| { | |
| "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": 0.18838398158550262, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.3948, | |
| "mean_token_accuracy": 0.9112365245819092, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.17007271945476532, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.3779, | |
| "mean_token_accuracy": 0.9201422408223152, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.1656438410282135, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 0.3341, | |
| "mean_token_accuracy": 0.9201170861721039, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.22235730290412903, | |
| "learning_rate": 0.00019984268150178167, | |
| "loss": 0.2128, | |
| "mean_token_accuracy": 0.9411133766174317, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.15161848068237305, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.1075, | |
| "mean_token_accuracy": 0.9636118650436402, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.10428358614444733, | |
| "learning_rate": 0.00019438833303083678, | |
| "loss": 0.0631, | |
| "mean_token_accuracy": 0.9756187975406647, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.03839333727955818, | |
| "learning_rate": 0.00018884456359788724, | |
| "loss": 0.0496, | |
| "mean_token_accuracy": 0.9804835319519043, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.08242008090019226, | |
| "learning_rate": 0.00018155608689592604, | |
| "loss": 0.0536, | |
| "mean_token_accuracy": 0.9777103424072265, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.0716392770409584, | |
| "learning_rate": 0.0001726660322034027, | |
| "loss": 0.0534, | |
| "mean_token_accuracy": 0.9774137914180756, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.06007474660873413, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.0477, | |
| "mean_token_accuracy": 0.9796860992908478, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.057174865156412125, | |
| "learning_rate": 0.00015080753452465296, | |
| "loss": 0.0521, | |
| "mean_token_accuracy": 0.9778975427150727, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.044427528977394104, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0487, | |
| "mean_token_accuracy": 0.979282945394516, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.04425638169050217, | |
| "learning_rate": 0.0001249776478167227, | |
| "loss": 0.0489, | |
| "mean_token_accuracy": 0.9788806915283204, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.049495019018650055, | |
| "learning_rate": 0.00011119644761033078, | |
| "loss": 0.0464, | |
| "mean_token_accuracy": 0.9806757926940918, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.04672574624419212, | |
| "learning_rate": 9.719537437241312e-05, | |
| "loss": 0.0466, | |
| "mean_token_accuracy": 0.9799793243408204, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.03360598906874657, | |
| "learning_rate": 8.324937766952638e-05, | |
| "loss": 0.0457, | |
| "mean_token_accuracy": 0.9792504906654358, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.05028126761317253, | |
| "learning_rate": 6.963232548903853e-05, | |
| "loss": 0.0477, | |
| "mean_token_accuracy": 0.9793957650661469, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.04520723596215248, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 0.0492, | |
| "mean_token_accuracy": 0.9786539614200592, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.04504053667187691, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0449, | |
| "mean_token_accuracy": 0.9805234730243683, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.04639808461070061, | |
| "learning_rate": 3.336534220479961e-05, | |
| "loss": 0.048, | |
| "mean_token_accuracy": 0.979764848947525, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.06406909227371216, | |
| "learning_rate": 2.3596262417839255e-05, | |
| "loss": 0.0432, | |
| "mean_token_accuracy": 0.9803461849689483, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.04847242683172226, | |
| "learning_rate": 1.5327580077171587e-05, | |
| "loss": 0.045, | |
| "mean_token_accuracy": 0.9807102084159851, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.04701913148164749, | |
| "learning_rate": 8.72167349386811e-06, | |
| "loss": 0.0468, | |
| "mean_token_accuracy": 0.9801470816135407, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.06175077706575394, | |
| "learning_rate": 3.908267805490051e-06, | |
| "loss": 0.0458, | |
| "mean_token_accuracy": 0.9797519445419312, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.07118166238069534, | |
| "learning_rate": 9.818874663554357e-07, | |
| "loss": 0.0431, | |
| "mean_token_accuracy": 0.9812374770641327, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.038404762744903564, | |
| "learning_rate": 0.0, | |
| "loss": 0.0459, | |
| "mean_token_accuracy": 0.9809239029884338, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 125, | |
| "total_flos": 1.595794234802176e+16, | |
| "train_loss": 0.08204185473918915, | |
| "train_runtime": 684.8349, | |
| "train_samples_per_second": 1.46, | |
| "train_steps_per_second": 0.183 | |
| } | |
| ], | |
| "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": 1.595794234802176e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |