| { | |
| "best_metric": 1.9268525838851929, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 2.0073319755600814, | |
| "eval_steps": 25, | |
| "global_step": 154, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013034623217922607, | |
| "grad_norm": 0.6276217103004456, | |
| "learning_rate": 7.5e-05, | |
| "loss": 2.9674, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013034623217922607, | |
| "eval_loss": 3.5546200275421143, | |
| "eval_runtime": 0.2814, | |
| "eval_samples_per_second": 177.672, | |
| "eval_steps_per_second": 46.195, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026069246435845215, | |
| "grad_norm": 0.6501481533050537, | |
| "learning_rate": 0.00015, | |
| "loss": 3.2018, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.039103869653767824, | |
| "grad_norm": 0.5839198231697083, | |
| "learning_rate": 0.000225, | |
| "loss": 3.3157, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05213849287169043, | |
| "grad_norm": 0.5366824865341187, | |
| "learning_rate": 0.0003, | |
| "loss": 3.3337, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06517311608961303, | |
| "grad_norm": 0.4950920641422272, | |
| "learning_rate": 0.0002999703922691041, | |
| "loss": 3.3257, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07820773930753565, | |
| "grad_norm": 0.4459711015224457, | |
| "learning_rate": 0.00029988158206334587, | |
| "loss": 3.2473, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09124236252545825, | |
| "grad_norm": 0.5029334425926208, | |
| "learning_rate": 0.00029973360833781664, | |
| "loss": 3.251, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10427698574338086, | |
| "grad_norm": 0.5529475808143616, | |
| "learning_rate": 0.0002995265359986831, | |
| "loss": 3.212, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11731160896130347, | |
| "grad_norm": 0.6158551573753357, | |
| "learning_rate": 0.00029926045587471686, | |
| "loss": 3.1893, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13034623217922606, | |
| "grad_norm": 0.6573907136917114, | |
| "learning_rate": 0.0002989354846774545, | |
| "loss": 3.1782, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14338085539714868, | |
| "grad_norm": 0.6919009685516357, | |
| "learning_rate": 0.0002985517649500034, | |
| "loss": 3.0629, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1564154786150713, | |
| "grad_norm": 0.7953146696090698, | |
| "learning_rate": 0.00029810946500451814, | |
| "loss": 3.132, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1694501018329939, | |
| "grad_norm": 0.9705007672309875, | |
| "learning_rate": 0.00029760877884837294, | |
| "loss": 2.7258, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1824847250509165, | |
| "grad_norm": 0.9804863333702087, | |
| "learning_rate": 0.0002970499260990637, | |
| "loss": 2.7512, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1955193482688391, | |
| "grad_norm": 0.6821589469909668, | |
| "learning_rate": 0.0002964331518878766, | |
| "loss": 2.6437, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20855397148676172, | |
| "grad_norm": 0.4936249554157257, | |
| "learning_rate": 0.0002957587267523652, | |
| "loss": 2.6137, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2215885947046843, | |
| "grad_norm": 0.5652141571044922, | |
| "learning_rate": 0.00029502694651768383, | |
| "loss": 2.6432, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23462321792260693, | |
| "grad_norm": 0.6153628826141357, | |
| "learning_rate": 0.000294238132166829, | |
| "loss": 2.6485, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24765784114052952, | |
| "grad_norm": 0.4337889552116394, | |
| "learning_rate": 0.0002933926296998457, | |
| "loss": 2.5919, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2606924643584521, | |
| "grad_norm": 0.5410802364349365, | |
| "learning_rate": 0.0002924908099820599, | |
| "loss": 2.6103, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27372708757637476, | |
| "grad_norm": 0.5030240416526794, | |
| "learning_rate": 0.00029153306858140533, | |
| "loss": 2.6104, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.28676171079429735, | |
| "grad_norm": 0.38985803723335266, | |
| "learning_rate": 0.00029051982559491393, | |
| "loss": 2.5794, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.29979633401221994, | |
| "grad_norm": 0.5979215502738953, | |
| "learning_rate": 0.00028945152546444754, | |
| "loss": 2.6287, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3128309572301426, | |
| "grad_norm": 0.5737847089767456, | |
| "learning_rate": 0.0002883286367817511, | |
| "loss": 2.6541, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3258655804480652, | |
| "grad_norm": 0.572758138179779, | |
| "learning_rate": 0.00028715165208291265, | |
| "loss": 2.6881, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3258655804480652, | |
| "eval_loss": 2.5153815746307373, | |
| "eval_runtime": 0.2797, | |
| "eval_samples_per_second": 178.771, | |
| "eval_steps_per_second": 46.481, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3389002036659878, | |
| "grad_norm": 1.4206351041793823, | |
| "learning_rate": 0.0002859210876323207, | |
| "loss": 2.4658, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.35193482688391037, | |
| "grad_norm": 1.5302618741989136, | |
| "learning_rate": 0.00028463748319621396, | |
| "loss": 2.5304, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.364969450101833, | |
| "grad_norm": 0.9723348021507263, | |
| "learning_rate": 0.00028330140180592156, | |
| "loss": 2.4213, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3780040733197556, | |
| "grad_norm": 0.4521373212337494, | |
| "learning_rate": 0.0002819134295108992, | |
| "loss": 2.4048, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3910386965376782, | |
| "grad_norm": 0.6521058678627014, | |
| "learning_rate": 0.00028047417512166837, | |
| "loss": 2.4019, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4040733197556008, | |
| "grad_norm": 0.7668533325195312, | |
| "learning_rate": 0.00027898426994277204, | |
| "loss": 2.4534, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.41710794297352344, | |
| "grad_norm": 0.791877269744873, | |
| "learning_rate": 0.0002774443674958634, | |
| "loss": 2.4232, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.43014256619144603, | |
| "grad_norm": 0.814365565776825, | |
| "learning_rate": 0.00027585514323305, | |
| "loss": 2.4323, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4431771894093686, | |
| "grad_norm": 0.6510496735572815, | |
| "learning_rate": 0.00027421729424061787, | |
| "loss": 2.3904, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45621181262729127, | |
| "grad_norm": 0.42264309525489807, | |
| "learning_rate": 0.00027253153893326646, | |
| "loss": 2.4016, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.46924643584521386, | |
| "grad_norm": 0.5813013911247253, | |
| "learning_rate": 0.0002707986167389884, | |
| "loss": 2.4511, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.48228105906313645, | |
| "grad_norm": 0.8300145864486694, | |
| "learning_rate": 0.0002690192877747315, | |
| "loss": 2.4128, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.49531568228105904, | |
| "grad_norm": 0.7689920663833618, | |
| "learning_rate": 0.0002671943325129871, | |
| "loss": 2.3281, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5083503054989816, | |
| "grad_norm": 1.024122953414917, | |
| "learning_rate": 0.0002653245514394482, | |
| "loss": 2.3381, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5213849287169042, | |
| "grad_norm": 0.6759045720100403, | |
| "learning_rate": 0.0002634107647018905, | |
| "loss": 2.3008, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5344195519348269, | |
| "grad_norm": 0.3922083377838135, | |
| "learning_rate": 0.0002614538117504284, | |
| "loss": 2.2719, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5474541751527495, | |
| "grad_norm": 0.5142776966094971, | |
| "learning_rate": 0.0002594545509693043, | |
| "loss": 2.276, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5604887983706721, | |
| "grad_norm": 0.6373997926712036, | |
| "learning_rate": 0.00025741385930037295, | |
| "loss": 2.2602, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5735234215885947, | |
| "grad_norm": 0.6760398149490356, | |
| "learning_rate": 0.00025533263185844587, | |
| "loss": 2.3169, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5865580448065173, | |
| "grad_norm": 0.7617467045783997, | |
| "learning_rate": 0.00025321178153866423, | |
| "loss": 2.2778, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5995926680244399, | |
| "grad_norm": 0.7649106979370117, | |
| "learning_rate": 0.00025105223861607306, | |
| "loss": 2.2692, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6126272912423625, | |
| "grad_norm": 0.6090757250785828, | |
| "learning_rate": 0.0002488549503375719, | |
| "loss": 2.2845, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6256619144602852, | |
| "grad_norm": 0.45042526721954346, | |
| "learning_rate": 0.0002466208805064206, | |
| "loss": 2.2431, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6386965376782078, | |
| "grad_norm": 0.46896523237228394, | |
| "learning_rate": 0.00024435100905948387, | |
| "loss": 2.2985, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6517311608961304, | |
| "grad_norm": 0.5649595260620117, | |
| "learning_rate": 0.00024204633163739828, | |
| "loss": 2.4211, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6517311608961304, | |
| "eval_loss": 2.2425832748413086, | |
| "eval_runtime": 0.2798, | |
| "eval_samples_per_second": 178.69, | |
| "eval_steps_per_second": 46.46, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.664765784114053, | |
| "grad_norm": 1.1472358703613281, | |
| "learning_rate": 0.00023970785914785144, | |
| "loss": 2.2791, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.6778004073319756, | |
| "grad_norm": 1.3499984741210938, | |
| "learning_rate": 0.00023733661732216452, | |
| "loss": 2.3292, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.6908350305498981, | |
| "grad_norm": 1.2178796529769897, | |
| "learning_rate": 0.00023493364626537257, | |
| "loss": 2.2938, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7038696537678207, | |
| "grad_norm": 0.9463868737220764, | |
| "learning_rate": 0.00023249999999999999, | |
| "loss": 2.2173, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7169042769857433, | |
| "grad_norm": 0.5750055909156799, | |
| "learning_rate": 0.00023003674600373153, | |
| "loss": 2.2036, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.729938900203666, | |
| "grad_norm": 0.3371862769126892, | |
| "learning_rate": 0.00022754496474118133, | |
| "loss": 2.167, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7429735234215886, | |
| "grad_norm": 0.6258431673049927, | |
| "learning_rate": 0.00022502574918996517, | |
| "loss": 2.2211, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7560081466395112, | |
| "grad_norm": 0.7280526161193848, | |
| "learning_rate": 0.00022248020436128478, | |
| "loss": 2.2122, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.7690427698574338, | |
| "grad_norm": 0.8275133371353149, | |
| "learning_rate": 0.00021990944681523302, | |
| "loss": 2.2137, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.7820773930753564, | |
| "grad_norm": 0.8840050101280212, | |
| "learning_rate": 0.0002173146041710339, | |
| "loss": 2.2311, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.795112016293279, | |
| "grad_norm": 0.957916796207428, | |
| "learning_rate": 0.00021469681461243153, | |
| "loss": 2.2478, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.8081466395112016, | |
| "grad_norm": 1.0393691062927246, | |
| "learning_rate": 0.00021205722638844505, | |
| "loss": 2.2579, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8211812627291243, | |
| "grad_norm": 0.3389835059642792, | |
| "learning_rate": 0.00020939699730970873, | |
| "loss": 2.1799, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.8342158859470469, | |
| "grad_norm": 0.5756048560142517, | |
| "learning_rate": 0.00020671729424061788, | |
| "loss": 2.1684, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8472505091649695, | |
| "grad_norm": 0.7830222249031067, | |
| "learning_rate": 0.00020401929258750365, | |
| "loss": 2.1438, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8602851323828921, | |
| "grad_norm": 0.8117411732673645, | |
| "learning_rate": 0.00020130417578306082, | |
| "loss": 2.1536, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.8733197556008147, | |
| "grad_norm": 0.7848119735717773, | |
| "learning_rate": 0.0001985731347672554, | |
| "loss": 2.129, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.8863543788187372, | |
| "grad_norm": 0.6703603863716125, | |
| "learning_rate": 0.00019582736746493853, | |
| "loss": 2.152, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.8993890020366598, | |
| "grad_norm": 0.4845719635486603, | |
| "learning_rate": 0.00019306807826039747, | |
| "loss": 2.1237, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.9124236252545825, | |
| "grad_norm": 0.3355918228626251, | |
| "learning_rate": 0.00019029647746907283, | |
| "loss": 2.0711, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9254582484725051, | |
| "grad_norm": 0.33707523345947266, | |
| "learning_rate": 0.00018751378080667378, | |
| "loss": 2.1033, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.9384928716904277, | |
| "grad_norm": 0.5474686622619629, | |
| "learning_rate": 0.00018472120885592555, | |
| "loss": 2.0707, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.9515274949083503, | |
| "grad_norm": 0.71000075340271, | |
| "learning_rate": 0.00018191998653118108, | |
| "loss": 2.1169, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.9645621181262729, | |
| "grad_norm": 0.8560431003570557, | |
| "learning_rate": 0.0001791113425411332, | |
| "loss": 2.176, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.9775967413441955, | |
| "grad_norm": 1.2276349067687988, | |
| "learning_rate": 0.0001762965088498626, | |
| "loss": 2.2966, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.9775967413441955, | |
| "eval_loss": 2.044175148010254, | |
| "eval_runtime": 0.2806, | |
| "eval_samples_per_second": 178.197, | |
| "eval_steps_per_second": 46.331, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.9906313645621181, | |
| "grad_norm": 0.28324252367019653, | |
| "learning_rate": 0.0001734767201364573, | |
| "loss": 2.0594, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.0036659877800407, | |
| "grad_norm": 0.4252139627933502, | |
| "learning_rate": 0.00017065321325344194, | |
| "loss": 2.9023, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.0167006109979633, | |
| "grad_norm": 0.532595157623291, | |
| "learning_rate": 0.00016782722668425316, | |
| "loss": 1.9476, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.0297352342158859, | |
| "grad_norm": 0.696269690990448, | |
| "learning_rate": 0.000165, | |
| "loss": 2.089, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.0427698574338085, | |
| "grad_norm": 0.6571292281150818, | |
| "learning_rate": 0.00016217277331574678, | |
| "loss": 2.0514, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.055804480651731, | |
| "grad_norm": 0.5735260248184204, | |
| "learning_rate": 0.00015934678674655805, | |
| "loss": 2.0645, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.0688391038696539, | |
| "grad_norm": 0.418550968170166, | |
| "learning_rate": 0.0001565232798635427, | |
| "loss": 2.0639, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.0818737270875765, | |
| "grad_norm": 0.32165512442588806, | |
| "learning_rate": 0.00015370349115013742, | |
| "loss": 2.0412, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.094908350305499, | |
| "grad_norm": 0.3411344289779663, | |
| "learning_rate": 0.0001508886574588668, | |
| "loss": 2.0738, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.1079429735234216, | |
| "grad_norm": 0.4526989459991455, | |
| "learning_rate": 0.0001480800134688189, | |
| "loss": 2.0482, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.1209775967413442, | |
| "grad_norm": 0.5264050960540771, | |
| "learning_rate": 0.00014527879114407445, | |
| "loss": 2.0155, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.1340122199592668, | |
| "grad_norm": 0.6333541870117188, | |
| "learning_rate": 0.0001424862191933262, | |
| "loss": 2.029, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.1470468431771894, | |
| "grad_norm": 0.6475998759269714, | |
| "learning_rate": 0.00013970352253092714, | |
| "loss": 2.0732, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.160081466395112, | |
| "grad_norm": 0.5682183504104614, | |
| "learning_rate": 0.00013693192173960253, | |
| "loss": 1.6717, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.1731160896130346, | |
| "grad_norm": 0.48593777418136597, | |
| "learning_rate": 0.00013417263253506147, | |
| "loss": 2.5498, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1861507128309572, | |
| "grad_norm": 0.517917811870575, | |
| "learning_rate": 0.00013142686523274463, | |
| "loss": 2.0097, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.1991853360488798, | |
| "grad_norm": 0.5828862190246582, | |
| "learning_rate": 0.00012869582421693912, | |
| "loss": 1.9987, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.2122199592668024, | |
| "grad_norm": 0.5273678302764893, | |
| "learning_rate": 0.00012598070741249632, | |
| "loss": 2.0205, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.225254582484725, | |
| "grad_norm": 0.49020346999168396, | |
| "learning_rate": 0.00012328270575938212, | |
| "loss": 1.9981, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.2382892057026478, | |
| "grad_norm": 0.35303086042404175, | |
| "learning_rate": 0.00012060300269029128, | |
| "loss": 1.9699, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.2513238289205701, | |
| "grad_norm": 0.27531367540359497, | |
| "learning_rate": 0.00011794277361155495, | |
| "loss": 2.0035, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.264358452138493, | |
| "grad_norm": 0.31903597712516785, | |
| "learning_rate": 0.00011530318538756846, | |
| "loss": 1.9783, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.2773930753564156, | |
| "grad_norm": 0.43081673979759216, | |
| "learning_rate": 0.0001126853958289661, | |
| "loss": 2.0053, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.2904276985743381, | |
| "grad_norm": 0.5114902257919312, | |
| "learning_rate": 0.00011009055318476698, | |
| "loss": 2.0032, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.3034623217922607, | |
| "grad_norm": 0.6454872488975525, | |
| "learning_rate": 0.00010751979563871518, | |
| "loss": 2.0436, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.3034623217922607, | |
| "eval_loss": 1.9786142110824585, | |
| "eval_runtime": 0.2787, | |
| "eval_samples_per_second": 179.386, | |
| "eval_steps_per_second": 46.64, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.3164969450101833, | |
| "grad_norm": 0.7522782683372498, | |
| "learning_rate": 0.00010497425081003482, | |
| "loss": 2.1272, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.329531568228106, | |
| "grad_norm": 0.7502726316452026, | |
| "learning_rate": 0.0001024550352588187, | |
| "loss": 2.2586, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.3425661914460285, | |
| "grad_norm": 0.4233168661594391, | |
| "learning_rate": 9.996325399626841e-05, | |
| "loss": 1.871, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.355600814663951, | |
| "grad_norm": 0.5849415063858032, | |
| "learning_rate": 9.750000000000003e-05, | |
| "loss": 1.9998, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.3686354378818737, | |
| "grad_norm": 0.5961419343948364, | |
| "learning_rate": 9.506635373462745e-05, | |
| "loss": 2.0286, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.3816700610997963, | |
| "grad_norm": 0.5850256085395813, | |
| "learning_rate": 9.266338267783541e-05, | |
| "loss": 1.9748, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.3947046843177189, | |
| "grad_norm": 0.5355044007301331, | |
| "learning_rate": 9.029214085214857e-05, | |
| "loss": 1.9777, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.4077393075356415, | |
| "grad_norm": 0.40355584025382996, | |
| "learning_rate": 8.795366836260173e-05, | |
| "loss": 1.9819, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.420773930753564, | |
| "grad_norm": 0.30112820863723755, | |
| "learning_rate": 8.564899094051614e-05, | |
| "loss": 1.9478, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.4338085539714869, | |
| "grad_norm": 0.286545068025589, | |
| "learning_rate": 8.33791194935794e-05, | |
| "loss": 1.9474, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.4468431771894092, | |
| "grad_norm": 0.3926275372505188, | |
| "learning_rate": 8.11450496624281e-05, | |
| "loss": 1.9474, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.459877800407332, | |
| "grad_norm": 0.5009521245956421, | |
| "learning_rate": 7.894776138392688e-05, | |
| "loss": 2.0219, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.4729124236252547, | |
| "grad_norm": 0.6338520646095276, | |
| "learning_rate": 7.678821846133576e-05, | |
| "loss": 2.0353, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.4859470468431772, | |
| "grad_norm": 0.7013182044029236, | |
| "learning_rate": 7.466736814155418e-05, | |
| "loss": 1.62, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.4989816700610998, | |
| "grad_norm": 0.40693536400794983, | |
| "learning_rate": 7.258614069962701e-05, | |
| "loss": 2.5179, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.5120162932790224, | |
| "grad_norm": 0.31738847494125366, | |
| "learning_rate": 7.054544903069565e-05, | |
| "loss": 1.9209, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.525050916496945, | |
| "grad_norm": 0.3408113718032837, | |
| "learning_rate": 6.854618824957157e-05, | |
| "loss": 1.9408, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.5380855397148676, | |
| "grad_norm": 0.30903321504592896, | |
| "learning_rate": 6.658923529810946e-05, | |
| "loss": 1.9548, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.5511201629327902, | |
| "grad_norm": 0.30865398049354553, | |
| "learning_rate": 6.467544856055175e-05, | |
| "loss": 1.9355, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.5641547861507128, | |
| "grad_norm": 0.2949885427951813, | |
| "learning_rate": 6.28056674870129e-05, | |
| "loss": 1.9534, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.5771894093686354, | |
| "grad_norm": 0.28894004225730896, | |
| "learning_rate": 6.098071222526847e-05, | |
| "loss": 1.9511, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.590224032586558, | |
| "grad_norm": 0.2710161507129669, | |
| "learning_rate": 5.9201383261011636e-05, | |
| "loss": 1.9424, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.6032586558044808, | |
| "grad_norm": 0.30530881881713867, | |
| "learning_rate": 5.7468461066733505e-05, | |
| "loss": 1.9794, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.6162932790224032, | |
| "grad_norm": 0.3637678027153015, | |
| "learning_rate": 5.578270575938211e-05, | |
| "loss": 1.9562, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.629327902240326, | |
| "grad_norm": 0.4117651581764221, | |
| "learning_rate": 5.4144856766949957e-05, | |
| "loss": 1.9505, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.629327902240326, | |
| "eval_loss": 1.9424113035202026, | |
| "eval_runtime": 0.2795, | |
| "eval_samples_per_second": 178.903, | |
| "eval_steps_per_second": 46.515, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.6423625254582483, | |
| "grad_norm": 0.5891804695129395, | |
| "learning_rate": 5.255563250413657e-05, | |
| "loss": 2.0759, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.6553971486761712, | |
| "grad_norm": 0.6447423696517944, | |
| "learning_rate": 5.1015730057227994e-05, | |
| "loss": 2.2958, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.6684317718940935, | |
| "grad_norm": 0.3930685818195343, | |
| "learning_rate": 4.952582487833161e-05, | |
| "loss": 1.817, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.6814663951120163, | |
| "grad_norm": 0.43411514163017273, | |
| "learning_rate": 4.808657048910077e-05, | |
| "loss": 1.9874, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.694501018329939, | |
| "grad_norm": 0.4237060546875, | |
| "learning_rate": 4.669859819407844e-05, | |
| "loss": 1.9388, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.7075356415478615, | |
| "grad_norm": 0.3899717926979065, | |
| "learning_rate": 4.536251680378601e-05, | |
| "loss": 1.9506, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.7205702647657841, | |
| "grad_norm": 0.3600156009197235, | |
| "learning_rate": 4.407891236767926e-05, | |
| "loss": 1.9307, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.7336048879837067, | |
| "grad_norm": 0.29930025339126587, | |
| "learning_rate": 4.2848347917087386e-05, | |
| "loss": 1.9395, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.7466395112016293, | |
| "grad_norm": 0.28485575318336487, | |
| "learning_rate": 4.167136321824887e-05, | |
| "loss": 1.9331, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.759674134419552, | |
| "grad_norm": 0.28593364357948303, | |
| "learning_rate": 4.054847453555244e-05, | |
| "loss": 1.9109, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.7727087576374747, | |
| "grad_norm": 0.33563509583473206, | |
| "learning_rate": 3.948017440508607e-05, | |
| "loss": 1.94, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.785743380855397, | |
| "grad_norm": 0.41171127557754517, | |
| "learning_rate": 3.846693141859465e-05, | |
| "loss": 1.9329, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.79877800407332, | |
| "grad_norm": 0.5771033763885498, | |
| "learning_rate": 3.7509190017940066e-05, | |
| "loss": 2.0034, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.8118126272912423, | |
| "grad_norm": 0.566257655620575, | |
| "learning_rate": 3.660737030015427e-05, | |
| "loss": 1.5604, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.824847250509165, | |
| "grad_norm": 0.44189655780792236, | |
| "learning_rate": 3.576186783317092e-05, | |
| "loss": 2.4998, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.8378818737270874, | |
| "grad_norm": 0.3839716911315918, | |
| "learning_rate": 3.4973053482316156e-05, | |
| "loss": 1.9946, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.8509164969450103, | |
| "grad_norm": 0.3798718750476837, | |
| "learning_rate": 3.4241273247634805e-05, | |
| "loss": 1.9378, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.8639511201629326, | |
| "grad_norm": 0.33077380061149597, | |
| "learning_rate": 3.356684811212336e-05, | |
| "loss": 1.9503, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.8769857433808554, | |
| "grad_norm": 0.3309776186943054, | |
| "learning_rate": 3.2950073900936234e-05, | |
| "loss": 1.9187, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.890020366598778, | |
| "grad_norm": 0.2614622116088867, | |
| "learning_rate": 3.2391221151627036e-05, | |
| "loss": 1.9367, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.9030549898167006, | |
| "grad_norm": 0.27304932475090027, | |
| "learning_rate": 3.1890534995481836e-05, | |
| "loss": 1.9302, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.9160896130346232, | |
| "grad_norm": 0.26790907979011536, | |
| "learning_rate": 3.144823504999658e-05, | |
| "loss": 1.9228, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.9291242362525458, | |
| "grad_norm": 0.3259439468383789, | |
| "learning_rate": 3.10645153225455e-05, | |
| "loss": 1.9133, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.9421588594704684, | |
| "grad_norm": 0.40042850375175476, | |
| "learning_rate": 3.0739544125283105e-05, | |
| "loss": 1.9946, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.955193482688391, | |
| "grad_norm": 0.49017587304115295, | |
| "learning_rate": 3.047346400131691e-05, | |
| "loss": 1.9776, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.955193482688391, | |
| "eval_loss": 1.9268525838851929, | |
| "eval_runtime": 0.2825, | |
| "eval_samples_per_second": 176.994, | |
| "eval_steps_per_second": 46.019, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.9682281059063138, | |
| "grad_norm": 0.5727090835571289, | |
| "learning_rate": 3.0266391662183335e-05, | |
| "loss": 2.0008, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.9812627291242362, | |
| "grad_norm": 0.6628953814506531, | |
| "learning_rate": 3.0118417936654115e-05, | |
| "loss": 2.2794, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.994297352342159, | |
| "grad_norm": 0.3259391188621521, | |
| "learning_rate": 3.0029607730895854e-05, | |
| "loss": 2.0307, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.0073319755600814, | |
| "grad_norm": 0.36595845222473145, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.3735, | |
| "step": 154 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 154, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.841916242211635e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |