| { | |
| "best_metric": 0.7602501511573792, | |
| "best_model_checkpoint": "../outputs/13b_chat_lora_ar/checkpoint-200", | |
| "epoch": 0.6389776357827476, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.8411, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.7918, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.5909, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.2588, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00015, | |
| "loss": 1.0547, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.9741, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.9258, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.9079, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00027, | |
| "loss": 0.8687, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8257, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00028591549295774643, | |
| "loss": 0.8167, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00027183098591549294, | |
| "loss": 0.797, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002577464788732394, | |
| "loss": 0.7874, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00024366197183098588, | |
| "loss": 0.7834, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002295774647887324, | |
| "loss": 0.7813, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00021549295774647887, | |
| "loss": 0.7717, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00020140845070422533, | |
| "loss": 0.7713, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00018732394366197181, | |
| "loss": 0.766, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0001732394366197183, | |
| "loss": 0.7621, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00015915492957746478, | |
| "loss": 0.7635, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.7602501511573792, | |
| "eval_runtime": 39.349, | |
| "eval_samples_per_second": 50.827, | |
| "eval_steps_per_second": 1.601, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 313, | |
| "num_train_epochs": 1, | |
| "total_flos": 6.32024838701056e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |