| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.03465, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.681640625, | |
| "eval_runtime": 8.3811, | |
| "eval_samples_per_second": 109.293, | |
| "eval_steps_per_second": 13.721, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.513671875, | |
| "eval_runtime": 8.2785, | |
| "eval_samples_per_second": 110.649, | |
| "eval_steps_per_second": 13.891, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5e-05, | |
| "loss": 6.5037, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 2.380859375, | |
| "eval_runtime": 8.3078, | |
| "eval_samples_per_second": 110.258, | |
| "eval_steps_per_second": 13.842, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 2.34375, | |
| "eval_runtime": 8.3276, | |
| "eval_samples_per_second": 109.996, | |
| "eval_steps_per_second": 13.81, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 5e-05, | |
| "loss": 4.8504, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 2.275390625, | |
| "eval_runtime": 8.3087, | |
| "eval_samples_per_second": 110.247, | |
| "eval_steps_per_second": 13.841, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 2.333984375, | |
| "eval_runtime": 8.287, | |
| "eval_samples_per_second": 110.535, | |
| "eval_steps_per_second": 13.877, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_loss": 2.20703125, | |
| "eval_runtime": 8.3018, | |
| "eval_samples_per_second": 110.337, | |
| "eval_steps_per_second": 13.852, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 5e-05, | |
| "loss": 4.3741, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_loss": 2.248046875, | |
| "eval_runtime": 8.2881, | |
| "eval_samples_per_second": 110.521, | |
| "eval_steps_per_second": 13.875, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_loss": 2.205078125, | |
| "eval_runtime": 8.2889, | |
| "eval_samples_per_second": 110.51, | |
| "eval_steps_per_second": 13.874, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 5e-05, | |
| "loss": 5.6907, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "eval_loss": 2.25, | |
| "eval_runtime": 8.2748, | |
| "eval_samples_per_second": 110.698, | |
| "eval_steps_per_second": 13.898, | |
| "step": 2000 | |
| } | |
| ], | |
| "max_steps": 10000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 11927855038464.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |