| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06863417982155114, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009151223976206818, | |
| "grad_norm": 53.509986877441406, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.9382, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009151223976206818, | |
| "eval_loss": 5.209521770477295, | |
| "eval_runtime": 269.0963, | |
| "eval_samples_per_second": 3.423, | |
| "eval_steps_per_second": 1.713, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018302447952413636, | |
| "grad_norm": 59.40241241455078, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.5577, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002745367192862045, | |
| "grad_norm": 34.23931884765625, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6193, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0036604895904827272, | |
| "grad_norm": 22.23225975036621, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.8745, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004575611988103409, | |
| "grad_norm": 11.005436897277832, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.666, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00549073438572409, | |
| "grad_norm": 6.069633483886719, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.4651, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006405856783344772, | |
| "grad_norm": 6.48963737487793, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.4599, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0073209791809654545, | |
| "grad_norm": 5.265394687652588, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.5091, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008236101578586136, | |
| "grad_norm": 4.875738143920898, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.5463, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009151223976206819, | |
| "grad_norm": 4.376837253570557, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.5592, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010066346373827499, | |
| "grad_norm": 3.9858877658843994, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.4601, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01098146877144818, | |
| "grad_norm": 4.524520397186279, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4564, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011896591169068863, | |
| "grad_norm": 4.058590888977051, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.3405, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012811713566689545, | |
| "grad_norm": 6.065700531005859, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.4246, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013726835964310227, | |
| "grad_norm": 3.748472213745117, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.2962, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014641958361930909, | |
| "grad_norm": 6.658496856689453, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.3704, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01555708075955159, | |
| "grad_norm": 5.924066066741943, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.4376, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.016472203157172273, | |
| "grad_norm": 0.02715293876826763, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0003, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017387325554792953, | |
| "grad_norm": 0.5976182818412781, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.02, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.018302447952413637, | |
| "grad_norm": 0.17597460746765137, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.0018, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019217570350034317, | |
| "grad_norm": 4.291876792907715, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1806, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.020132692747654998, | |
| "grad_norm": 3.9051401615142822, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.157, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02104781514527568, | |
| "grad_norm": 2.4507651329040527, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0579, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02196293754289636, | |
| "grad_norm": 2.8427188396453857, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0496, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022878059940517045, | |
| "grad_norm": 1.8807505369186401, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.0158, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022878059940517045, | |
| "eval_loss": 0.29860904812812805, | |
| "eval_runtime": 271.9036, | |
| "eval_samples_per_second": 3.387, | |
| "eval_steps_per_second": 1.695, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023793182338137726, | |
| "grad_norm": 0.3018530309200287, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.0027, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.024708304735758406, | |
| "grad_norm": 1.2422139644622803, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0072, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02562342713337909, | |
| "grad_norm": 0.9640685319900513, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.009, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02653854953099977, | |
| "grad_norm": 4.360398769378662, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.1776, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.027453671928620454, | |
| "grad_norm": 309.7273254394531, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4983, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.028368794326241134, | |
| "grad_norm": 3.7143096923828125, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0492, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.029283916723861818, | |
| "grad_norm": 0.2380424439907074, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.001, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.030199039121482498, | |
| "grad_norm": 0.11934609711170197, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0004, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03111416151910318, | |
| "grad_norm": 0.007320514414459467, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03202928391672386, | |
| "grad_norm": 0.002803817857056856, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.032944406314344546, | |
| "grad_norm": 0.0005631367093883455, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03385952871196522, | |
| "grad_norm": 0.02052667923271656, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.0001, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.034774651109585906, | |
| "grad_norm": 0.0067352899350225925, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03568977350720659, | |
| "grad_norm": 0.0002736738242674619, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.036604895904827274, | |
| "grad_norm": 0.00117769546341151, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03752001830244795, | |
| "grad_norm": 0.001372729311697185, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.038435140700068635, | |
| "grad_norm": 0.00026712805265560746, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03935026309768932, | |
| "grad_norm": 0.00031787759508006275, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.040265385495309995, | |
| "grad_norm": 0.000843716028612107, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04118050789293068, | |
| "grad_norm": 0.0002576544648036361, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04209563029055136, | |
| "grad_norm": 0.13201799988746643, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.0004, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.043010752688172046, | |
| "grad_norm": 0.0014015285996720195, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04392587508579272, | |
| "grad_norm": 0.0066895028576254845, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0001, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04484099748341341, | |
| "grad_norm": 0.0023771661799401045, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04575611988103409, | |
| "grad_norm": 0.8348031640052795, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.0032, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04575611988103409, | |
| "eval_loss": 0.19106687605381012, | |
| "eval_runtime": 271.369, | |
| "eval_samples_per_second": 3.394, | |
| "eval_steps_per_second": 1.699, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04667124227865477, | |
| "grad_norm": 10.542644500732422, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5443, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04758636467627545, | |
| "grad_norm": 5.551739692687988, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.2044, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.048501487073896135, | |
| "grad_norm": 7.962470054626465, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.3918, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.04941660947151681, | |
| "grad_norm": 9.332234382629395, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6089, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.050331731869137496, | |
| "grad_norm": 7.265214443206787, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.4531, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05124685426675818, | |
| "grad_norm": 7.815890789031982, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.3726, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.05216197666437886, | |
| "grad_norm": 7.1828765869140625, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3523, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.05307709906199954, | |
| "grad_norm": 8.059473037719727, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.4862, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.053992221459620224, | |
| "grad_norm": 6.242551326751709, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.4128, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.05490734385724091, | |
| "grad_norm": 4.751944065093994, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3559, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.055822466254861584, | |
| "grad_norm": 3.4567954540252686, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.2912, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.05673758865248227, | |
| "grad_norm": 5.8354692459106445, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.4136, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.05765271105010295, | |
| "grad_norm": 5.292219638824463, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3484, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.058567833447723636, | |
| "grad_norm": 5.4359846115112305, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.4286, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05948295584534431, | |
| "grad_norm": 3.9820847511291504, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.2672, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.060398078242964996, | |
| "grad_norm": 5.325780868530273, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4854, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.06131320064058568, | |
| "grad_norm": 2.7474725246429443, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.1493, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.06222832303820636, | |
| "grad_norm": 0.031556036323308945, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.0002, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.06314344543582705, | |
| "grad_norm": 1.6410260200500488, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0273, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.06405856783344772, | |
| "grad_norm": 0.6467976570129395, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.0064, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0649736902310684, | |
| "grad_norm": 0.680183470249176, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.0023, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.06588881262868909, | |
| "grad_norm": 3.648841619491577, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0219, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06680393502630977, | |
| "grad_norm": 3.311021089553833, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.0454, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.06771905742393045, | |
| "grad_norm": 0.4128534495830536, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.002, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.06863417982155114, | |
| "grad_norm": 0.006412339396774769, | |
| "learning_rate": 0.0, | |
| "loss": 0.0001, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06863417982155114, | |
| "eval_loss": 0.11607871204614639, | |
| "eval_runtime": 271.5587, | |
| "eval_samples_per_second": 3.392, | |
| "eval_steps_per_second": 1.698, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.157714927419392e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |