| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00578368999421631, | |
| "eval_steps": 9, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001156737998843262, | |
| "grad_norm": 1.395166277885437, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6313, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001156737998843262, | |
| "eval_loss": 1.9891488552093506, | |
| "eval_runtime": 738.5884, | |
| "eval_samples_per_second": 9.857, | |
| "eval_steps_per_second": 1.232, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002313475997686524, | |
| "grad_norm": 1.2996492385864258, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6748, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003470213996529786, | |
| "grad_norm": 1.7481492757797241, | |
| "learning_rate": 3e-05, | |
| "loss": 1.7503, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004626951995373048, | |
| "grad_norm": 3.627359390258789, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5117, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000578368999421631, | |
| "grad_norm": 2.383563995361328, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2055, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006940427993059572, | |
| "grad_norm": 1.7713170051574707, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9405, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008097165991902834, | |
| "grad_norm": 2.0939180850982666, | |
| "learning_rate": 7e-05, | |
| "loss": 2.1283, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009253903990746096, | |
| "grad_norm": 0.9817687273025513, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6677, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010410641989589359, | |
| "grad_norm": 0.5597569346427917, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2373, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010410641989589359, | |
| "eval_loss": 1.639083743095398, | |
| "eval_runtime": 740.2556, | |
| "eval_samples_per_second": 9.834, | |
| "eval_steps_per_second": 1.229, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001156737998843262, | |
| "grad_norm": 0.9529999494552612, | |
| "learning_rate": 0.0001, | |
| "loss": 1.668, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012724117987275882, | |
| "grad_norm": 1.0801961421966553, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.7986, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0013880855986119144, | |
| "grad_norm": 0.5361855030059814, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.3109, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0015037593984962407, | |
| "grad_norm": 0.6420459747314453, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.4781, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0016194331983805667, | |
| "grad_norm": 0.8224722146987915, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.5962, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.001735106998264893, | |
| "grad_norm": 0.7396243810653687, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.5408, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0018507807981492192, | |
| "grad_norm": 1.3103138208389282, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.545, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0019664545980335453, | |
| "grad_norm": 0.8075879812240601, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.4319, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0020821283979178718, | |
| "grad_norm": 0.7657693028450012, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.4987, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0020821283979178718, | |
| "eval_loss": 1.4760798215866089, | |
| "eval_runtime": 740.2741, | |
| "eval_samples_per_second": 9.834, | |
| "eval_steps_per_second": 1.229, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002197802197802198, | |
| "grad_norm": 0.6409154534339905, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.4464, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002313475997686524, | |
| "grad_norm": 1.1145334243774414, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.6525, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0024291497975708503, | |
| "grad_norm": 0.5951794385910034, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.4047, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0025448235974551764, | |
| "grad_norm": 0.9459831118583679, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.8246, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0026604973973395024, | |
| "grad_norm": 0.5552104115486145, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.3021, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002776171197223829, | |
| "grad_norm": 0.6463938355445862, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.2261, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002891844997108155, | |
| "grad_norm": 0.5082288980484009, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3508, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0030075187969924814, | |
| "grad_norm": 0.6465054154396057, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.2657, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0031231925968768074, | |
| "grad_norm": 0.6023719906806946, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 1.4483, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0031231925968768074, | |
| "eval_loss": 1.3892802000045776, | |
| "eval_runtime": 740.4541, | |
| "eval_samples_per_second": 9.832, | |
| "eval_steps_per_second": 1.229, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0032388663967611335, | |
| "grad_norm": 0.46956098079681396, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.2895, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00335454019664546, | |
| "grad_norm": 0.5599877834320068, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 1.3907, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.003470213996529786, | |
| "grad_norm": 0.6060083508491516, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.398, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003585887796414112, | |
| "grad_norm": 0.9557406902313232, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 1.4978, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0037015615962984385, | |
| "grad_norm": 0.575370728969574, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.4165, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0038172353961827645, | |
| "grad_norm": 0.7410251498222351, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 1.3919, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.003932909196067091, | |
| "grad_norm": 0.5126181244850159, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.3076, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004048582995951417, | |
| "grad_norm": 0.5956414937973022, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.3227, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0041642567958357435, | |
| "grad_norm": 0.6212967038154602, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.2832, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0041642567958357435, | |
| "eval_loss": 1.3439499139785767, | |
| "eval_runtime": 744.255, | |
| "eval_samples_per_second": 9.782, | |
| "eval_steps_per_second": 1.223, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004279930595720069, | |
| "grad_norm": 0.5324627757072449, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.318, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.004395604395604396, | |
| "grad_norm": 0.5703225135803223, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.5839, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.004511278195488722, | |
| "grad_norm": 0.7628889679908752, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 1.517, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.004626951995373048, | |
| "grad_norm": 1.1482807397842407, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.7088, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004742625795257374, | |
| "grad_norm": 0.4733085036277771, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 1.3973, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.004858299595141701, | |
| "grad_norm": 0.7030467391014099, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.3371, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.004973973395026026, | |
| "grad_norm": 0.46287447214126587, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 1.2644, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.005089647194910353, | |
| "grad_norm": 0.482746958732605, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.3177, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005205320994794679, | |
| "grad_norm": 0.4805569350719452, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.4233, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005205320994794679, | |
| "eval_loss": 1.320542812347412, | |
| "eval_runtime": 742.5308, | |
| "eval_samples_per_second": 9.804, | |
| "eval_steps_per_second": 1.226, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005320994794679005, | |
| "grad_norm": 0.6398974657058716, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.3809, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005436668594563331, | |
| "grad_norm": 0.7115899920463562, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 1.4922, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.005552342394447658, | |
| "grad_norm": 0.539852499961853, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.1924, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.005668016194331984, | |
| "grad_norm": 0.47398844361305237, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 1.2039, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.00578368999421631, | |
| "grad_norm": 0.6044884324073792, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.3744, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.3054705844224e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |