| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9968051118210862, | |
| "eval_steps": 500, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.025559105431309903, | |
| "grad_norm": 0.289137162340478, | |
| "learning_rate": 0.0, | |
| "loss": 0.3266, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.051118210862619806, | |
| "grad_norm": 0.36973551978435704, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3313, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07667731629392971, | |
| "grad_norm": 0.2732315516426874, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3303, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10223642172523961, | |
| "grad_norm": 0.2597580054860974, | |
| "learning_rate": 9.981987442712634e-06, | |
| "loss": 0.3423, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12779552715654952, | |
| "grad_norm": 0.2697449479690651, | |
| "learning_rate": 9.928079551738542e-06, | |
| "loss": 0.332, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15335463258785942, | |
| "grad_norm": 0.25309401502954254, | |
| "learning_rate": 9.838664734667496e-06, | |
| "loss": 0.327, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.17891373801916932, | |
| "grad_norm": 0.27529103447394754, | |
| "learning_rate": 9.714387227305422e-06, | |
| "loss": 0.3285, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.20447284345047922, | |
| "grad_norm": 0.2889094866893254, | |
| "learning_rate": 9.55614245194068e-06, | |
| "loss": 0.3311, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23003194888178913, | |
| "grad_norm": 0.2712110683187625, | |
| "learning_rate": 9.365070565805941e-06, | |
| "loss": 0.324, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.25559105431309903, | |
| "grad_norm": 0.24648784218290704, | |
| "learning_rate": 9.142548246219212e-06, | |
| "loss": 0.3241, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28115015974440893, | |
| "grad_norm": 0.29712964571803824, | |
| "learning_rate": 8.890178771592198e-06, | |
| "loss": 0.3244, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.30670926517571884, | |
| "grad_norm": 0.2772525502837915, | |
| "learning_rate": 8.609780469772623e-06, | |
| "loss": 0.3256, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.33226837060702874, | |
| "grad_norm": 0.2526573223769238, | |
| "learning_rate": 8.303373616950408e-06, | |
| "loss": 0.3336, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.35782747603833864, | |
| "grad_norm": 0.2635285630510388, | |
| "learning_rate": 7.973165881521435e-06, | |
| "loss": 0.3318, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.38338658146964855, | |
| "grad_norm": 0.25991946225793233, | |
| "learning_rate": 7.621536417786159e-06, | |
| "loss": 0.3266, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.40894568690095845, | |
| "grad_norm": 0.25315737536933286, | |
| "learning_rate": 7.251018724088367e-06, | |
| "loss": 0.3327, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.43450479233226835, | |
| "grad_norm": 0.24709052635535717, | |
| "learning_rate": 6.864282388901544e-06, | |
| "loss": 0.3219, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.46006389776357826, | |
| "grad_norm": 0.27814659712607975, | |
| "learning_rate": 6.464113856382752e-06, | |
| "loss": 0.3251, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.48562300319488816, | |
| "grad_norm": 0.268231192267561, | |
| "learning_rate": 6.053396349978632e-06, | |
| "loss": 0.3285, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5111821086261981, | |
| "grad_norm": 0.2714599056641117, | |
| "learning_rate": 5.635089098734394e-06, | |
| "loss": 0.3353, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.536741214057508, | |
| "grad_norm": 0.24892849217960455, | |
| "learning_rate": 5.212206015980742e-06, | |
| "loss": 0.3202, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5623003194888179, | |
| "grad_norm": 0.8000171073978954, | |
| "learning_rate": 4.78779398401926e-06, | |
| "loss": 0.324, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5878594249201278, | |
| "grad_norm": 0.25908701405057327, | |
| "learning_rate": 4.364910901265607e-06, | |
| "loss": 0.322, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6134185303514377, | |
| "grad_norm": 0.3247798502427564, | |
| "learning_rate": 3.94660365002137e-06, | |
| "loss": 0.3267, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6389776357827476, | |
| "grad_norm": 0.24656372827286238, | |
| "learning_rate": 3.5358861436172487e-06, | |
| "loss": 0.3277, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6645367412140575, | |
| "grad_norm": 0.25183717084089036, | |
| "learning_rate": 3.1357176110984578e-06, | |
| "loss": 0.3247, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6900958466453674, | |
| "grad_norm": 0.2598414197304092, | |
| "learning_rate": 2.748981275911633e-06, | |
| "loss": 0.3263, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7156549520766773, | |
| "grad_norm": 0.24396214951229034, | |
| "learning_rate": 2.3784635822138424e-06, | |
| "loss": 0.3279, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7412140575079872, | |
| "grad_norm": 0.27742140446678865, | |
| "learning_rate": 2.0268341184785674e-06, | |
| "loss": 0.3316, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7667731629392971, | |
| "grad_norm": 0.25654935409245083, | |
| "learning_rate": 1.6966263830495939e-06, | |
| "loss": 0.3236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.792332268370607, | |
| "grad_norm": 0.26688723474809534, | |
| "learning_rate": 1.390219530227378e-06, | |
| "loss": 0.3275, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8178913738019169, | |
| "grad_norm": 0.2479813064586462, | |
| "learning_rate": 1.1098212284078037e-06, | |
| "loss": 0.3197, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8434504792332268, | |
| "grad_norm": 0.2536977791931697, | |
| "learning_rate": 8.574517537807897e-07, | |
| "loss": 0.3252, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8690095846645367, | |
| "grad_norm": 0.24801829225262584, | |
| "learning_rate": 6.349294341940593e-07, | |
| "loss": 0.3355, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8945686900958466, | |
| "grad_norm": 0.2706032820742307, | |
| "learning_rate": 4.43857548059321e-07, | |
| "loss": 0.3264, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9201277955271565, | |
| "grad_norm": 0.252449919674056, | |
| "learning_rate": 2.85612772694579e-07, | |
| "loss": 0.3196, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9456869009584664, | |
| "grad_norm": 0.2498131850343059, | |
| "learning_rate": 1.6133526533250566e-07, | |
| "loss": 0.3214, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9712460063897763, | |
| "grad_norm": 0.2572325049468514, | |
| "learning_rate": 7.192044826145772e-08, | |
| "loss": 0.3252, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9968051118210862, | |
| "grad_norm": 0.29239230986253134, | |
| "learning_rate": 1.8012557287367394e-08, | |
| "loss": 0.3245, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9968051118210862, | |
| "step": 39, | |
| "total_flos": 114509424099328.0, | |
| "train_loss": 0.3272496698758541, | |
| "train_runtime": 480.0246, | |
| "train_samples_per_second": 20.832, | |
| "train_steps_per_second": 0.081 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 39, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 40, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 114509424099328.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |