| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 2.881791353225708, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.5889, | |
| "mean_token_accuracy": 0.7378508150577545, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 2.391357421875, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 1.5443, | |
| "mean_token_accuracy": 0.7398458048701286, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.118521809577942, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 1.2002, | |
| "mean_token_accuracy": 0.7715764760971069, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 1.0675394535064697, | |
| "learning_rate": 0.00019984268150178167, | |
| "loss": 0.6574, | |
| "mean_token_accuracy": 0.8407589793205261, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.8859553933143616, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.2203, | |
| "mean_token_accuracy": 0.9314744651317597, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.2922598719596863, | |
| "learning_rate": 0.00019438833303083678, | |
| "loss": 0.13, | |
| "mean_token_accuracy": 0.9530190467834473, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.20312735438346863, | |
| "learning_rate": 0.00018884456359788724, | |
| "loss": 0.1211, | |
| "mean_token_accuracy": 0.954474687576294, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.20204055309295654, | |
| "learning_rate": 0.00018155608689592604, | |
| "loss": 0.118, | |
| "mean_token_accuracy": 0.9528149247169495, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.23521462082862854, | |
| "learning_rate": 0.0001726660322034027, | |
| "loss": 0.1129, | |
| "mean_token_accuracy": 0.9575592815876007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.2090936303138733, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.114, | |
| "mean_token_accuracy": 0.9550538718700409, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.1480427235364914, | |
| "learning_rate": 0.00015080753452465296, | |
| "loss": 0.1106, | |
| "mean_token_accuracy": 0.9557833790779113, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.16799816489219666, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.1108, | |
| "mean_token_accuracy": 0.9567516028881073, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.15008902549743652, | |
| "learning_rate": 0.0001249776478167227, | |
| "loss": 0.1101, | |
| "mean_token_accuracy": 0.9583537817001343, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.3704455494880676, | |
| "learning_rate": 0.00011119644761033078, | |
| "loss": 0.1059, | |
| "mean_token_accuracy": 0.9594001948833466, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.24417561292648315, | |
| "learning_rate": 9.719537437241312e-05, | |
| "loss": 0.1062, | |
| "mean_token_accuracy": 0.9597463130950927, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.11766213178634644, | |
| "learning_rate": 8.324937766952638e-05, | |
| "loss": 0.106, | |
| "mean_token_accuracy": 0.9577570855617523, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.18638619780540466, | |
| "learning_rate": 6.963232548903853e-05, | |
| "loss": 0.1121, | |
| "mean_token_accuracy": 0.9562596201896667, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.10747609287500381, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 0.1061, | |
| "mean_token_accuracy": 0.958360093832016, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.10966020822525024, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.1037, | |
| "mean_token_accuracy": 0.959806889295578, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.07960451394319534, | |
| "learning_rate": 3.336534220479961e-05, | |
| "loss": 0.1102, | |
| "mean_token_accuracy": 0.9574779450893403, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.09165750443935394, | |
| "learning_rate": 2.3596262417839255e-05, | |
| "loss": 0.1045, | |
| "mean_token_accuracy": 0.9585564255714416, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.12533125281333923, | |
| "learning_rate": 1.5327580077171587e-05, | |
| "loss": 0.1084, | |
| "mean_token_accuracy": 0.9575954079627991, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.10980326682329178, | |
| "learning_rate": 8.72167349386811e-06, | |
| "loss": 0.1048, | |
| "mean_token_accuracy": 0.960148960351944, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.10381416231393814, | |
| "learning_rate": 3.908267805490051e-06, | |
| "loss": 0.1053, | |
| "mean_token_accuracy": 0.9586725831031799, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.10477844625711441, | |
| "learning_rate": 9.818874663554357e-07, | |
| "loss": 0.1047, | |
| "mean_token_accuracy": 0.9589699864387512, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.3871605694293976, | |
| "learning_rate": 0.0, | |
| "loss": 0.1508, | |
| "mean_token_accuracy": 0.9559036910533905, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 125, | |
| "total_flos": 628397218725888.0, | |
| "train_loss": 0.0, | |
| "train_runtime": 2.265, | |
| "train_samples_per_second": 441.506, | |
| "train_steps_per_second": 55.188 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 628397218725888.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |