| "grad_norm": 11.722749710083008, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.3506, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007547169811320755, | |
| "grad_norm": 10.132170677185059, | |
| "learning_rate": 0.00015, | |
| "loss": 0.6881, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009056603773584906, | |
| "grad_norm": 4.307816028594971, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.1223, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010566037735849057, | |
| "grad_norm": 0.7658965587615967, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.0231, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012075471698113207, | |
| "grad_norm": 0.04265095666050911, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.0011, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013584905660377358, | |
| "grad_norm": 0.017767086625099182, | |
| "learning_rate": 0.00027, | |
| "loss": 0.0003, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01509433962264151, | |
| "grad_norm": 0.011602415703237057, | |
| "learning_rate": 0.0003, | |
| "loss": 0.0002, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01660377358490566, | |
| "grad_norm": 0.03181695565581322, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.0004, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.018113207547169812, | |
| "grad_norm": 0.05330698564648628, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.0005, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.019622641509433963, | |
| "grad_norm": 0.025343570858240128, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.0002, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.021132075471698115, | |
| "grad_norm": 0.0021175649017095566, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.022641509433962263, | |
| "grad_norm": 0.0011911799665540457, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024150943396226414, | |
| "grad_norm": 0.0003560419427230954, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.025660377358490565, | |
| "grad_norm": 0.00067779456730932, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.027169811320754716, | |
| "grad_norm": 0.0009647771366871893, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.028679245283018868, | |
| "grad_norm": 0.0003761858679354191, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03018867924528302, | |
| "grad_norm": 0.0005870265304110944, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03169811320754717, | |
| "grad_norm": 0.000383986858651042, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03320754716981132, | |
| "grad_norm": 0.005932660773396492, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03471698113207547, | |
| "grad_norm": 36.32376480102539, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.2835, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.036226415094339624, | |
| "grad_norm": 2.1993796825408936, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.0043, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03773584905660377, | |
| "grad_norm": 0.00012767089356202632, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03773584905660377, | |
| "eval_loss": 7.517421181546524e-05, | |
| "eval_runtime": 4.2094, | |
| "eval_samples_per_second": 11.878, | |
| "eval_steps_per_second": 1.663, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03924528301886793, | |
| "grad_norm": 0.0003870428481604904, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.040754716981132075, | |
| "grad_norm": 0.005472894757986069, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04226415094339623, | |
| "grad_norm": 0.07725609093904495, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.0004, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04377358490566038, | |
| "grad_norm": 0.02922365628182888, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0001, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.045283018867924525, | |
| "grad_norm": 0.022537946701049805, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.0001, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04679245283018868, | |
| "grad_norm": 0.003779177786782384, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04830188679245283, | |
| "grad_norm": 0.0010583605617284775, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04981132075471698, | |
| "grad_norm": 0.00034484267234802246, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05132075471698113, | |
| "grad_norm": 0.00039084404124878347, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.052830188679245285, | |
| "grad_norm": 0.0004337659338489175, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05433962264150943, | |
| "grad_norm": 0.0008137256954796612, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05584905660377359, | |
| "grad_norm": 0.0009190964046865702, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.057358490566037736, | |
| "grad_norm": 0.0008511942578479648, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05886792452830188, | |
| "grad_norm": 0.0011096836533397436, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06037735849056604, | |
| "grad_norm": 0.0015806319424882531, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.061886792452830186, | |
| "grad_norm": 0.0018580264877527952, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06339622641509433, | |
| "grad_norm": 0.0010565021075308323, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0649056603773585, | |
| "grad_norm": 0.0007690914790146053, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06641509433962264, | |
| "grad_norm": 0.004054183140397072, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06792452830188679, | |
| "grad_norm": 0.000730887521058321, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06943396226415094, | |
| "grad_norm": 0.00044435824383981526, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0709433962264151, | |
| "grad_norm": 0.00042757357005029917, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07245283018867925, | |
| "grad_norm": 0.0003725688438862562, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0739622641509434, | |
| "grad_norm": 0.001020943047478795, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07547169811320754, | |
| "grad_norm": 0.0002570598153397441, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07547169811320754, | |
| "eval_loss": 2.3195319954538718e-05, | |
| "eval_runtime": 4.2144, | |
| "eval_samples_per_second": 11.864, | |
| "eval_steps_per_second": 1.661, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07698113207547169, | |
| "grad_norm": 0.15251204371452332, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 0.0003, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.07849056603773585, | |
| "grad_norm": 0.005662671290338039, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.0022388154175132513, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.08150943396226415, | |
| "grad_norm": 0.0037454920820891857, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0830188679245283, | |
| "grad_norm": 0.015162762254476547, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.08452830188679246, | |
| "grad_norm": 0.002864385489374399, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0860377358490566, | |
| "grad_norm": 0.0016423336928710341, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.08754716981132075, | |
| "grad_norm": 0.0003825683379545808, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0890566037735849, | |
| "grad_norm": 0.00015799446555320174, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.09056603773584905, | |
| "grad_norm": 0.00015713188622612506, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09207547169811321, | |
| "grad_norm": 0.00025742893922142684, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.09358490566037736, | |
| "grad_norm": 0.00015674770111218095, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.09509433962264151, | |
| "grad_norm": 0.00010490669228602201, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.09660377358490566, | |
| "grad_norm": 0.00021542170725297183, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.09811320754716982, | |
| "grad_norm": 0.00013019933248870075, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.09962264150943397, | |
| "grad_norm": 0.00012139895261498168, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.10113207547169811, | |
| "grad_norm": 7.941039075376466e-05, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.10264150943396226, | |
| "grad_norm": 0.0001448198891011998, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.10415094339622641, | |
| "grad_norm": 0.00020370357378851622, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.10566037735849057, | |
| "grad_norm": 0.00010941782966256142, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.10716981132075472, | |
| "grad_norm": 0.0001951769954757765, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.10867924528301887, | |
| "grad_norm": 0.0001411143020959571, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.11018867924528301, | |
| "grad_norm": 0.00015462335431948304, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.11169811320754718, | |
| "grad_norm": 0.0002607516653370112, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.11320754716981132, | |
| "grad_norm": 7.921539508970454e-05, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.11320754716981132, | |
| "eval_loss": 1.744836140460393e-06, | |
| "eval_runtime": 4.2094, | |
| "eval_samples_per_second": 11.878, | |
| "eval_steps_per_second": 1.663, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.11471698113207547, | |
| "grad_norm": 9.14011980057694e-05, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.11622641509433962, | |
| "grad_norm": 0.00013622430560644716, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.11773584905660377, | |
| "grad_norm": 0.00016065326053649187, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.11924528301886793, | |
| "grad_norm": 0.00017030604067258537, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.12075471698113208, | |
| "grad_norm": 0.0002959435514640063, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12226415094339622, | |
| "grad_norm": 7.727096817689016e-05, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.12377358490566037, | |
| "grad_norm": 0.0001273597008548677, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.12528301886792453, | |
| "grad_norm": 6.839417619630694e-05, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.12679245283018867, | |
| "grad_norm": 6.494703120552003e-05, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.12830188679245283, | |
| "grad_norm": 6.701619713567197e-05, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.129811320754717, | |
| "grad_norm": 0.00010753441893029958, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.13132075471698113, | |
| "grad_norm": 0.00015338734374381602, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.1328301886792453, | |
| "grad_norm": 6.136780575616285e-05, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.13433962264150942, | |
| "grad_norm": 9.956698340829462e-05, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.13584905660377358, | |
| "grad_norm": 0.0001380999747198075, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.13735849056603774, | |
| "grad_norm": 6.714855408063158e-05, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.13886792452830188, | |
| "grad_norm": 0.00010223900608252734, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.14037735849056604, | |
| "grad_norm": 0.00013666001905221492, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.1418867924528302, | |
| "grad_norm": 0.0001388599193887785, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.14339622641509434, | |
| "grad_norm": 9.564343781676143e-05, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1449056603773585, | |
| "grad_norm": 0.00011167208140250295, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.14641509433962263, | |
| "grad_norm": 0.0002111889043590054, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.1479245283018868, | |
| "grad_norm": 0.00010389567614765838, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.14943396226415095, | |
| "grad_norm": 0.00016280317504424602, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.1509433962264151, | |
| "grad_norm": 0.00014044858107808977, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1509433962264151, | |
| "eval_loss": 1.082283802134043e-06, | |
| "eval_runtime": 4.2074, | |
| "eval_samples_per_second": 11.884, | |
| "eval_steps_per_second": 1.664, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15245283018867925, | |
| "grad_norm": 2.1298315914464183e-05, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.15396226415094338, | |
| "grad_norm": 0.00017682627367321402, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.15547169811320755, | |
| "grad_norm": 4.0571725548943505e-05, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.1569811320754717, | |
| "grad_norm": 3.1571042200084776e-05, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.15849056603773584, | |
| "grad_norm": 1.788660119927954e-05, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.5078448086569551e-05, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.16150943396226414, | |
| "grad_norm": 2.4111786842695437e-05, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.1630188679245283, | |
| "grad_norm": 2.8707843739539385e-05, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.16452830188679246, | |
| "grad_norm": 4.438353062141687e-05, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.1660377358490566, | |
| "grad_norm": 3.8902497180970386e-05, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.16754716981132076, | |
| "grad_norm": 6.369838956743479e-05, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.16905660377358492, | |
| "grad_norm": 6.360220140777528e-05, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.17056603773584905, | |
| "grad_norm": 4.417836316861212e-05, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.1720754716981132, | |
| "grad_norm": 8.401078230235726e-05, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.17358490566037735, | |
| "grad_norm": 4.5576893171528354e-05, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.1750943396226415, | |
| "grad_norm": 3.908126745955087e-05, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.17660377358490567, | |
| "grad_norm": 4.5852139010094106e-05, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.1781132075471698, | |
| "grad_norm": 5.557672920986079e-05, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.17962264150943397, | |
| "grad_norm": 0.0001369229139527306, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.1811320754716981, | |
| "grad_norm": 6.510502134915441e-05, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.18264150943396226, | |
| "grad_norm": 0.00012901521404273808, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.18415094339622642, | |
| "grad_norm": 7.49451428418979e-05, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.18566037735849056, | |
| "grad_norm": 8.595697727287188e-05, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.18716981132075472, | |
| "grad_norm": 6.461943121394143e-05, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.18867924528301888, | |
| "grad_norm": 5.69835101487115e-05, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.18867924528301888, | |
| "eval_loss": 8.622415066383837e-07, | |
| "eval_runtime": 4.2048, | |
| "eval_samples_per_second": 11.891, | |
| "eval_steps_per_second": 1.665, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.19018867924528302, | |
| "grad_norm": 3.0237964892876334e-05, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.19169811320754718, | |
| "grad_norm": 2.042949381575454e-05, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.1932075471698113, | |
| "grad_norm": 3.0739392968825996e-05, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.19471698113207547, | |
| "grad_norm": 8.033741323743016e-05, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.19622641509433963, | |
| "grad_norm": 6.30953727522865e-05, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.19773584905660377, | |
| "grad_norm": 1.7301101252087392e-05, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.19924528301886793, | |
| "grad_norm": 3.599835326895118e-05, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.20075471698113206, | |
| "grad_norm": 4.0078033634927124e-05, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.20226415094339623, | |
| "grad_norm": 4.6186356485122815e-05, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.2037735849056604, | |
| "grad_norm": 4.505734978010878e-05, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.20528301886792452, | |
| "grad_norm": 4.943280146108009e-05, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.20679245283018868, | |
| "grad_norm": 4.755162444780581e-05, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.20830188679245282, | |
| "grad_norm": 4.70041049993597e-05, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.20981132075471698, | |
| "grad_norm": 3.964366624131799e-05, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.21132075471698114, | |
| "grad_norm": 0.42303475737571716, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 0.0002, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.21283018867924527, | |
| "grad_norm": 0.00010890993871726096, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.21433962264150944, | |
| "grad_norm": 5.2230472647352144e-05, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.2158490566037736, | |
| "grad_norm": 0.9842696785926819, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.0004, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.21735849056603773, | |
| "grad_norm": 3.418095002416521e-05, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.2188679245283019, | |
| "grad_norm": 8.156678086379543e-05, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.22037735849056603, | |
| "grad_norm": 0.0001543686812510714, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.2218867924528302, | |
| "grad_norm": 0.00012703303946182132, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.22339622641509435, | |
| "grad_norm": 0.00015206955140456557, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.22490566037735849, | |
| "grad_norm": 0.0001602250849828124, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.22641509433962265, | |
| "grad_norm": 0.0002219385205535218, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22641509433962265, | |
| "eval_loss": 1.065322521753842e-06, | |
| "eval_runtime": 4.213, | |
| "eval_samples_per_second": 11.868, | |
| "eval_steps_per_second": 1.662, | |
| "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": 2.364765716348928e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |