| { | |
| "best_metric": 1.3581866025924683, | |
| "best_model_checkpoint": "flan-t5-small-prompt/checkpoint-11702", | |
| "epoch": 2.0, | |
| "global_step": 11702, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.91454452230388e-05, | |
| "loss": 2.2473, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.82908904460776e-05, | |
| "loss": 1.9761, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.7436335669116395e-05, | |
| "loss": 1.8802, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.658178089215519e-05, | |
| "loss": 1.8477, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.572722611519399e-05, | |
| "loss": 1.8029, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.487267133823278e-05, | |
| "loss": 1.7633, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.401811656127158e-05, | |
| "loss": 1.7704, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.3163561784310376e-05, | |
| "loss": 1.7068, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.230900700734917e-05, | |
| "loss": 1.732, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.145445223038797e-05, | |
| "loss": 1.7168, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.059989745342677e-05, | |
| "loss": 1.6812, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 14.935384615384615, | |
| "eval_loss": 1.4240827560424805, | |
| "eval_rouge1": 52.0316, | |
| "eval_rouge2": 33.7896, | |
| "eval_rougeL": 49.2826, | |
| "eval_rougeLsum": 49.8238, | |
| "eval_runtime": 375.6869, | |
| "eval_samples_per_second": 13.841, | |
| "eval_steps_per_second": 1.73, | |
| "step": 5851 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.9745342676465566e-05, | |
| "loss": 1.6711, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.889078789950436e-05, | |
| "loss": 1.651, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.803623312254316e-05, | |
| "loss": 1.6327, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.718167834558196e-05, | |
| "loss": 1.6171, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.6327123568620756e-05, | |
| "loss": 1.6142, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 3.5472568791659546e-05, | |
| "loss": 1.5843, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 3.4618014014698344e-05, | |
| "loss": 1.6075, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.376345923773714e-05, | |
| "loss": 1.5917, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.290890446077594e-05, | |
| "loss": 1.5797, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.205434968381473e-05, | |
| "loss": 1.6037, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.119979490685353e-05, | |
| "loss": 1.5926, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3.0345240129892328e-05, | |
| "loss": 1.5684, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 14.967115384615385, | |
| "eval_loss": 1.3581866025924683, | |
| "eval_rouge1": 53.5315, | |
| "eval_rouge2": 35.1883, | |
| "eval_rougeL": 50.7765, | |
| "eval_rougeLsum": 51.3334, | |
| "eval_runtime": 392.0061, | |
| "eval_samples_per_second": 13.265, | |
| "eval_steps_per_second": 1.658, | |
| "step": 11702 | |
| } | |
| ], | |
| "max_steps": 29255, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.7400094802313216e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |