| { | |
| "best_metric": 2.6812992095947266, | |
| "best_model_checkpoint": "output/bill-wurtz/checkpoint-140", | |
| "epoch": 5.0, | |
| "global_step": 140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012591446386292745, | |
| "loss": 3.5789, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.577107195028616e-05, | |
| "loss": 3.3728, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.668773501204858e-05, | |
| "loss": 3.2429, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.152382364220488e-05, | |
| "loss": 3.2491, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.849121878224087e-06, | |
| "loss": 3.1415, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.1433706283569336, | |
| "eval_runtime": 0.6351, | |
| "eval_samples_per_second": 42.515, | |
| "eval_steps_per_second": 6.299, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.137086214086682e-06, | |
| "loss": 2.9586, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.7634920609188867e-05, | |
| "loss": 3.0624, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 6.461126473674133e-05, | |
| "loss": 2.9663, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00010290000000000001, | |
| "loss": 2.8978, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0001299031991261861, | |
| "loss": 2.9441, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.056016445159912, | |
| "eval_runtime": 0.6316, | |
| "eval_samples_per_second": 42.746, | |
| "eval_steps_per_second": 6.333, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00013676865759867644, | |
| "loss": 2.5878, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.762599468231201, | |
| "eval_runtime": 0.5151, | |
| "eval_samples_per_second": 40.769, | |
| "eval_steps_per_second": 5.824, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.00013040646433810595, | |
| "loss": 2.8115, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.00010509740044895205, | |
| "loss": 2.5949, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.860000000000001e-05, | |
| "loss": 2.6643, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.210259955104798e-05, | |
| "loss": 2.5837, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 6.793535661894062e-06, | |
| "loss": 2.7461, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.6894850730895996, | |
| "eval_runtime": 0.5306, | |
| "eval_samples_per_second": 39.579, | |
| "eval_steps_per_second": 5.654, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.313424013235498e-07, | |
| "loss": 2.4693, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 1.496636030269314e-05, | |
| "loss": 2.4734, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 4.594285634987545e-05, | |
| "loss": 2.5555, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 8.386493606940314e-05, | |
| "loss": 2.498, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.0001171075251893971, | |
| "loss": 2.3626, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.0001354800547756731, | |
| "loss": 2.4603, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.6920154094696045, | |
| "eval_runtime": 0.5456, | |
| "eval_samples_per_second": 38.49, | |
| "eval_steps_per_second": 5.499, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.00013335039645915404, | |
| "loss": 2.3237, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.00011137140040750914, | |
| "loss": 2.2052, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 7.62807630606869e-05, | |
| "loss": 2.2121, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 3.883557549653544e-05, | |
| "loss": 2.2551, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 1.0514719932939762e-05, | |
| "loss": 2.2849, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.2654, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.6812992095947266, | |
| "eval_runtime": 0.5264, | |
| "eval_samples_per_second": 39.891, | |
| "eval_steps_per_second": 5.699, | |
| "step": 140 | |
| } | |
| ], | |
| "max_steps": 616, | |
| "num_train_epochs": 22, | |
| "total_flos": 145278369792000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |