| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.19743336623889438, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019743336623889437, | |
| "grad_norm": 6.547708296445712, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.1475, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.039486673247778874, | |
| "grad_norm": 10.243558327653483, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.919, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.059230009871668314, | |
| "grad_norm": 8.190842923306958, | |
| "learning_rate": 4.999862557147196e-05, | |
| "loss": 1.0148, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07897334649555775, | |
| "grad_norm": 6.626953800225776, | |
| "learning_rate": 4.9987631049976855e-05, | |
| "loss": 1.0564, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09871668311944719, | |
| "grad_norm": 6.916811883128889, | |
| "learning_rate": 4.9965646842432604e-05, | |
| "loss": 0.9836, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11846001974333663, | |
| "grad_norm": 6.4522014440623305, | |
| "learning_rate": 4.9932682617604446e-05, | |
| "loss": 1.1074, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13820335636722605, | |
| "grad_norm": 7.70608536157259, | |
| "learning_rate": 4.988875287332459e-05, | |
| "loss": 1.1445, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1579466929911155, | |
| "grad_norm": 5.3644893348597025, | |
| "learning_rate": 4.983985645323552e-05, | |
| "loss": 1.1925, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17769002961500494, | |
| "grad_norm": 8.964673740218958, | |
| "learning_rate": 4.97751494291786e-05, | |
| "loss": 1.2047, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.19743336623889438, | |
| "grad_norm": 5.80041165915173, | |
| "learning_rate": 4.969954616956005e-05, | |
| "loss": 1.1511, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19743336623889438, | |
| "eval_loss": 1.08984375, | |
| "eval_runtime": 24.2076, | |
| "eval_samples_per_second": 37.178, | |
| "eval_steps_per_second": 4.668, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1518, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 579799351296.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |