| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 23, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.043478260869565216, | |
| "grad_norm": 175.0689984240026, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.9054, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.21739130434782608, | |
| "grad_norm": 79.67845628958918, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 1.504, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.43478260869565216, | |
| "grad_norm": 64.35160771163739, | |
| "learning_rate": 1.4539904997395468e-05, | |
| "loss": 1.0155, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6521739130434783, | |
| "grad_norm": 9.000685319809348, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.3389, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 1.7263718654244882, | |
| "learning_rate": 1.0899347581163222e-06, | |
| "loss": 0.1693, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.11961643397808075, | |
| "eval_runtime": 68.0834, | |
| "eval_samples_per_second": 21.092, | |
| "eval_steps_per_second": 0.661, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 23, | |
| "total_flos": 4815732080640.0, | |
| "train_loss": 0.6914656097474305, | |
| "train_runtime": 333.972, | |
| "train_samples_per_second": 4.3, | |
| "train_steps_per_second": 0.069 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 23, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 4815732080640.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |