| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 3433, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029129041654529567, | |
| "grad_norm": 0.13301080465316772, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.4859, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.058258083309059135, | |
| "grad_norm": 0.24819637835025787, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.5086, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08738712496358869, | |
| "grad_norm": 0.2222064584493637, | |
| "learning_rate": 6e-06, | |
| "loss": 2.4653, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11651616661811827, | |
| "grad_norm": 0.3736318349838257, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.3876, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.14564520827264782, | |
| "grad_norm": 0.44497305154800415, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3407, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.17477424992717738, | |
| "grad_norm": 0.5166358351707458, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.2951, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.20390329158170697, | |
| "grad_norm": 0.5752297043800354, | |
| "learning_rate": 1.4e-05, | |
| "loss": 2.2502, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.23303233323623654, | |
| "grad_norm": 0.8210733532905579, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.1539, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.2621613748907661, | |
| "grad_norm": 0.9511260390281677, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.1106, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.29129041654529564, | |
| "grad_norm": 0.9485260248184204, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0728, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3204194581998252, | |
| "grad_norm": 1.2509729862213135, | |
| "learning_rate": 1.9916750424140173e-05, | |
| "loss": 1.9686, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.34954849985435477, | |
| "grad_norm": 1.201899766921997, | |
| "learning_rate": 1.9668387794936857e-05, | |
| "loss": 1.9571, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.37867754150888433, | |
| "grad_norm": 1.625450849533081, | |
| "learning_rate": 1.9259047329098173e-05, | |
| "loss": 1.9467, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.40780658316341395, | |
| "grad_norm": 1.0702261924743652, | |
| "learning_rate": 1.869554451065679e-05, | |
| "loss": 1.93, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.4369356248179435, | |
| "grad_norm": 1.2770276069641113, | |
| "learning_rate": 1.7987261613738918e-05, | |
| "loss": 1.9, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4660646664724731, | |
| "grad_norm": 1.1146663427352905, | |
| "learning_rate": 1.7145991488495997e-05, | |
| "loss": 1.8802, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.49519370812700264, | |
| "grad_norm": 1.2624766826629639, | |
| "learning_rate": 1.618574121115003e-05, | |
| "loss": 1.8791, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5243227497815321, | |
| "grad_norm": 1.325671672821045, | |
| "learning_rate": 1.5122498867362679e-05, | |
| "loss": 1.8353, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5534517914360617, | |
| "grad_norm": 1.1726603507995605, | |
| "learning_rate": 1.397396735196525e-05, | |
| "loss": 1.9057, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5825808330905913, | |
| "grad_norm": 1.0342259407043457, | |
| "learning_rate": 1.2759269617261439e-05, | |
| "loss": 1.8641, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.6117098747451208, | |
| "grad_norm": 1.2554254531860352, | |
| "learning_rate": 1.1498630277493646e-05, | |
| "loss": 1.8813, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.6408389163996504, | |
| "grad_norm": 1.3348976373672485, | |
| "learning_rate": 1.0213038870731443e-05, | |
| "loss": 1.8919, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.66996795805418, | |
| "grad_norm": 1.320646047592163, | |
| "learning_rate": 8.923900384843229e-06, | |
| "loss": 1.8163, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6990969997087095, | |
| "grad_norm": 1.3995234966278076, | |
| "learning_rate": 7.65267886626396e-06, | |
| "loss": 1.8456, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.7282260413632391, | |
| "grad_norm": 1.6419973373413086, | |
| "learning_rate": 6.420540045442756e-06, | |
| "loss": 1.8961, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7573550830177687, | |
| "grad_norm": 1.266167402267456, | |
| "learning_rate": 5.247998929226381e-06, | |
| "loss": 1.8257, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.7864841246722983, | |
| "grad_norm": 1.2374173402786255, | |
| "learning_rate": 4.154578227735479e-06, | |
| "loss": 1.842, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.8156131663268279, | |
| "grad_norm": 1.1420338153839111, | |
| "learning_rate": 3.1584833028971385e-06, | |
| "loss": 1.8826, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.8447422079813575, | |
| "grad_norm": 1.4649367332458496, | |
| "learning_rate": 2.276299050713151e-06, | |
| "loss": 1.8156, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.873871249635887, | |
| "grad_norm": 1.246354341506958, | |
| "learning_rate": 1.522713764148417e-06, | |
| "loss": 1.8338, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.9030002912904166, | |
| "grad_norm": 1.3653801679611206, | |
| "learning_rate": 9.102745742990871e-07, | |
| "loss": 1.8364, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.9321293329449462, | |
| "grad_norm": 1.972670555114746, | |
| "learning_rate": 4.4917854172413567e-07, | |
| "loss": 1.8059, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.9612583745994757, | |
| "grad_norm": 1.2663543224334717, | |
| "learning_rate": 1.4710287625206654e-07, | |
| "loss": 1.8462, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.9903874162540053, | |
| "grad_norm": 1.3993514776229858, | |
| "learning_rate": 9.077112088505813e-09, | |
| "loss": 1.8679, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 3433, | |
| "total_flos": 6.253123043328e+16, | |
| "train_loss": 1.9996433352507346, | |
| "train_runtime": 916.5503, | |
| "train_samples_per_second": 7.491, | |
| "train_steps_per_second": 3.746 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3433, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.253123043328e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |