| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "global_step": 732, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0071, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 69.49572032587398, | |
| "eval_f1": 72.3955989739612, | |
| "eval_runtime": 9.3521, | |
| "eval_samples_per_second": 1036.877, | |
| "eval_steps_per_second": 3.315, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5106, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 69.23790863153553, | |
| "eval_f1": 73.11703884791969, | |
| "eval_runtime": 8.7135, | |
| "eval_samples_per_second": 1112.875, | |
| "eval_steps_per_second": 3.558, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4499, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_exact_match": 70.26915540888935, | |
| "eval_f1": 73.2316411397418, | |
| "eval_runtime": 8.6973, | |
| "eval_samples_per_second": 1114.94, | |
| "eval_steps_per_second": 3.564, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4097, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_exact_match": 70.05259358564504, | |
| "eval_f1": 72.9686899402206, | |
| "eval_runtime": 8.6799, | |
| "eval_samples_per_second": 1117.174, | |
| "eval_steps_per_second": 3.571, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3784, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_exact_match": 70.3619676188512, | |
| "eval_f1": 73.05879115940134, | |
| "eval_runtime": 8.692, | |
| "eval_samples_per_second": 1115.618, | |
| "eval_steps_per_second": 3.566, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3567, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_exact_match": 70.85696607198102, | |
| "eval_f1": 73.53518484191017, | |
| "eval_runtime": 8.6772, | |
| "eval_samples_per_second": 1117.529, | |
| "eval_steps_per_second": 3.573, | |
| "step": 732 | |
| } | |
| ], | |
| "max_steps": 1220, | |
| "num_train_epochs": 10, | |
| "total_flos": 231098185416704.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |