| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2946593001841621, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014732965009208103, | |
| "eval_loss": 3.2565059661865234, | |
| "eval_runtime": 9.5073, | |
| "eval_samples_per_second": 30.082, | |
| "eval_steps_per_second": 15.041, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014732965009208104, | |
| "grad_norm": 9.559073448181152, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 12.2293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029465930018416207, | |
| "grad_norm": 4.93825101852417, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 9.9564, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04419889502762431, | |
| "grad_norm": 9.91961669921875, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 9.8079, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.058931860036832415, | |
| "grad_norm": 5.816501140594482, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 9.2638, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07366482504604052, | |
| "grad_norm": 9.118745803833008, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 8.4909, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07366482504604052, | |
| "eval_loss": 2.232351541519165, | |
| "eval_runtime": 9.4871, | |
| "eval_samples_per_second": 30.146, | |
| "eval_steps_per_second": 15.073, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08839779005524862, | |
| "grad_norm": 9.087752342224121, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 9.2702, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10313075506445672, | |
| "grad_norm": 7.378783702850342, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 8.6637, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11786372007366483, | |
| "grad_norm": 8.353407859802246, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 8.1776, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13259668508287292, | |
| "grad_norm": 5.851109504699707, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 6.9892, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.14732965009208104, | |
| "grad_norm": 6.5868635177612305, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 7.9818, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14732965009208104, | |
| "eval_loss": 1.9617358446121216, | |
| "eval_runtime": 9.4797, | |
| "eval_samples_per_second": 30.17, | |
| "eval_steps_per_second": 15.085, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16206261510128914, | |
| "grad_norm": 6.711369514465332, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 7.8214, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.17679558011049723, | |
| "grad_norm": 14.236952781677246, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 7.9774, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.19152854511970535, | |
| "grad_norm": 7.926298141479492, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 7.2531, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.20626151012891344, | |
| "grad_norm": 13.80014419555664, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 7.1338, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.22099447513812154, | |
| "grad_norm": 9.227843284606934, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 7.1253, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22099447513812154, | |
| "eval_loss": 1.8401877880096436, | |
| "eval_runtime": 9.4754, | |
| "eval_samples_per_second": 30.183, | |
| "eval_steps_per_second": 15.092, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23572744014732966, | |
| "grad_norm": 8.340475082397461, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 7.8165, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2504604051565378, | |
| "grad_norm": 6.904959678649902, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 7.3912, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.26519337016574585, | |
| "grad_norm": 12.668907165527344, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 7.2124, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.27992633517495397, | |
| "grad_norm": 7.423076629638672, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 7.2794, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2946593001841621, | |
| "grad_norm": 7.438624858856201, | |
| "learning_rate": 0.0, | |
| "loss": 6.928, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2946593001841621, | |
| "eval_loss": 1.818465232849121, | |
| "eval_runtime": 9.4776, | |
| "eval_samples_per_second": 30.177, | |
| "eval_steps_per_second": 15.088, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2900734689214464e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |