| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5028013216491883, | |
| "eval_steps": 500, | |
| "global_step": 7000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007182876023559833, | |
| "grad_norm": 102.55565643310547, | |
| "learning_rate": 3.339317773788151e-07, | |
| "loss": 4.51, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.014365752047119667, | |
| "grad_norm": 20.8671875, | |
| "learning_rate": 6.929982046678636e-07, | |
| "loss": 1.3058, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0215486280706795, | |
| "grad_norm": 16.238826751708984, | |
| "learning_rate": 1.0520646319569122e-06, | |
| "loss": 0.7671, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.028731504094239333, | |
| "grad_norm": 12.669879913330078, | |
| "learning_rate": 1.4111310592459606e-06, | |
| "loss": 0.639, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.03591438011779917, | |
| "grad_norm": 13.375199317932129, | |
| "learning_rate": 1.770197486535009e-06, | |
| "loss": 0.5396, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.043097256141359, | |
| "grad_norm": 36.680416107177734, | |
| "learning_rate": 2.1292639138240576e-06, | |
| "loss": 0.4649, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.050280132164918834, | |
| "grad_norm": 15.553112983703613, | |
| "learning_rate": 2.488330341113106e-06, | |
| "loss": 0.4561, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.057463008188478666, | |
| "grad_norm": 28.032434463500977, | |
| "learning_rate": 2.847396768402155e-06, | |
| "loss": 0.4152, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.0646458842120385, | |
| "grad_norm": 40.55122756958008, | |
| "learning_rate": 3.2064631956912027e-06, | |
| "loss": 0.412, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.07182876023559834, | |
| "grad_norm": 48.380340576171875, | |
| "learning_rate": 3.5655296229802514e-06, | |
| "loss": 0.4159, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.07901163625915816, | |
| "grad_norm": 18.708255767822266, | |
| "learning_rate": 3.9245960502693e-06, | |
| "loss": 0.3397, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.086194512282718, | |
| "grad_norm": 10.165841102600098, | |
| "learning_rate": 4.283662477558348e-06, | |
| "loss": 0.355, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.09337738830627783, | |
| "grad_norm": 17.107013702392578, | |
| "learning_rate": 4.6427289048473974e-06, | |
| "loss": 0.3312, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.10056026432983767, | |
| "grad_norm": 38.87083053588867, | |
| "learning_rate": 5.001795332136446e-06, | |
| "loss": 0.2452, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.1077431403533975, | |
| "grad_norm": 17.743247985839844, | |
| "learning_rate": 5.360861759425494e-06, | |
| "loss": 0.2204, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.11492601637695733, | |
| "grad_norm": 35.18050765991211, | |
| "learning_rate": 5.719928186714543e-06, | |
| "loss": 0.2338, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.12210889240051717, | |
| "grad_norm": 8.888273239135742, | |
| "learning_rate": 6.078994614003591e-06, | |
| "loss": 0.2269, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.129291768424077, | |
| "grad_norm": 6.807362079620361, | |
| "learning_rate": 6.4380610412926396e-06, | |
| "loss": 0.233, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.13647464444763682, | |
| "grad_norm": 3.313542366027832, | |
| "learning_rate": 6.797127468581688e-06, | |
| "loss": 0.2033, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.14365752047119668, | |
| "grad_norm": 4.184378623962402, | |
| "learning_rate": 7.156193895870737e-06, | |
| "loss": 0.1904, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1508403964947565, | |
| "grad_norm": 29.64693832397461, | |
| "learning_rate": 7.515260323159785e-06, | |
| "loss": 0.2063, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.15802327251831633, | |
| "grad_norm": 19.15960121154785, | |
| "learning_rate": 7.874326750448834e-06, | |
| "loss": 0.2206, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.16520614854187618, | |
| "grad_norm": 12.115074157714844, | |
| "learning_rate": 8.233393177737883e-06, | |
| "loss": 0.1949, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.172389024565436, | |
| "grad_norm": 9.53875732421875, | |
| "learning_rate": 8.59245960502693e-06, | |
| "loss": 0.2, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.17957190058899583, | |
| "grad_norm": 3.5382916927337646, | |
| "learning_rate": 8.951526032315979e-06, | |
| "loss": 0.1875, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.18675477661255566, | |
| "grad_norm": 1.2547463178634644, | |
| "learning_rate": 9.310592459605027e-06, | |
| "loss": 0.2033, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.1939376526361155, | |
| "grad_norm": 1.9213370084762573, | |
| "learning_rate": 9.669658886894077e-06, | |
| "loss": 0.1946, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.20112052865967533, | |
| "grad_norm": 35.58647155761719, | |
| "learning_rate": 9.996807534219244e-06, | |
| "loss": 0.2231, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.20830340468323516, | |
| "grad_norm": 3.3178770542144775, | |
| "learning_rate": 9.956901711959775e-06, | |
| "loss": 0.1868, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.215486280706795, | |
| "grad_norm": 22.328224182128906, | |
| "learning_rate": 9.916995889700309e-06, | |
| "loss": 0.2107, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.22266915673035484, | |
| "grad_norm": 28.90311050415039, | |
| "learning_rate": 9.877090067440841e-06, | |
| "loss": 0.2068, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.22985203275391466, | |
| "grad_norm": 4.699060916900635, | |
| "learning_rate": 9.837184245181373e-06, | |
| "loss": 0.1987, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.2370349087774745, | |
| "grad_norm": 16.968143463134766, | |
| "learning_rate": 9.797278422921906e-06, | |
| "loss": 0.1688, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.24421778480103434, | |
| "grad_norm": 8.749013900756836, | |
| "learning_rate": 9.757372600662436e-06, | |
| "loss": 0.1803, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.25140066082459417, | |
| "grad_norm": 16.449424743652344, | |
| "learning_rate": 9.71746677840297e-06, | |
| "loss": 0.2231, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.258583536848154, | |
| "grad_norm": 0.8674511313438416, | |
| "learning_rate": 9.677560956143502e-06, | |
| "loss": 0.1853, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.2657664128717138, | |
| "grad_norm": 6.190998554229736, | |
| "learning_rate": 9.637655133884035e-06, | |
| "loss": 0.1669, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.27294928889527365, | |
| "grad_norm": 10.102142333984375, | |
| "learning_rate": 9.597749311624567e-06, | |
| "loss": 0.2075, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.2801321649188335, | |
| "grad_norm": 22.571224212646484, | |
| "learning_rate": 9.557843489365099e-06, | |
| "loss": 0.2019, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.28731504094239335, | |
| "grad_norm": 29.87354278564453, | |
| "learning_rate": 9.517937667105631e-06, | |
| "loss": 0.2022, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2944979169659532, | |
| "grad_norm": 4.910442352294922, | |
| "learning_rate": 9.478031844846164e-06, | |
| "loss": 0.1816, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.301680792989513, | |
| "grad_norm": 18.66014289855957, | |
| "learning_rate": 9.438126022586697e-06, | |
| "loss": 0.1998, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.30886366901307283, | |
| "grad_norm": 42.844818115234375, | |
| "learning_rate": 9.398220200327228e-06, | |
| "loss": 0.193, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.31604654503663265, | |
| "grad_norm": 8.83779525756836, | |
| "learning_rate": 9.35831437806776e-06, | |
| "loss": 0.1681, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.3232294210601925, | |
| "grad_norm": 3.474717140197754, | |
| "learning_rate": 9.318408555808294e-06, | |
| "loss": 0.1608, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.33041229708375236, | |
| "grad_norm": 4.746242046356201, | |
| "learning_rate": 9.278502733548825e-06, | |
| "loss": 0.1552, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.3375951731073122, | |
| "grad_norm": 4.5783915519714355, | |
| "learning_rate": 9.238596911289359e-06, | |
| "loss": 0.1646, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.344778049130872, | |
| "grad_norm": 9.975970268249512, | |
| "learning_rate": 9.198691089029889e-06, | |
| "loss": 0.1791, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.35196092515443184, | |
| "grad_norm": 1.2798261642456055, | |
| "learning_rate": 9.158785266770423e-06, | |
| "loss": 0.1842, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.35914380117799166, | |
| "grad_norm": 6.015448570251465, | |
| "learning_rate": 9.118879444510955e-06, | |
| "loss": 0.1751, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.3663266772015515, | |
| "grad_norm": 7.062718391418457, | |
| "learning_rate": 9.078973622251488e-06, | |
| "loss": 0.1751, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.3735095532251113, | |
| "grad_norm": 0.9326837062835693, | |
| "learning_rate": 9.03906779999202e-06, | |
| "loss": 0.1646, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.3806924292486712, | |
| "grad_norm": 1.695087194442749, | |
| "learning_rate": 8.999161977732552e-06, | |
| "loss": 0.1577, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.387875305272231, | |
| "grad_norm": 19.320249557495117, | |
| "learning_rate": 8.959256155473084e-06, | |
| "loss": 0.1729, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.39505818129579084, | |
| "grad_norm": 3.8522274494171143, | |
| "learning_rate": 8.919350333213616e-06, | |
| "loss": 0.1781, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.40224105731935067, | |
| "grad_norm": 2.3610100746154785, | |
| "learning_rate": 8.879444510954149e-06, | |
| "loss": 0.1975, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.4094239333429105, | |
| "grad_norm": 6.998334884643555, | |
| "learning_rate": 8.839538688694681e-06, | |
| "loss": 0.1629, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.4166068093664703, | |
| "grad_norm": 15.58069896697998, | |
| "learning_rate": 8.799632866435213e-06, | |
| "loss": 0.1764, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.42378968539003015, | |
| "grad_norm": 40.70027160644531, | |
| "learning_rate": 8.759727044175747e-06, | |
| "loss": 0.1923, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.43097256141359, | |
| "grad_norm": 8.034761428833008, | |
| "learning_rate": 8.719821221916278e-06, | |
| "loss": 0.1795, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.43815543743714985, | |
| "grad_norm": 1.1275875568389893, | |
| "learning_rate": 8.679915399656812e-06, | |
| "loss": 0.1477, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.4453383134607097, | |
| "grad_norm": 8.35661792755127, | |
| "learning_rate": 8.640009577397342e-06, | |
| "loss": 0.1687, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.4525211894842695, | |
| "grad_norm": 19.17778968811035, | |
| "learning_rate": 8.600103755137876e-06, | |
| "loss": 0.1409, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.45970406550782933, | |
| "grad_norm": 22.45587730407715, | |
| "learning_rate": 8.560197932878408e-06, | |
| "loss": 0.1676, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.46688694153138915, | |
| "grad_norm": 27.29585075378418, | |
| "learning_rate": 8.520292110618939e-06, | |
| "loss": 0.1656, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.474069817554949, | |
| "grad_norm": 2.3996095657348633, | |
| "learning_rate": 8.480386288359473e-06, | |
| "loss": 0.1622, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.48125269357850886, | |
| "grad_norm": 15.577359199523926, | |
| "learning_rate": 8.440480466100005e-06, | |
| "loss": 0.1748, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.4884355696020687, | |
| "grad_norm": 16.934419631958008, | |
| "learning_rate": 8.400574643840537e-06, | |
| "loss": 0.1689, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.4956184456256285, | |
| "grad_norm": 2.9546115398406982, | |
| "learning_rate": 8.36066882158107e-06, | |
| "loss": 0.1695, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.5028013216491883, | |
| "grad_norm": 2.370490550994873, | |
| "learning_rate": 8.320762999321602e-06, | |
| "loss": 0.1396, | |
| "step": 7000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 27844, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |