| { | |
| "best_metric": 0.9095029239766083, | |
| "best_model_checkpoint": "./priority_model\\checkpoint-46", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 46, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.43478260869565216, | |
| "grad_norm": 5.8311944007873535, | |
| "learning_rate": 1.8550724637681162e-05, | |
| "loss": 1.0181, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 7.023670196533203, | |
| "learning_rate": 1.710144927536232e-05, | |
| "loss": 0.8761, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8888888888888888, | |
| "eval_f1": 0.8887926887926887, | |
| "eval_loss": 0.6216873526573181, | |
| "eval_runtime": 1.0711, | |
| "eval_samples_per_second": 42.014, | |
| "eval_steps_per_second": 5.602, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3043478260869565, | |
| "grad_norm": 5.623006820678711, | |
| "learning_rate": 1.565217391304348e-05, | |
| "loss": 0.7532, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7391304347826086, | |
| "grad_norm": 9.884881973266602, | |
| "learning_rate": 1.420289855072464e-05, | |
| "loss": 0.5316, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9111111111111111, | |
| "eval_f1": 0.9095029239766083, | |
| "eval_loss": 0.3368909955024719, | |
| "eval_runtime": 1.0808, | |
| "eval_samples_per_second": 41.635, | |
| "eval_steps_per_second": 5.551, | |
| "step": 46 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 138, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "total_flos": 16372643532840.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |