| { | |
| "best_metric": 0.8395341634750366, | |
| "best_model_checkpoint": "../outputs/7b_chat_lora_ar/checkpoint-200", | |
| "epoch": 0.7662835249042146, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.0671, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.9822, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.731, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.439, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00015, | |
| "loss": 1.2119, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.0864, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.0386, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.9894, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00027, | |
| "loss": 0.9454, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9238, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00028136645962732916, | |
| "loss": 0.9011, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00026273291925465835, | |
| "loss": 0.8916, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00024409937888198756, | |
| "loss": 0.8839, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00022546583850931675, | |
| "loss": 0.8757, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00020683229813664593, | |
| "loss": 0.8617, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00018819875776397512, | |
| "loss": 0.8598, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00016956521739130433, | |
| "loss": 0.8515, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00015093167701863352, | |
| "loss": 0.8523, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00013229813664596273, | |
| "loss": 0.8419, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00011366459627329192, | |
| "loss": 0.8356, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.8395341634750366, | |
| "eval_runtime": 25.8353, | |
| "eval_samples_per_second": 77.414, | |
| "eval_steps_per_second": 2.439, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 261, | |
| "num_train_epochs": 1, | |
| "total_flos": 3.8996439031873536e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |