| { | |
| "best_metric": 0.3033078610897064, | |
| "best_model_checkpoint": "weights/checkpoint-2400", | |
| "epoch": 2.05477107402653, | |
| "global_step": 2400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0008858447488584475, | |
| "loss": 1.0868, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.3964288830757141, | |
| "eval_rouge1": 0.1061059158446104, | |
| "eval_rouge2": 0.03465244917613476, | |
| "eval_rougeL": 0.10627894663827464, | |
| "eval_rougeLsum": 0.10587803730968609, | |
| "eval_runtime": 213.0846, | |
| "eval_samples_per_second": 11.667, | |
| "eval_steps_per_second": 1.46, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.000771689497716895, | |
| "loss": 0.4378, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.3599437475204468, | |
| "eval_rouge1": 0.10699235686427112, | |
| "eval_rouge2": 0.034402581194616595, | |
| "eval_rougeL": 0.10726814102163426, | |
| "eval_rougeLsum": 0.10683004020509843, | |
| "eval_runtime": 209.0997, | |
| "eval_samples_per_second": 11.889, | |
| "eval_steps_per_second": 1.487, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0006575342465753425, | |
| "loss": 0.3695, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.3147580027580261, | |
| "eval_rouge1": 0.10717208698017014, | |
| "eval_rouge2": 0.03477288244690299, | |
| "eval_rougeL": 0.10748345500504963, | |
| "eval_rougeLsum": 0.10712451901224819, | |
| "eval_runtime": 208.2509, | |
| "eval_samples_per_second": 11.938, | |
| "eval_steps_per_second": 1.493, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00054337899543379, | |
| "loss": 0.2645, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 0.31476476788520813, | |
| "eval_rouge1": 0.10597239490642546, | |
| "eval_rouge2": 0.033266358974880464, | |
| "eval_rougeL": 0.10614402559092825, | |
| "eval_rougeLsum": 0.10592368490095762, | |
| "eval_runtime": 208.6832, | |
| "eval_samples_per_second": 11.913, | |
| "eval_steps_per_second": 1.49, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00042922374429223744, | |
| "loss": 0.2503, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 0.3020365834236145, | |
| "eval_rouge1": 0.10566329888936485, | |
| "eval_rouge2": 0.03209767038592902, | |
| "eval_rougeL": 0.10595888780924984, | |
| "eval_rougeLsum": 0.10570986122575018, | |
| "eval_runtime": 207.8626, | |
| "eval_samples_per_second": 11.96, | |
| "eval_steps_per_second": 1.496, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.00031506849315068495, | |
| "loss": 0.2264, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 0.3033078610897064, | |
| "eval_rouge1": 0.10519725760071695, | |
| "eval_rouge2": 0.03199324082356017, | |
| "eval_rougeL": 0.10550921669284499, | |
| "eval_rougeLsum": 0.10514026310687613, | |
| "eval_runtime": 207.427, | |
| "eval_samples_per_second": 11.985, | |
| "eval_steps_per_second": 1.499, | |
| "step": 2400 | |
| } | |
| ], | |
| "max_steps": 3504, | |
| "num_train_epochs": 3, | |
| "total_flos": 5666207247866880.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |