| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18538324420677363, | |
| "eval_steps": 72, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0030897207367795603, | |
| "grad_norm": 121222.5390625, | |
| "learning_rate": 4.0000000000000007e-10, | |
| "loss": 28.6291, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006179441473559121, | |
| "grad_norm": 118161.796875, | |
| "learning_rate": 8.000000000000001e-10, | |
| "loss": 28.0625, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009269162210338681, | |
| "grad_norm": 125806.6796875, | |
| "learning_rate": 1.2e-09, | |
| "loss": 27.2823, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012358882947118241, | |
| "grad_norm": 112738.1484375, | |
| "learning_rate": 1.6000000000000003e-09, | |
| "loss": 29.0227, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015448603683897801, | |
| "grad_norm": 121833.5390625, | |
| "learning_rate": 2e-09, | |
| "loss": 27.4845, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018538324420677363, | |
| "grad_norm": 122112.65625, | |
| "learning_rate": 1.9989008914857113e-09, | |
| "loss": 26.6542, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02162804515745692, | |
| "grad_norm": 122619.7265625, | |
| "learning_rate": 1.995605982021898e-09, | |
| "loss": 27.3283, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.024717765894236483, | |
| "grad_norm": 124364.53125, | |
| "learning_rate": 1.990122514534651e-09, | |
| "loss": 26.9111, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.027807486631016044, | |
| "grad_norm": 123087.8671875, | |
| "learning_rate": 1.9824625428755763e-09, | |
| "loss": 26.6357, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.030897207367795602, | |
| "grad_norm": 136198.734375, | |
| "learning_rate": 1.972642905324813e-09, | |
| "loss": 23.6223, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03398692810457516, | |
| "grad_norm": 123133.7578125, | |
| "learning_rate": 1.9606851875768402e-09, | |
| "loss": 25.9946, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.037076648841354726, | |
| "grad_norm": 103042.3515625, | |
| "learning_rate": 1.946615675290434e-09, | |
| "loss": 30.1162, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.040166369578134284, | |
| "grad_norm": 131866.765625, | |
| "learning_rate": 1.930465296307087e-09, | |
| "loss": 25.6211, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04325609031491384, | |
| "grad_norm": 122014.0625, | |
| "learning_rate": 1.9122695526648967e-09, | |
| "loss": 26.5086, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04634581105169341, | |
| "grad_norm": 124875.875, | |
| "learning_rate": 1.8920684425573866e-09, | |
| "loss": 27.6806, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.049435531788472965, | |
| "grad_norm": 130853.09375, | |
| "learning_rate": 1.8699063724087904e-09, | |
| "loss": 25.0591, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.052525252525252523, | |
| "grad_norm": 134673.421875, | |
| "learning_rate": 1.8458320592590975e-09, | |
| "loss": 25.3938, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05561497326203209, | |
| "grad_norm": 112125.9765625, | |
| "learning_rate": 1.8198984236734246e-09, | |
| "loss": 28.5848, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05870469399881165, | |
| "grad_norm": 123824.6875, | |
| "learning_rate": 1.7921624734111293e-09, | |
| "loss": 27.1392, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.061794414735591205, | |
| "grad_norm": 125568.03125, | |
| "learning_rate": 1.7626851781103819e-09, | |
| "loss": 25.654, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06488413547237076, | |
| "grad_norm": 120140.71875, | |
| "learning_rate": 1.7315313352636692e-09, | |
| "loss": 27.8295, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06797385620915032, | |
| "grad_norm": 125886.3203125, | |
| "learning_rate": 1.6987694277788419e-09, | |
| "loss": 26.6647, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0710635769459299, | |
| "grad_norm": 119238.578125, | |
| "learning_rate": 1.664471473438822e-09, | |
| "loss": 26.6455, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07415329768270945, | |
| "grad_norm": 117924.9921875, | |
| "learning_rate": 1.6287128665908851e-09, | |
| "loss": 26.5597, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07724301841948901, | |
| "grad_norm": 131537.625, | |
| "learning_rate": 1.5915722124135226e-09, | |
| "loss": 26.2297, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08033273915626857, | |
| "grad_norm": 129350.40625, | |
| "learning_rate": 1.5531311541251995e-09, | |
| "loss": 27.3055, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08342245989304813, | |
| "grad_norm": 121738.21875, | |
| "learning_rate": 1.513474193514842e-09, | |
| "loss": 26.4486, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08651218062982768, | |
| "grad_norm": 122703.90625, | |
| "learning_rate": 1.4726885051885652e-09, | |
| "loss": 27.6315, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08960190136660724, | |
| "grad_norm": 120508.328125, | |
| "learning_rate": 1.4308637449409705e-09, | |
| "loss": 26.4159, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09269162210338681, | |
| "grad_norm": 116380.859375, | |
| "learning_rate": 1.3880918526722497e-09, | |
| "loss": 28.3796, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09578134284016637, | |
| "grad_norm": 126698.1796875, | |
| "learning_rate": 1.344466850284333e-09, | |
| "loss": 27.0027, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09887106357694593, | |
| "grad_norm": 128378.515625, | |
| "learning_rate": 1.3000846350003408e-09, | |
| "loss": 25.3418, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10196078431372549, | |
| "grad_norm": 116183.1796875, | |
| "learning_rate": 1.2550427685616766e-09, | |
| "loss": 29.4539, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10505050505050505, | |
| "grad_norm": 119771.0625, | |
| "learning_rate": 1.2094402627661447e-09, | |
| "loss": 26.9952, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1081402257872846, | |
| "grad_norm": 117849.8515625, | |
| "learning_rate": 1.16337736181853e-09, | |
| "loss": 28.5859, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11122994652406418, | |
| "grad_norm": 121979.3359375, | |
| "learning_rate": 1.1169553219720828e-09, | |
| "loss": 28.5073, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11431966726084374, | |
| "grad_norm": 125324.3984375, | |
| "learning_rate": 1.070276188945293e-09, | |
| "loss": 26.0588, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1174093879976233, | |
| "grad_norm": 131353.421875, | |
| "learning_rate": 1.0234425736032608e-09, | |
| "loss": 24.2387, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12049910873440285, | |
| "grad_norm": 120623.5, | |
| "learning_rate": 9.765574263967397e-10, | |
| "loss": 27.3392, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12358882947118241, | |
| "grad_norm": 117227.8515625, | |
| "learning_rate": 9.297238110547074e-10, | |
| "loss": 28.0838, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12667855020796198, | |
| "grad_norm": 119083.9375, | |
| "learning_rate": 8.830446780279176e-10, | |
| "loss": 27.8417, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12976827094474153, | |
| "grad_norm": 139472.0625, | |
| "learning_rate": 8.366226381814697e-10, | |
| "loss": 25.6301, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1328579916815211, | |
| "grad_norm": 110898.171875, | |
| "learning_rate": 7.905597372338558e-10, | |
| "loss": 27.9009, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13594771241830064, | |
| "grad_norm": 121771.7265625, | |
| "learning_rate": 7.449572314383236e-10, | |
| "loss": 26.8833, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13903743315508021, | |
| "grad_norm": 123917.234375, | |
| "learning_rate": 6.999153649996595e-10, | |
| "loss": 25.6374, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1421271538918598, | |
| "grad_norm": 121639.7421875, | |
| "learning_rate": 6.555331497156672e-10, | |
| "loss": 25.5364, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14521687462863933, | |
| "grad_norm": 116252.3828125, | |
| "learning_rate": 6.119081473277502e-10, | |
| "loss": 28.6826, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1483065953654189, | |
| "grad_norm": 116441.125, | |
| "learning_rate": 5.691362550590297e-10, | |
| "loss": 28.0026, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15139631610219845, | |
| "grad_norm": 125541.921875, | |
| "learning_rate": 5.273114948114346e-10, | |
| "loss": 24.9752, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15448603683897802, | |
| "grad_norm": 114526.9609375, | |
| "learning_rate": 4.865258064851579e-10, | |
| "loss": 27.5153, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15757575757575756, | |
| "grad_norm": 118780.75, | |
| "learning_rate": 4.4686884587480063e-10, | |
| "loss": 27.9096, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.16066547831253714, | |
| "grad_norm": 108833.6875, | |
| "learning_rate": 4.084277875864776e-10, | |
| "loss": 28.2642, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1637551990493167, | |
| "grad_norm": 124329.8984375, | |
| "learning_rate": 3.7128713340911535e-10, | |
| "loss": 26.1074, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.16684491978609625, | |
| "grad_norm": 136048.546875, | |
| "learning_rate": 3.3552852656117837e-10, | |
| "loss": 23.3226, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.16993464052287582, | |
| "grad_norm": 124232.1796875, | |
| "learning_rate": 3.0123057222115837e-10, | |
| "loss": 26.2317, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.17302436125965537, | |
| "grad_norm": 112182.0390625, | |
| "learning_rate": 2.6846866473633127e-10, | |
| "loss": 27.8249, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.17611408199643494, | |
| "grad_norm": 123877.953125, | |
| "learning_rate": 2.3731482188961816e-10, | |
| "loss": 27.2162, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.17920380273321448, | |
| "grad_norm": 118916.7421875, | |
| "learning_rate": 2.078375265888707e-10, | |
| "loss": 25.814, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.18229352346999406, | |
| "grad_norm": 140265.84375, | |
| "learning_rate": 1.8010157632657544e-10, | |
| "loss": 23.8831, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.18538324420677363, | |
| "grad_norm": 126473.171875, | |
| "learning_rate": 1.5416794074090257e-10, | |
| "loss": 24.0671, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 72, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.956275843497984e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |