| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.01297016861219196, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00025940337224383917, |
| "grad_norm": 13.49365234375, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 1.5584, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0005188067444876783, |
| "grad_norm": 2.6006040573120117, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 0.7111, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0007782101167315176, |
| "grad_norm": 4.435553073883057, |
| "learning_rate": 4.8e-05, |
| "loss": 0.3076, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0010376134889753567, |
| "grad_norm": 1.1146177053451538, |
| "learning_rate": 6.400000000000001e-05, |
| "loss": 0.1826, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0012970168612191958, |
| "grad_norm": 0.8707008957862854, |
| "learning_rate": 8e-05, |
| "loss": 0.1341, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0015564202334630351, |
| "grad_norm": 1.7411352396011353, |
| "learning_rate": 9.6e-05, |
| "loss": 0.1144, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.0018158236057068742, |
| "grad_norm": 0.9691908955574036, |
| "learning_rate": 0.00011200000000000001, |
| "loss": 0.0831, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.0020752269779507134, |
| "grad_norm": 1.0398532152175903, |
| "learning_rate": 0.00012800000000000002, |
| "loss": 0.0801, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.0023346303501945525, |
| "grad_norm": 0.5252112746238708, |
| "learning_rate": 0.000144, |
| "loss": 0.081, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.0025940337224383916, |
| "grad_norm": 0.6552278995513916, |
| "learning_rate": 0.00016, |
| "loss": 0.0821, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0028534370946822307, |
| "grad_norm": 0.6302046775817871, |
| "learning_rate": 0.00017600000000000002, |
| "loss": 0.0749, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.0031128404669260703, |
| "grad_norm": 0.7439587712287903, |
| "learning_rate": 0.000192, |
| "loss": 0.0647, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.0033722438391699094, |
| "grad_norm": 6.8584771156311035, |
| "learning_rate": 0.0001999978128380225, |
| "loss": 0.0726, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.0036316472114137485, |
| "grad_norm": 2.014613389968872, |
| "learning_rate": 0.0001999803161162393, |
| "loss": 0.0936, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.0038910505836575876, |
| "grad_norm": 1.3758050203323364, |
| "learning_rate": 0.00019994532573409262, |
| "loss": 0.1089, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.004150453955901427, |
| "grad_norm": 1.3027769327163696, |
| "learning_rate": 0.00019989284781388617, |
| "loss": 0.0772, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.004409857328145266, |
| "grad_norm": 1.021938443183899, |
| "learning_rate": 0.00019982289153773646, |
| "loss": 0.0695, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.004669260700389105, |
| "grad_norm": 0.8069638609886169, |
| "learning_rate": 0.00019973546914596623, |
| "loss": 0.0624, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.004928664072632944, |
| "grad_norm": 0.5198134779930115, |
| "learning_rate": 0.00019963059593496268, |
| "loss": 0.0481, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.005188067444876783, |
| "grad_norm": 0.39965012669563293, |
| "learning_rate": 0.00019950829025450114, |
| "loss": 0.0493, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.005447470817120622, |
| "grad_norm": 0.8152652978897095, |
| "learning_rate": 0.0001993685735045343, |
| "loss": 0.0477, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.005706874189364461, |
| "grad_norm": 0.7083427309989929, |
| "learning_rate": 0.0001992114701314478, |
| "loss": 0.0501, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.0059662775616083005, |
| "grad_norm": 0.690096914768219, |
| "learning_rate": 0.000199037007623783, |
| "loss": 0.0509, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.0062256809338521405, |
| "grad_norm": 0.871699869632721, |
| "learning_rate": 0.00019884521650742715, |
| "loss": 0.0464, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.00648508430609598, |
| "grad_norm": 0.6445639133453369, |
| "learning_rate": 0.00019863613034027224, |
| "loss": 0.0462, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.006744487678339819, |
| "grad_norm": 0.4920782148838043, |
| "learning_rate": 0.0001984097857063434, |
| "loss": 0.0425, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.007003891050583658, |
| "grad_norm": 0.8624788522720337, |
| "learning_rate": 0.0001981662222093976, |
| "loss": 0.0471, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.007263294422827497, |
| "grad_norm": 0.5704030990600586, |
| "learning_rate": 0.00019790548246599447, |
| "loss": 0.0571, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.007522697795071336, |
| "grad_norm": 0.569247841835022, |
| "learning_rate": 0.00019762761209803927, |
| "loss": 0.0531, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.007782101167315175, |
| "grad_norm": 0.7414583563804626, |
| "learning_rate": 0.0001973326597248006, |
| "loss": 0.0455, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.008041504539559013, |
| "grad_norm": 0.42905348539352417, |
| "learning_rate": 0.00019702067695440332, |
| "loss": 0.0542, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.008300907911802853, |
| "grad_norm": 0.6132651567459106, |
| "learning_rate": 0.00019669171837479873, |
| "loss": 0.0439, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.008560311284046693, |
| "grad_norm": 0.44733384251594543, |
| "learning_rate": 0.00019634584154421317, |
| "loss": 0.0429, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.008819714656290532, |
| "grad_norm": 0.516659677028656, |
| "learning_rate": 0.00019598310698107702, |
| "loss": 0.0407, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.009079118028534372, |
| "grad_norm": 0.2340136468410492, |
| "learning_rate": 0.00019560357815343577, |
| "loss": 0.036, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.00933852140077821, |
| "grad_norm": 0.6629723906517029, |
| "learning_rate": 0.00019520732146784491, |
| "loss": 0.041, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.00959792477302205, |
| "grad_norm": 0.3777199387550354, |
| "learning_rate": 0.0001947944062577507, |
| "loss": 0.0414, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.009857328145265888, |
| "grad_norm": 0.44298338890075684, |
| "learning_rate": 0.00019436490477135878, |
| "loss": 0.0371, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.010116731517509728, |
| "grad_norm": 0.4530090093612671, |
| "learning_rate": 0.00019391889215899299, |
| "loss": 0.037, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.010376134889753566, |
| "grad_norm": 0.36142367124557495, |
| "learning_rate": 0.0001934564464599461, |
| "loss": 0.0387, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.010635538261997406, |
| "grad_norm": 0.36559927463531494, |
| "learning_rate": 0.00019297764858882514, |
| "loss": 0.0386, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.010894941634241245, |
| "grad_norm": 0.47660204768180847, |
| "learning_rate": 0.00019248258232139388, |
| "loss": 0.0316, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.011154345006485085, |
| "grad_norm": 0.2614981234073639, |
| "learning_rate": 0.00019197133427991436, |
| "loss": 0.0417, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.011413748378728923, |
| "grad_norm": 0.44811561703681946, |
| "learning_rate": 0.00019144399391799043, |
| "loss": 0.036, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.011673151750972763, |
| "grad_norm": 0.4213508367538452, |
| "learning_rate": 0.00019090065350491626, |
| "loss": 0.0399, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.011932555123216601, |
| "grad_norm": 0.29146406054496765, |
| "learning_rate": 0.0001903414081095315, |
| "loss": 0.0376, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.012191958495460441, |
| "grad_norm": 0.2714293897151947, |
| "learning_rate": 0.00018976635558358722, |
| "loss": 0.0362, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.012451361867704281, |
| "grad_norm": 0.3767367899417877, |
| "learning_rate": 0.00018917559654462474, |
| "loss": 0.0364, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.01271076523994812, |
| "grad_norm": 0.36578992009162903, |
| "learning_rate": 0.00018856923435837022, |
| "loss": 0.0327, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.01297016861219196, |
| "grad_norm": 0.32976096868515015, |
| "learning_rate": 0.0001879473751206489, |
| "loss": 0.04, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.5729978171392e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
