| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.5, | |
| "eval_steps": 500, | |
| "global_step": 175, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 5.114527702331543, | |
| "learning_rate": 0.00019998209226697376, | |
| "loss": 0.7202, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 3.297234296798706, | |
| "learning_rate": 0.00019784091409455728, | |
| "loss": 0.3157, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 1.1975072622299194, | |
| "learning_rate": 0.00019220586030376134, | |
| "loss": 0.216, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 1.313912034034729, | |
| "learning_rate": 0.00018327815731637612, | |
| "loss": 0.1807, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.9035260677337646, | |
| "learning_rate": 0.0001713766112687139, | |
| "loss": 0.1576, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 1.169536828994751, | |
| "learning_rate": 0.00015692622352080662, | |
| "loss": 0.1362, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.7937868237495422, | |
| "learning_rate": 0.0001404430139595877, | |
| "loss": 0.1172, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.6412622928619385, | |
| "learning_rate": 0.00012251559405226941, | |
| "loss": 0.1065, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 0.6135754585266113, | |
| "learning_rate": 0.00010378414767176705, | |
| "loss": 0.0952, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.6013264060020447, | |
| "learning_rate": 8.491757028386263e-05, | |
| "loss": 0.1005, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 0.7380222082138062, | |
| "learning_rate": 6.658958285026102e-05, | |
| "loss": 0.0794, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.42198696732521057, | |
| "learning_rate": 4.945467341434195e-05, | |
| "loss": 0.1008, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": 0.3692607879638672, | |
| "learning_rate": 3.4124725489820645e-05, | |
| "loss": 0.0545, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.5357337594032288, | |
| "learning_rate": 2.1147167846963422e-05, | |
| "loss": 0.0585, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 0.45641225576400757, | |
| "learning_rate": 1.0985425962260343e-05, | |
| "loss": 0.0608, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.21990008652210236, | |
| "learning_rate": 4.002373205607723e-06, | |
| "loss": 0.0544, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.4285714285714284, | |
| "grad_norm": 0.41038212180137634, | |
| "learning_rate": 4.4737271914411236e-07, | |
| "loss": 0.048, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "step": 175, | |
| "total_flos": 6343017759525312.0, | |
| "train_loss": 0.15042741894721984, | |
| "train_runtime": 99.7314, | |
| "train_samples_per_second": 28.075, | |
| "train_steps_per_second": 1.755 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 175, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6343017759525312.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |