| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 370, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.33337631821632385, | |
| "eval_runtime": 0.1147, | |
| "eval_samples_per_second": 880.656, | |
| "eval_steps_per_second": 226.704, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.3713286519050598, | |
| "eval_runtime": 0.1141, | |
| "eval_samples_per_second": 885.137, | |
| "eval_steps_per_second": 227.857, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.4043624699115753, | |
| "eval_runtime": 0.1144, | |
| "eval_samples_per_second": 883.135, | |
| "eval_steps_per_second": 227.342, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.3933059275150299, | |
| "eval_runtime": 0.1145, | |
| "eval_samples_per_second": 881.837, | |
| "eval_steps_per_second": 227.007, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.4124599099159241, | |
| "eval_runtime": 0.1149, | |
| "eval_samples_per_second": 879.298, | |
| "eval_steps_per_second": 226.354, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.4385315775871277, | |
| "eval_runtime": 0.1147, | |
| "eval_samples_per_second": 880.488, | |
| "eval_steps_per_second": 226.66, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.4169441759586334, | |
| "eval_runtime": 0.1149, | |
| "eval_samples_per_second": 879.269, | |
| "eval_steps_per_second": 226.346, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.4322397708892822, | |
| "eval_runtime": 0.1151, | |
| "eval_samples_per_second": 877.257, | |
| "eval_steps_per_second": 225.828, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.4463120996952057, | |
| "eval_runtime": 0.1144, | |
| "eval_samples_per_second": 882.807, | |
| "eval_steps_per_second": 227.257, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.449594110250473, | |
| "eval_runtime": 0.1148, | |
| "eval_samples_per_second": 879.457, | |
| "eval_steps_per_second": 226.395, | |
| "step": 370 | |
| } | |
| ], | |
| "max_steps": 370, | |
| "num_train_epochs": 10, | |
| "total_flos": 16089814007808.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |