| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9932279909706545, | |
| "eval_steps": 50, | |
| "global_step": 663, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022573363431151242, | |
| "grad_norm": 18.10373149143315, | |
| "learning_rate": 5e-07, | |
| "loss": 1.7281, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.045146726862302484, | |
| "grad_norm": 12.098369998439862, | |
| "learning_rate": 1e-06, | |
| "loss": 1.5872, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06772009029345373, | |
| "grad_norm": 7.799480392523437, | |
| "learning_rate": 9.998553453302385e-07, | |
| "loss": 1.2742, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09029345372460497, | |
| "grad_norm": 4.3243576184049015, | |
| "learning_rate": 9.99421465020848e-07, | |
| "loss": 1.1293, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11286681715575621, | |
| "grad_norm": 3.8123521250599035, | |
| "learning_rate": 9.9869861012308e-07, | |
| "loss": 1.0773, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13544018058690746, | |
| "grad_norm": 3.7302202580496955, | |
| "learning_rate": 9.976871988942804e-07, | |
| "loss": 1.0241, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1580135440180587, | |
| "grad_norm": 3.6817019638097315, | |
| "learning_rate": 9.963878165558785e-07, | |
| "loss": 0.9907, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18058690744920994, | |
| "grad_norm": 3.6570665491053798, | |
| "learning_rate": 9.948012149547666e-07, | |
| "loss": 0.9535, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20316027088036118, | |
| "grad_norm": 3.5815310725056895, | |
| "learning_rate": 9.929283121282675e-07, | |
| "loss": 0.9562, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.22573363431151242, | |
| "grad_norm": 3.5857342727356256, | |
| "learning_rate": 9.9077019177294e-07, | |
| "loss": 0.9196, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22573363431151242, | |
| "eval_loss": 0.9316988587379456, | |
| "eval_runtime": 110.0444, | |
| "eval_samples_per_second": 57.25, | |
| "eval_steps_per_second": 0.9, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24830699774266365, | |
| "grad_norm": 3.8011407294134836, | |
| "learning_rate": 9.88328102617534e-07, | |
| "loss": 0.9367, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2708803611738149, | |
| "grad_norm": 3.4590500642130086, | |
| "learning_rate": 9.856034577004504e-07, | |
| "loss": 0.9275, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.29345372460496616, | |
| "grad_norm": 3.576144528772592, | |
| "learning_rate": 9.82597833552132e-07, | |
| "loss": 0.919, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3160270880361174, | |
| "grad_norm": 3.324174107907928, | |
| "learning_rate": 9.793129692828533e-07, | |
| "loss": 0.9057, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.33860045146726864, | |
| "grad_norm": 3.8855820879993144, | |
| "learning_rate": 9.757507655764384e-07, | |
| "loss": 0.8901, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3611738148984199, | |
| "grad_norm": 3.469991558293526, | |
| "learning_rate": 9.719132835904906e-07, | |
| "loss": 0.9147, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3837471783295711, | |
| "grad_norm": 3.514613408390947, | |
| "learning_rate": 9.678027437637677e-07, | |
| "loss": 0.8819, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.40632054176072235, | |
| "grad_norm": 3.648475056062095, | |
| "learning_rate": 9.634215245313939e-07, | |
| "loss": 0.8867, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4288939051918736, | |
| "grad_norm": 3.5559364392174695, | |
| "learning_rate": 9.587721609486543e-07, | |
| "loss": 0.8809, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.45146726862302483, | |
| "grad_norm": 3.4130223122860843, | |
| "learning_rate": 9.538573432241637e-07, | |
| "loss": 0.8737, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.45146726862302483, | |
| "eval_loss": 0.8765010833740234, | |
| "eval_runtime": 109.5348, | |
| "eval_samples_per_second": 57.516, | |
| "eval_steps_per_second": 0.904, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.47404063205417607, | |
| "grad_norm": 3.787400905783148, | |
| "learning_rate": 9.486799151632612e-07, | |
| "loss": 0.885, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4966139954853273, | |
| "grad_norm": 3.535608347392897, | |
| "learning_rate": 9.432428725225326e-07, | |
| "loss": 0.8814, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5191873589164786, | |
| "grad_norm": 3.6894303777250927, | |
| "learning_rate": 9.375493612764085e-07, | |
| "loss": 0.881, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5417607223476298, | |
| "grad_norm": 3.577445458553245, | |
| "learning_rate": 9.316026757968454e-07, | |
| "loss": 0.8572, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5643340857787811, | |
| "grad_norm": 3.5992375922791284, | |
| "learning_rate": 9.2540625694714e-07, | |
| "loss": 0.8654, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5869074492099323, | |
| "grad_norm": 3.4939966180593824, | |
| "learning_rate": 9.189636900909817e-07, | |
| "loss": 0.8603, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6094808126410836, | |
| "grad_norm": 3.815700262637612, | |
| "learning_rate": 9.122787030178949e-07, | |
| "loss": 0.8511, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6320541760722348, | |
| "grad_norm": 3.7360996720156314, | |
| "learning_rate": 9.053551637862692e-07, | |
| "loss": 0.8622, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.654627539503386, | |
| "grad_norm": 3.7059514280124, | |
| "learning_rate": 8.98197078485229e-07, | |
| "loss": 0.8371, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6772009029345373, | |
| "grad_norm": 3.4566197799411778, | |
| "learning_rate": 8.908085889166357e-07, | |
| "loss": 0.8557, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6772009029345373, | |
| "eval_loss": 0.8529915809631348, | |
| "eval_runtime": 109.5763, | |
| "eval_samples_per_second": 57.494, | |
| "eval_steps_per_second": 0.903, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6997742663656885, | |
| "grad_norm": 4.108966235237678, | |
| "learning_rate": 8.831939701985636e-07, | |
| "loss": 0.8493, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.7223476297968398, | |
| "grad_norm": 3.500706471908252, | |
| "learning_rate": 8.75357628291637e-07, | |
| "loss": 0.8561, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.744920993227991, | |
| "grad_norm": 3.465064110849232, | |
| "learning_rate": 8.673040974496584e-07, | |
| "loss": 0.8382, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7674943566591422, | |
| "grad_norm": 3.4468913764280824, | |
| "learning_rate": 8.590380375960053e-07, | |
| "loss": 0.8347, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7900677200902935, | |
| "grad_norm": 3.689915124175266, | |
| "learning_rate": 8.505642316273111e-07, | |
| "loss": 0.8421, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.8126410835214447, | |
| "grad_norm": 3.380084999051841, | |
| "learning_rate": 8.418875826459919e-07, | |
| "loss": 0.8317, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.835214446952596, | |
| "grad_norm": 3.6696844138559808, | |
| "learning_rate": 8.330131111232201e-07, | |
| "loss": 0.8407, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8577878103837472, | |
| "grad_norm": 3.4940832177035293, | |
| "learning_rate": 8.239459519939851e-07, | |
| "loss": 0.8539, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8803611738148984, | |
| "grad_norm": 3.214918919448116, | |
| "learning_rate": 8.14691351685925e-07, | |
| "loss": 0.8347, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.9029345372460497, | |
| "grad_norm": 3.427510592132526, | |
| "learning_rate": 8.052546650836453e-07, | |
| "loss": 0.8242, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9029345372460497, | |
| "eval_loss": 0.8354331254959106, | |
| "eval_runtime": 109.4188, | |
| "eval_samples_per_second": 57.577, | |
| "eval_steps_per_second": 0.905, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9255079006772009, | |
| "grad_norm": 3.6927117939398886, | |
| "learning_rate": 7.956413524302823e-07, | |
| "loss": 0.8204, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.9480812641083521, | |
| "grad_norm": 3.6666105985738606, | |
| "learning_rate": 7.858569761681047e-07, | |
| "loss": 0.8545, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9706546275395034, | |
| "grad_norm": 3.875619463407146, | |
| "learning_rate": 7.759071977199806e-07, | |
| "loss": 0.8431, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.9932279909706546, | |
| "grad_norm": 3.2790864439936875, | |
| "learning_rate": 7.657977742135725e-07, | |
| "loss": 0.8245, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0158013544018059, | |
| "grad_norm": 3.3063820393602876, | |
| "learning_rate": 7.555345551501557e-07, | |
| "loss": 0.7956, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.0383747178329572, | |
| "grad_norm": 3.707635627262872, | |
| "learning_rate": 7.451234790199871e-07, | |
| "loss": 0.7706, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.0609480812641083, | |
| "grad_norm": 3.6504981451650096, | |
| "learning_rate": 7.345705698661852e-07, | |
| "loss": 0.7521, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.0835214446952597, | |
| "grad_norm": 3.4617956642188097, | |
| "learning_rate": 7.23881933799104e-07, | |
| "loss": 0.7465, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.1060948081264108, | |
| "grad_norm": 3.6172380022954935, | |
| "learning_rate": 7.130637554632257e-07, | |
| "loss": 0.7727, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.1286681715575622, | |
| "grad_norm": 3.793915550967959, | |
| "learning_rate": 7.021222944586088e-07, | |
| "loss": 0.7715, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.1286681715575622, | |
| "eval_loss": 0.8277800679206848, | |
| "eval_runtime": 109.5657, | |
| "eval_samples_per_second": 57.5, | |
| "eval_steps_per_second": 0.904, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.1512415349887133, | |
| "grad_norm": 3.4955286501011735, | |
| "learning_rate": 6.910638817189664e-07, | |
| "loss": 0.7589, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.1738148984198646, | |
| "grad_norm": 3.5834856426118615, | |
| "learning_rate": 6.798949158484705e-07, | |
| "loss": 0.7784, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.1963882618510158, | |
| "grad_norm": 3.655680306693504, | |
| "learning_rate": 6.686218594193993e-07, | |
| "loss": 0.7402, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.2189616252821671, | |
| "grad_norm": 3.86229701873481, | |
| "learning_rate": 6.572512352327726e-07, | |
| "loss": 0.7759, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.2415349887133182, | |
| "grad_norm": 3.5211869951686983, | |
| "learning_rate": 6.457896225441371e-07, | |
| "loss": 0.7549, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.2641083521444696, | |
| "grad_norm": 3.5889293223377208, | |
| "learning_rate": 6.342436532566865e-07, | |
| "loss": 0.7564, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.2866817155756207, | |
| "grad_norm": 3.607920044891375, | |
| "learning_rate": 6.226200080839182e-07, | |
| "loss": 0.7629, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.309255079006772, | |
| "grad_norm": 3.553446162126762, | |
| "learning_rate": 6.109254126840479e-07, | |
| "loss": 0.7531, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.3318284424379232, | |
| "grad_norm": 3.5301798790372207, | |
| "learning_rate": 5.991666337684176e-07, | |
| "loss": 0.7572, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.3544018058690745, | |
| "grad_norm": 3.627738643773189, | |
| "learning_rate": 5.873504751861507e-07, | |
| "loss": 0.7752, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.3544018058690745, | |
| "eval_loss": 0.819725513458252, | |
| "eval_runtime": 109.6357, | |
| "eval_samples_per_second": 57.463, | |
| "eval_steps_per_second": 0.903, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.3769751693002257, | |
| "grad_norm": 3.609521496977633, | |
| "learning_rate": 5.754837739873178e-07, | |
| "loss": 0.7622, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.399548532731377, | |
| "grad_norm": 3.556720507344035, | |
| "learning_rate": 5.635733964668909e-07, | |
| "loss": 0.7487, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.4221218961625282, | |
| "grad_norm": 3.8469023502440756, | |
| "learning_rate": 5.516262341917778e-07, | |
| "loss": 0.7568, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.4446952595936795, | |
| "grad_norm": 3.553420846727805, | |
| "learning_rate": 5.396492000132325e-07, | |
| "loss": 0.7584, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.4672686230248306, | |
| "grad_norm": 3.671248637273475, | |
| "learning_rate": 5.276492240669503e-07, | |
| "loss": 0.7708, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.489841986455982, | |
| "grad_norm": 3.4883623820641922, | |
| "learning_rate": 5.156332497631621e-07, | |
| "loss": 0.742, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.5124153498871333, | |
| "grad_norm": 3.5733319503202776, | |
| "learning_rate": 5.036082297690464e-07, | |
| "loss": 0.7578, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.5349887133182845, | |
| "grad_norm": 3.453860123250934, | |
| "learning_rate": 4.915811219857882e-07, | |
| "loss": 0.7542, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.5575620767494356, | |
| "grad_norm": 3.6891903258202206, | |
| "learning_rate": 4.795588855226055e-07, | |
| "loss": 0.7589, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.580135440180587, | |
| "grad_norm": 3.647875532185229, | |
| "learning_rate": 4.6754847667008004e-07, | |
| "loss": 0.7359, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.580135440180587, | |
| "eval_loss": 0.8135123252868652, | |
| "eval_runtime": 109.5806, | |
| "eval_samples_per_second": 57.492, | |
| "eval_steps_per_second": 0.903, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.6027088036117383, | |
| "grad_norm": 3.5680267072205427, | |
| "learning_rate": 4.5555684487511693e-07, | |
| "loss": 0.7674, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.6252821670428894, | |
| "grad_norm": 3.281054570962508, | |
| "learning_rate": 4.435909287198646e-07, | |
| "loss": 0.7565, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.6478555304740405, | |
| "grad_norm": 3.3765578443383224, | |
| "learning_rate": 4.316576519069226e-07, | |
| "loss": 0.7578, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.670428893905192, | |
| "grad_norm": 3.536076248505112, | |
| "learning_rate": 4.197639192531573e-07, | |
| "loss": 0.7533, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.6930022573363432, | |
| "grad_norm": 3.9641281540021023, | |
| "learning_rate": 4.079166126944453e-07, | |
| "loss": 0.7674, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.7155756207674944, | |
| "grad_norm": 3.777058403651495, | |
| "learning_rate": 3.9612258730365823e-07, | |
| "loss": 0.7355, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.7381489841986455, | |
| "grad_norm": 3.7311845269819783, | |
| "learning_rate": 3.843886673241883e-07, | |
| "loss": 0.7512, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.7607223476297968, | |
| "grad_norm": 3.5531260457665073, | |
| "learning_rate": 3.7272164222131387e-07, | |
| "loss": 0.7544, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.7832957110609482, | |
| "grad_norm": 3.815873779507455, | |
| "learning_rate": 3.611282627536887e-07, | |
| "loss": 0.7572, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.8058690744920993, | |
| "grad_norm": 3.5694044492417034, | |
| "learning_rate": 3.496152370672255e-07, | |
| "loss": 0.7467, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.8058690744920993, | |
| "eval_loss": 0.8077942132949829, | |
| "eval_runtime": 109.5421, | |
| "eval_samples_per_second": 57.512, | |
| "eval_steps_per_second": 0.904, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.8284424379232505, | |
| "grad_norm": 3.5715817669773866, | |
| "learning_rate": 3.381892268136392e-07, | |
| "loss": 0.7387, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.8510158013544018, | |
| "grad_norm": 3.632625798422972, | |
| "learning_rate": 3.2685684329588956e-07, | |
| "loss": 0.7459, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.8735891647855532, | |
| "grad_norm": 3.4083610886198614, | |
| "learning_rate": 3.1562464364275774e-07, | |
| "loss": 0.755, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.8961625282167043, | |
| "grad_norm": 3.5098768134992255, | |
| "learning_rate": 3.044991270147699e-07, | |
| "loss": 0.7485, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.9187358916478554, | |
| "grad_norm": 3.570449170370788, | |
| "learning_rate": 2.934867308436613e-07, | |
| "loss": 0.7457, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.9413092550790068, | |
| "grad_norm": 3.5437186541935386, | |
| "learning_rate": 2.825938271075572e-07, | |
| "loss": 0.7456, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.963882618510158, | |
| "grad_norm": 3.6156752309028244, | |
| "learning_rate": 2.7182671864402856e-07, | |
| "loss": 0.7367, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.9864559819413092, | |
| "grad_norm": 3.541183052041991, | |
| "learning_rate": 2.6119163550315194e-07, | |
| "loss": 0.7605, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.0090293453724604, | |
| "grad_norm": 3.668354373946963, | |
| "learning_rate": 2.506947313426854e-07, | |
| "loss": 0.7443, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 2.0316027088036117, | |
| "grad_norm": 3.6174990546812342, | |
| "learning_rate": 2.4034207986744847e-07, | |
| "loss": 0.7024, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.0316027088036117, | |
| "eval_loss": 0.8078460097312927, | |
| "eval_runtime": 109.5409, | |
| "eval_samples_per_second": 57.513, | |
| "eval_steps_per_second": 0.904, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.054176072234763, | |
| "grad_norm": 3.6197344117961983, | |
| "learning_rate": 2.301396713149627e-07, | |
| "loss": 0.7042, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 2.0767494356659144, | |
| "grad_norm": 3.6219776063121687, | |
| "learning_rate": 2.2009340898938738e-07, | |
| "loss": 0.6819, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.0993227990970653, | |
| "grad_norm": 3.749685991397984, | |
| "learning_rate": 2.1020910584575891e-07, | |
| "loss": 0.7138, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 2.1218961625282167, | |
| "grad_norm": 3.686378460444093, | |
| "learning_rate": 2.0049248112650563e-07, | |
| "loss": 0.6967, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.144469525959368, | |
| "grad_norm": 3.8202046159252903, | |
| "learning_rate": 1.9094915705218711e-07, | |
| "loss": 0.6911, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.1670428893905194, | |
| "grad_norm": 4.093386454062259, | |
| "learning_rate": 1.8158465556837304e-07, | |
| "loss": 0.6825, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.1896162528216703, | |
| "grad_norm": 3.6669210094430875, | |
| "learning_rate": 1.7240439515054218e-07, | |
| "loss": 0.6957, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 2.2121896162528216, | |
| "grad_norm": 3.7920265300049887, | |
| "learning_rate": 1.634136876688504e-07, | |
| "loss": 0.7123, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.234762979683973, | |
| "grad_norm": 3.8406082616032484, | |
| "learning_rate": 1.5461773531458455e-07, | |
| "loss": 0.7014, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 2.2573363431151243, | |
| "grad_norm": 3.7396677582411995, | |
| "learning_rate": 1.460216275900769e-07, | |
| "loss": 0.6984, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.2573363431151243, | |
| "eval_loss": 0.8086156249046326, | |
| "eval_runtime": 109.6842, | |
| "eval_samples_per_second": 57.438, | |
| "eval_steps_per_second": 0.903, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.2799097065462752, | |
| "grad_norm": 3.810172890487716, | |
| "learning_rate": 1.3763033836382392e-07, | |
| "loss": 0.6953, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 2.3024830699774266, | |
| "grad_norm": 3.7650154233741318, | |
| "learning_rate": 1.294487229925132e-07, | |
| "loss": 0.7049, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.325056433408578, | |
| "grad_norm": 3.7977324434068622, | |
| "learning_rate": 1.2148151551162345e-07, | |
| "loss": 0.6996, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 2.3476297968397293, | |
| "grad_norm": 3.7271690299752636, | |
| "learning_rate": 1.137333258962227e-07, | |
| "loss": 0.7046, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.37020316027088, | |
| "grad_norm": 3.7696874152910693, | |
| "learning_rate": 1.0620863739355135e-07, | |
| "loss": 0.7038, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.3927765237020315, | |
| "grad_norm": 3.6784969120555937, | |
| "learning_rate": 9.891180392893117e-08, | |
| "loss": 0.684, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.415349887133183, | |
| "grad_norm": 3.923781431171795, | |
| "learning_rate": 9.184704758650241e-08, | |
| "loss": 0.7056, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 2.4379232505643342, | |
| "grad_norm": 3.8228025983942624, | |
| "learning_rate": 8.501845616624798e-08, | |
| "loss": 0.6876, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.460496613995485, | |
| "grad_norm": 3.9688517448973624, | |
| "learning_rate": 7.842998081871493e-08, | |
| "loss": 0.7139, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 2.4830699774266365, | |
| "grad_norm": 3.909192582651566, | |
| "learning_rate": 7.208543375880594e-08, | |
| "loss": 0.7063, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.4830699774266365, | |
| "eval_loss": 0.8080305457115173, | |
| "eval_runtime": 109.6111, | |
| "eval_samples_per_second": 57.476, | |
| "eval_steps_per_second": 0.903, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.505643340857788, | |
| "grad_norm": 3.6883752732106125, | |
| "learning_rate": 6.598848605996004e-08, | |
| "loss": 0.6922, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.528216704288939, | |
| "grad_norm": 3.8586414745206814, | |
| "learning_rate": 6.014266553000074e-08, | |
| "loss": 0.7121, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.55079006772009, | |
| "grad_norm": 3.6987869873044725, | |
| "learning_rate": 5.4551354669881145e-08, | |
| "loss": 0.6944, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 2.5733634311512414, | |
| "grad_norm": 3.7083356878972222, | |
| "learning_rate": 4.921778871650539e-08, | |
| "loss": 0.703, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.595936794582393, | |
| "grad_norm": 3.7810271982778305, | |
| "learning_rate": 4.414505377075978e-08, | |
| "loss": 0.692, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.618510158013544, | |
| "grad_norm": 4.00249924161769, | |
| "learning_rate": 3.933608501183788e-08, | |
| "loss": 0.6901, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.6410835214446955, | |
| "grad_norm": 3.790359559860126, | |
| "learning_rate": 3.479366499889058e-08, | |
| "loss": 0.6997, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 2.6636568848758464, | |
| "grad_norm": 3.588096321178088, | |
| "learning_rate": 3.052042206098537e-08, | |
| "loss": 0.6826, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.6862302483069977, | |
| "grad_norm": 3.7054037608925148, | |
| "learning_rate": 2.6518828776306347e-08, | |
| "loss": 0.6909, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 2.708803611738149, | |
| "grad_norm": 3.703171492172673, | |
| "learning_rate": 2.279120054147393e-08, | |
| "loss": 0.6873, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.708803611738149, | |
| "eval_loss": 0.80707848072052, | |
| "eval_runtime": 109.463, | |
| "eval_samples_per_second": 57.554, | |
| "eval_steps_per_second": 0.904, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.7313769751693, | |
| "grad_norm": 3.9293753380698884, | |
| "learning_rate": 1.9339694231813252e-08, | |
| "loss": 0.6997, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 2.7539503386004514, | |
| "grad_norm": 4.137942412644628, | |
| "learning_rate": 1.616630695334592e-08, | |
| "loss": 0.7078, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.7765237020316027, | |
| "grad_norm": 3.9534669915381877, | |
| "learning_rate": 1.3272874887227281e-08, | |
| "loss": 0.6966, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 2.799097065462754, | |
| "grad_norm": 3.7231816025762168, | |
| "learning_rate": 1.066107222729712e-08, | |
| "loss": 0.7013, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.8216704288939054, | |
| "grad_norm": 3.58992452351805, | |
| "learning_rate": 8.332410211360608e-09, | |
| "loss": 0.7107, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.8442437923250563, | |
| "grad_norm": 3.744424909335921, | |
| "learning_rate": 6.288236246757284e-09, | |
| "loss": 0.6907, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.8668171557562077, | |
| "grad_norm": 3.9524208371805956, | |
| "learning_rate": 4.529733130726299e-09, | |
| "loss": 0.7125, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 2.889390519187359, | |
| "grad_norm": 3.7901367668148027, | |
| "learning_rate": 3.0579183660177086e-09, | |
| "loss": 0.6974, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.91196388261851, | |
| "grad_norm": 3.6006642909643714, | |
| "learning_rate": 1.8736435721465326e-09, | |
| "loss": 0.695, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 2.9345372460496613, | |
| "grad_norm": 3.671968035371273, | |
| "learning_rate": 9.775939926296439e-10, | |
| "loss": 0.7067, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.9345372460496613, | |
| "eval_loss": 0.8069904446601868, | |
| "eval_runtime": 109.6344, | |
| "eval_samples_per_second": 57.464, | |
| "eval_steps_per_second": 0.903, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.9571106094808126, | |
| "grad_norm": 3.6036456106402284, | |
| "learning_rate": 3.7028809849098954e-10, | |
| "loss": 0.705, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 2.979683972911964, | |
| "grad_norm": 3.7354799118910087, | |
| "learning_rate": 5.2077288264951166e-11, | |
| "loss": 0.6905, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.9932279909706545, | |
| "step": 663, | |
| "total_flos": 3909114547666944.0, | |
| "train_loss": 0.7958762821928228, | |
| "train_runtime": 10129.4465, | |
| "train_samples_per_second": 16.793, | |
| "train_steps_per_second": 0.065 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 663, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3909114547666944.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |