| { | |
| "best_metric": 0.7962789535522461, | |
| "best_model_checkpoint": "../outputs/13b_chat_lora_0/checkpoint-200", | |
| "epoch": 0.6825938566552902, | |
| "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": 1.591, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.5586, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.3909, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.1395, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00015, | |
| "loss": 0.9936, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.939, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.9151, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.8975, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00027, | |
| "loss": 0.8636, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8319, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00028445595854922277, | |
| "loss": 0.8163, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00026891191709844557, | |
| "loss": 0.814, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00025336787564766836, | |
| "loss": 0.8116, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002378238341968912, | |
| "loss": 0.8058, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00022227979274611396, | |
| "loss": 0.8039, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00020673575129533678, | |
| "loss": 0.8035, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00019119170984455958, | |
| "loss": 0.7976, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00017564766839378237, | |
| "loss": 0.7947, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00016010362694300517, | |
| "loss": 0.7911, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00014455958549222797, | |
| "loss": 0.7928, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.7962789535522461, | |
| "eval_runtime": 39.6388, | |
| "eval_samples_per_second": 50.456, | |
| "eval_steps_per_second": 1.589, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 293, | |
| "num_train_epochs": 1, | |
| "total_flos": 6.32024838701056e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |