| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8493894165535956, | |
| "eval_steps": 50, | |
| "global_step": 350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.000980951231800518, | |
| "loss": 1.7983, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.6800895929336548, | |
| "eval_runtime": 79.4837, | |
| "eval_samples_per_second": 10.304, | |
| "eval_steps_per_second": 1.032, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0008643535534997409, | |
| "loss": 1.648, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.6579192876815796, | |
| "eval_runtime": 80.5139, | |
| "eval_samples_per_second": 10.172, | |
| "eval_steps_per_second": 1.018, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.000666265691928808, | |
| "loss": 1.6202, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 1.6476719379425049, | |
| "eval_runtime": 81.2124, | |
| "eval_samples_per_second": 10.085, | |
| "eval_steps_per_second": 1.01, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00043099136249808665, | |
| "loss": 1.5998, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 1.6405467987060547, | |
| "eval_runtime": 80.4615, | |
| "eval_samples_per_second": 10.179, | |
| "eval_steps_per_second": 1.019, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00021115129043425184, | |
| "loss": 1.5781, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 1.6351187229156494, | |
| "eval_runtime": 79.4429, | |
| "eval_samples_per_second": 10.309, | |
| "eval_steps_per_second": 1.032, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.591422293498632e-05, | |
| "loss": 1.5429, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 1.6372405290603638, | |
| "eval_runtime": 80.2927, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 1.021, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0, | |
| "loss": 1.5488, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 1.6368159055709839, | |
| "eval_runtime": 80.9154, | |
| "eval_samples_per_second": 10.122, | |
| "eval_steps_per_second": 1.013, | |
| "step": 350 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 350, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "total_flos": 9.826726868965786e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |