| { | |
| "best_metric": 2.617305040359497, | |
| "best_model_checkpoint": "output/checkpoint-10", | |
| "epoch": 0.0016666666666666668, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 5.1377, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 5.1144, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.4e-05, | |
| "loss": 5.2944, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 5.277, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4e-05, | |
| "loss": 4.7688, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 4.7068, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 4.905, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 4.6467, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 7.2e-05, | |
| "loss": 4.4809, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8e-05, | |
| "loss": 4.4408, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 2.617305040359497, | |
| "eval_rouge1": 0.1402, | |
| "eval_rouge2": 0.0375, | |
| "eval_rougeL": 0.104, | |
| "eval_rougeLsum": 0.1032, | |
| "eval_runtime": 19.242, | |
| "eval_samples_per_second": 2.598, | |
| "eval_steps_per_second": 0.364, | |
| "step": 10 | |
| } | |
| ], | |
| "max_steps": 6000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 8969223955120128.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |