| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.67032967032967, | |
| "global_step": 220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0006987161058019419, | |
| "loss": 0.6983, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0006909041709298167, | |
| "loss": 0.6882, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0006761524102240084, | |
| "loss": 0.688, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0006618522834659287, | |
| "loss": 0.9653, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0006360647222822923, | |
| "loss": 0.6844, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0006044537082955259, | |
| "loss": 0.7206, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.0005676627505917628, | |
| "loss": 0.6859, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.0005264408069734912, | |
| "loss": 0.6803, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 0.00048162703733850993, | |
| "loss": 0.6876, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 0.0004341337208043474, | |
| "loss": 0.672, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.00038492768433622394, | |
| "loss": 0.6803, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.0003350106209381392, | |
| "loss": 0.6804, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.00028539869807195416, | |
| "loss": 0.6505, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 0.00023710187141825318, | |
| "loss": 0.6645, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 0.00019110332509115864, | |
| "loss": 0.6214, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 0.00014833945684503654, | |
| "loss": 0.6356, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 0.00010968081571656524, | |
| "loss": 0.5941, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 7.591438015680559e-05, | |
| "loss": 0.5754, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 4.7727537419395036e-05, | |
| "loss": 0.5813, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 2.5694090338324998e-05, | |
| "loss": 0.5361, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 1.0262576356951625e-05, | |
| "loss": 0.5233, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 1.7471365991241382e-06, | |
| "loss": 0.5181, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "step": 220, | |
| "total_flos": 0.0, | |
| "train_loss": 0.6559816967357289, | |
| "train_runtime": 11143.63, | |
| "train_samples_per_second": 1.302, | |
| "train_steps_per_second": 0.02 | |
| } | |
| ], | |
| "max_steps": 220, | |
| "num_train_epochs": 10, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |