| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9957173447537473, | |
| "eval_steps": 500, | |
| "global_step": 155, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.15481117367744446, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1213, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.16627414524555206, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1341, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.14720524847507477, | |
| "learning_rate": 6e-05, | |
| "loss": 1.148, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.15325099229812622, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1435, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.16704852879047394, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0895, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.11686641722917557, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0784, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.09641632437705994, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0612, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.12384118884801865, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0566, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.07287071645259857, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0442, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.07469318807125092, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0083, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.08364757895469666, | |
| "learning_rate": 0.00019999761633493753, | |
| "loss": 1.0169, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.07763934135437012, | |
| "learning_rate": 0.0001999904654533872, | |
| "loss": 1.0348, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.06744416803121567, | |
| "learning_rate": 0.0001999785476962552, | |
| "loss": 1.0123, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.07724820077419281, | |
| "learning_rate": 0.00019996186363170035, | |
| "loss": 1.0188, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.0746370479464531, | |
| "learning_rate": 0.00019994041405510705, | |
| "loss": 1.0164, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.055804282426834106, | |
| "learning_rate": 0.00019991419998904747, | |
| "loss": 1.0587, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.054163169115781784, | |
| "learning_rate": 0.00019988322268323268, | |
| "loss": 1.0149, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.05897677689790726, | |
| "learning_rate": 0.00019984748361445308, | |
| "loss": 1.0136, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.05603804066777229, | |
| "learning_rate": 0.00019980698448650804, | |
| "loss": 0.9996, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.06250110268592834, | |
| "learning_rate": 0.0001997617272301248, | |
| "loss": 1.0145, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.05678323656320572, | |
| "learning_rate": 0.000199711714002866, | |
| "loss": 1.0005, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.05278163403272629, | |
| "learning_rate": 0.00019965694718902745, | |
| "loss": 1.0034, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.05601625144481659, | |
| "learning_rate": 0.00019959742939952392, | |
| "loss": 0.9915, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.054547134786844254, | |
| "learning_rate": 0.00019953316347176488, | |
| "loss": 1.0115, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.06417939066886902, | |
| "learning_rate": 0.0001994641524695193, | |
| "loss": 0.9862, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.061326365917921066, | |
| "learning_rate": 0.0001993903996827694, | |
| "loss": 0.9889, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.05376205965876579, | |
| "learning_rate": 0.00019931190862755417, | |
| "loss": 0.9604, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.0678999274969101, | |
| "learning_rate": 0.00019922868304580118, | |
| "loss": 1.0492, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.053755760192871094, | |
| "learning_rate": 0.0001991407269051487, | |
| "loss": 0.9985, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.05401955544948578, | |
| "learning_rate": 0.00019904804439875633, | |
| "loss": 0.9787, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.05666874349117279, | |
| "learning_rate": 0.0001989506399451051, | |
| "loss": 0.9886, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.05425805598497391, | |
| "learning_rate": 0.00019884851818778693, | |
| "loss": 1.0197, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.06086369976401329, | |
| "learning_rate": 0.00019874168399528305, | |
| "loss": 0.9879, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.05577366426587105, | |
| "learning_rate": 0.00019863014246073214, | |
| "loss": 0.9808, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.05853752791881561, | |
| "learning_rate": 0.0001985138989016874, | |
| "loss": 0.957, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.0582735501229763, | |
| "learning_rate": 0.00019839295885986296, | |
| "loss": 0.9732, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.07255622744560242, | |
| "learning_rate": 0.00019826732810086998, | |
| "loss": 1.0199, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.06085599586367607, | |
| "learning_rate": 0.00019813701261394136, | |
| "loss": 0.9946, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.06600817292928696, | |
| "learning_rate": 0.00019800201861164664, | |
| "loss": 0.9646, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.0634196326136589, | |
| "learning_rate": 0.00019786235252959553, | |
| "loss": 1.0092, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.05254920944571495, | |
| "learning_rate": 0.00019771802102613127, | |
| "loss": 0.9535, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.06008182466030121, | |
| "learning_rate": 0.00019756903098201308, | |
| "loss": 0.9897, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.07715290039777756, | |
| "learning_rate": 0.00019741538950008818, | |
| "loss": 1.0132, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.06104297190904617, | |
| "learning_rate": 0.0001972571039049533, | |
| "loss": 0.9938, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.06008582562208176, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 0.9889, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.05699775367975235, | |
| "learning_rate": 0.00019692663078008132, | |
| "loss": 0.9843, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.05760645866394043, | |
| "learning_rate": 0.00019675445900508909, | |
| "loss": 0.9677, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.06075143814086914, | |
| "learning_rate": 0.00019657767462562544, | |
| "loss": 0.9929, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.059820640832185745, | |
| "learning_rate": 0.00019639628606958533, | |
| "loss": 0.9889, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.059315863996744156, | |
| "learning_rate": 0.00019621030198436006, | |
| "loss": 0.9994, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.05949851870536804, | |
| "learning_rate": 0.00019601973123642492, | |
| "loss": 0.9593, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.06036762520670891, | |
| "learning_rate": 0.00019582458291091663, | |
| "loss": 0.9669, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.05799931660294533, | |
| "learning_rate": 0.00019562486631120006, | |
| "loss": 0.9731, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.05733400583267212, | |
| "learning_rate": 0.00019542059095842485, | |
| "loss": 0.9676, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.06894834339618683, | |
| "learning_rate": 0.00019521176659107142, | |
| "loss": 1.0142, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.0657154992222786, | |
| "learning_rate": 0.00019499840316448673, | |
| "loss": 0.9598, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.0570225715637207, | |
| "learning_rate": 0.00019478051085040975, | |
| "loss": 0.9979, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.06271913647651672, | |
| "learning_rate": 0.00019455810003648637, | |
| "loss": 0.9694, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.05831892415881157, | |
| "learning_rate": 0.0001943311813257743, | |
| "loss": 0.9934, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.061948519200086594, | |
| "learning_rate": 0.00019409976553623766, | |
| "loss": 0.9812, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.06726415455341339, | |
| "learning_rate": 0.00019386386370023103, | |
| "loss": 0.9837, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.057408351451158524, | |
| "learning_rate": 0.00019362348706397373, | |
| "loss": 0.9512, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.057638928294181824, | |
| "learning_rate": 0.00019337864708701357, | |
| "loss": 0.9622, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.06090644374489784, | |
| "learning_rate": 0.00019312935544168048, | |
| "loss": 0.9927, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.05811937153339386, | |
| "learning_rate": 0.00019287562401253022, | |
| "loss": 0.9905, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.05927939713001251, | |
| "learning_rate": 0.00019261746489577765, | |
| "loss": 0.9604, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.06021604314446449, | |
| "learning_rate": 0.0001923548903987201, | |
| "loss": 0.9535, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.07004135102033615, | |
| "learning_rate": 0.00019208791303915063, | |
| "loss": 1.0032, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.05626143515110016, | |
| "learning_rate": 0.0001918165455447614, | |
| "loss": 0.9726, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.06130916625261307, | |
| "learning_rate": 0.00019154080085253666, | |
| "loss": 0.9646, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.06467108428478241, | |
| "learning_rate": 0.0001912606921081362, | |
| "loss": 0.9516, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.06047213450074196, | |
| "learning_rate": 0.0001909762326652686, | |
| "loss": 0.9664, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.05907664820551872, | |
| "learning_rate": 0.00019068743608505455, | |
| "loss": 0.9796, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.06679921597242355, | |
| "learning_rate": 0.00019039431613538047, | |
| "loss": 0.9678, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.06133173033595085, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.9875, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.05841493234038353, | |
| "learning_rate": 0.00018979516222907775, | |
| "loss": 0.9686, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.0660431906580925, | |
| "learning_rate": 0.00018948915683609388, | |
| "loss": 0.9863, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.05776617303490639, | |
| "learning_rate": 0.00018917888519957754, | |
| "loss": 0.9417, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.05937017872929573, | |
| "learning_rate": 0.00018886436211120193, | |
| "loss": 0.9995, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.06314114481210709, | |
| "learning_rate": 0.000188545602565321, | |
| "loss": 0.9806, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.060519032180309296, | |
| "learning_rate": 0.00018822262175825462, | |
| "loss": 0.9741, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.06154269725084305, | |
| "learning_rate": 0.00018789543508756408, | |
| "loss": 0.9793, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.06176121160387993, | |
| "learning_rate": 0.00018756405815131813, | |
| "loss": 0.9453, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.06044905260205269, | |
| "learning_rate": 0.00018722850674734927, | |
| "loss": 0.9462, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.05896229296922684, | |
| "learning_rate": 0.00018688879687250067, | |
| "loss": 0.9963, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.06071419641375542, | |
| "learning_rate": 0.0001865449447218635, | |
| "loss": 0.9914, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.0697932317852974, | |
| "learning_rate": 0.00018619696668800492, | |
| "loss": 0.9726, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.062443289905786514, | |
| "learning_rate": 0.00018584487936018661, | |
| "loss": 1.0084, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.059460923075675964, | |
| "learning_rate": 0.0001854886995235738, | |
| "loss": 0.9404, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.058260347694158554, | |
| "learning_rate": 0.00018512844415843514, | |
| "loss": 0.9796, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.05946533381938934, | |
| "learning_rate": 0.00018476413043933313, | |
| "loss": 0.9418, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.06572849303483963, | |
| "learning_rate": 0.00018439577573430555, | |
| "loss": 0.9785, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.06783867627382278, | |
| "learning_rate": 0.00018402339760403713, | |
| "loss": 0.9747, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.06454402953386307, | |
| "learning_rate": 0.00018364701380102266, | |
| "loss": 0.9779, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.06309663504362106, | |
| "learning_rate": 0.00018326664226872065, | |
| "loss": 0.9643, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.05967305600643158, | |
| "learning_rate": 0.00018288230114069765, | |
| "loss": 0.9752, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.05811592936515808, | |
| "learning_rate": 0.0001824940087397641, | |
| "loss": 0.9551, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.0642295628786087, | |
| "learning_rate": 0.00018210178357710058, | |
| "loss": 0.9522, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.05724099278450012, | |
| "learning_rate": 0.0001817056443513754, | |
| "loss": 1.0051, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.056155964732170105, | |
| "learning_rate": 0.00018130560994785325, | |
| "loss": 0.9778, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.058100346475839615, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.9825, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.06120794638991356, | |
| "learning_rate": 0.00018049393207604733, | |
| "loss": 0.9839, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.056975312530994415, | |
| "learning_rate": 0.00018008232730312723, | |
| "loss": 0.9968, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.06239038705825806, | |
| "learning_rate": 0.00017966690474129285, | |
| "loss": 0.9906, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.5958348512649536, | |
| "learning_rate": 0.00017924768419510904, | |
| "loss": 2.6531, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.06554935872554779, | |
| "learning_rate": 0.00017882468565020326, | |
| "loss": 1.0164, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.05698655918240547, | |
| "learning_rate": 0.00017839792927231254, | |
| "loss": 0.9516, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.06186239421367645, | |
| "learning_rate": 0.00017796743540632223, | |
| "loss": 0.9933, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.05811876431107521, | |
| "learning_rate": 0.00017753322457529614, | |
| "loss": 0.9552, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.06247268617153168, | |
| "learning_rate": 0.00017709531747949796, | |
| "loss": 0.9316, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.06278502196073532, | |
| "learning_rate": 0.00017665373499540463, | |
| "loss": 0.9867, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.06079186499118805, | |
| "learning_rate": 0.00017620849817471092, | |
| "loss": 1.0233, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.05586745962500572, | |
| "learning_rate": 0.00017575962824332596, | |
| "loss": 0.9454, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.059647805988788605, | |
| "learning_rate": 0.00017530714660036112, | |
| "loss": 0.9718, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.060143355280160904, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.9927, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.4768543541431427, | |
| "learning_rate": 0.0001743914346360205, | |
| "loss": 2.4526, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.059104178100824356, | |
| "learning_rate": 0.00017392824796965702, | |
| "loss": 0.9366, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.06858639419078827, | |
| "learning_rate": 0.00017346153689965727, | |
| "loss": 0.9783, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.06308155506849289, | |
| "learning_rate": 0.00017299132367567857, | |
| "loss": 0.9688, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.0601269006729126, | |
| "learning_rate": 0.00017251763071433765, | |
| "loss": 0.9937, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.06544536352157593, | |
| "learning_rate": 0.00017204048059814175, | |
| "loss": 0.9351, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.06467759609222412, | |
| "learning_rate": 0.00017155989607441213, | |
| "loss": 0.9918, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.061619073152542114, | |
| "learning_rate": 0.0001710759000541995, | |
| "loss": 0.9872, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.06122846156358719, | |
| "learning_rate": 0.00017058851561119198, | |
| "loss": 0.968, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.08277314156293869, | |
| "learning_rate": 0.00017009776598061495, | |
| "loss": 0.9869, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.07559008151292801, | |
| "learning_rate": 0.00016960367455812336, | |
| "loss": 0.9804, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.06251110136508942, | |
| "learning_rate": 0.00016910626489868649, | |
| "loss": 0.978, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.06253345310688019, | |
| "learning_rate": 0.0001686055607154648, | |
| "loss": 0.9524, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.05948334559798241, | |
| "learning_rate": 0.00016810158587867973, | |
| "loss": 0.9826, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.06356865167617798, | |
| "learning_rate": 0.00016759436441447545, | |
| "loss": 0.9805, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.06536010652780533, | |
| "learning_rate": 0.00016708392050377363, | |
| "loss": 1.0146, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.06137322261929512, | |
| "learning_rate": 0.00016657027848112062, | |
| "loss": 0.9457, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.05955340713262558, | |
| "learning_rate": 0.00016605346283352727, | |
| "loss": 0.9823, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.0602475143969059, | |
| "learning_rate": 0.00016553349819930165, | |
| "loss": 1.0077, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.05905039981007576, | |
| "learning_rate": 0.00016501040936687443, | |
| "loss": 0.9313, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.06087419390678406, | |
| "learning_rate": 0.00016448422127361706, | |
| "loss": 0.9725, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.059714119881391525, | |
| "learning_rate": 0.00016395495900465304, | |
| "loss": 0.9963, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.06461544334888458, | |
| "learning_rate": 0.000163422647791662, | |
| "loss": 0.957, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.06247726082801819, | |
| "learning_rate": 0.00016288731301167668, | |
| "loss": 0.9742, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.06527213007211685, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.9789, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.059757690876722336, | |
| "learning_rate": 0.00016180767497835503, | |
| "loss": 0.9309, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.059084221720695496, | |
| "learning_rate": 0.00016126342319492784, | |
| "loss": 0.9546, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 1.778961181640625, | |
| "learning_rate": 0.00016071625078187114, | |
| "loss": 2.6066, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.06468740105628967, | |
| "learning_rate": 0.00016016618382470012, | |
| "loss": 0.9472, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.061647091060876846, | |
| "learning_rate": 0.00015961324854692254, | |
| "loss": 0.9836, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.06061193719506264, | |
| "learning_rate": 0.0001590574713087885, | |
| "loss": 0.982, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.06635820865631104, | |
| "learning_rate": 0.00015849887860603374, | |
| "loss": 0.9873, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.06260058283805847, | |
| "learning_rate": 0.00015793749706861636, | |
| "loss": 0.9827, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.06037148833274841, | |
| "learning_rate": 0.00015737335345944757, | |
| "loss": 1.0072, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.06277037411928177, | |
| "learning_rate": 0.00015680647467311557, | |
| "loss": 0.9498, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.06306284666061401, | |
| "learning_rate": 0.00015623688773460357, | |
| "loss": 0.9866, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.07311715185642242, | |
| "learning_rate": 0.00015566461979800122, | |
| "loss": 0.9722, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.06143077090382576, | |
| "learning_rate": 0.00015508969814521025, | |
| "loss": 0.9442, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.067879818379879, | |
| "learning_rate": 0.00015451215018464387, | |
| "loss": 0.9416, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.06907378137111664, | |
| "learning_rate": 0.00015393200344991995, | |
| "loss": 0.9813, | |
| "step": 155 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 465, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 155, | |
| "total_flos": 3.361969685082931e+18, | |
| "train_batch_size": 5, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |