| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 5972, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.7488278633623578e-05, | |
| "loss": 0.0111, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.011657167226076126, | |
| "eval_runtime": 165.5471, | |
| "eval_samples_per_second": 309.211, | |
| "eval_steps_per_second": 4.832, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.4976557267247155e-05, | |
| "loss": 0.0095, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.246483590087073e-05, | |
| "loss": 0.0092, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.011485742405056953, | |
| "eval_runtime": 165.5589, | |
| "eval_samples_per_second": 309.189, | |
| "eval_steps_per_second": 4.832, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.9953114534494306e-05, | |
| "loss": 0.0091, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.7441393168117883e-05, | |
| "loss": 0.009, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.011583332903683186, | |
| "eval_runtime": 165.5818, | |
| "eval_samples_per_second": 309.146, | |
| "eval_steps_per_second": 4.831, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.4929671801741461e-05, | |
| "loss": 0.0091, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.2417950435365037e-05, | |
| "loss": 0.0079, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 0.01197287067770958, | |
| "eval_runtime": 165.5801, | |
| "eval_samples_per_second": 309.15, | |
| "eval_steps_per_second": 4.831, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 9.906229068988614e-06, | |
| "loss": 0.008, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.394507702612191e-06, | |
| "loss": 0.008, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.012653556652367115, | |
| "eval_runtime": 165.5534, | |
| "eval_samples_per_second": 309.199, | |
| "eval_steps_per_second": 4.832, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.882786336235767e-06, | |
| "loss": 0.0077, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.3710649698593436e-06, | |
| "loss": 0.0073, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.012686667963862419, | |
| "eval_runtime": 165.5035, | |
| "eval_samples_per_second": 309.293, | |
| "eval_steps_per_second": 4.834, | |
| "step": 5970 | |
| } | |
| ], | |
| "max_steps": 5972, | |
| "num_train_epochs": 2, | |
| "total_flos": 2.01113970314453e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |