| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9823182711198428, | |
| "eval_steps": 10, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.980286753286195e-05, | |
| "loss": 1.4539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 1.4374, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 1.3338, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.285738229751587, | |
| "eval_runtime": 24.0251, | |
| "eval_samples_per_second": 5.369, | |
| "eval_steps_per_second": 1.082, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 1.286, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 1.2798, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.259059190750122, | |
| "eval_runtime": 24.0291, | |
| "eval_samples_per_second": 5.368, | |
| "eval_steps_per_second": 1.082, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0, | |
| "loss": 1.2639, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "step": 25, | |
| "total_flos": 6.39647288959959e+16, | |
| "train_loss": 1.3208525276184082, | |
| "train_runtime": 3151.0527, | |
| "train_samples_per_second": 1.613, | |
| "train_steps_per_second": 0.008 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "total_flos": 6.39647288959959e+16, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |