| { | |
| "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": 4.959076881408691, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.8894, | |
| "mean_token_accuracy": 0.6759726703166962, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 3.325948715209961, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 1.8457, | |
| "mean_token_accuracy": 0.6744399294257164, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.0953567028045654, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 1.3863, | |
| "mean_token_accuracy": 0.7154875338077545, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.8824595212936401, | |
| "learning_rate": 0.00019984268150178167, | |
| "loss": 0.8812, | |
| "mean_token_accuracy": 0.802780419588089, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.7127411365509033, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.3838, | |
| "mean_token_accuracy": 0.9001224040985107, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.5814230442047119, | |
| "learning_rate": 0.00019438833303083678, | |
| "loss": 0.1288, | |
| "mean_token_accuracy": 0.9640743255615234, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.3094175457954407, | |
| "learning_rate": 0.00018884456359788724, | |
| "loss": 0.091, | |
| "mean_token_accuracy": 0.9696201145648956, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.28704366087913513, | |
| "learning_rate": 0.00018155608689592604, | |
| "loss": 0.0822, | |
| "mean_token_accuracy": 0.9697297215461731, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.10918337106704712, | |
| "learning_rate": 0.0001726660322034027, | |
| "loss": 0.0786, | |
| "mean_token_accuracy": 0.9703457236289978, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.10930587351322174, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.0757, | |
| "mean_token_accuracy": 0.9704258263111114, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.08647102862596512, | |
| "learning_rate": 0.00015080753452465296, | |
| "loss": 0.0725, | |
| "mean_token_accuracy": 0.9722082138061523, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.11223802715539932, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0766, | |
| "mean_token_accuracy": 0.9705742001533508, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.10774961858987808, | |
| "learning_rate": 0.0001249776478167227, | |
| "loss": 0.0715, | |
| "mean_token_accuracy": 0.9713926434516906, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.18533609807491302, | |
| "learning_rate": 0.00011119644761033078, | |
| "loss": 0.0742, | |
| "mean_token_accuracy": 0.9715357601642609, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.1414521187543869, | |
| "learning_rate": 9.719537437241312e-05, | |
| "loss": 0.0726, | |
| "mean_token_accuracy": 0.9722862243652344, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.11008978635072708, | |
| "learning_rate": 8.324937766952638e-05, | |
| "loss": 0.0726, | |
| "mean_token_accuracy": 0.9715758740901947, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.0934567004442215, | |
| "learning_rate": 6.963232548903853e-05, | |
| "loss": 0.0698, | |
| "mean_token_accuracy": 0.9724796772003174, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.09209822118282318, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 0.0714, | |
| "mean_token_accuracy": 0.9721440374851227, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.09165395051240921, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0699, | |
| "mean_token_accuracy": 0.9724449038505554, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.09419706463813782, | |
| "learning_rate": 3.336534220479961e-05, | |
| "loss": 0.0729, | |
| "mean_token_accuracy": 0.9713936984539032, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.08532276749610901, | |
| "learning_rate": 2.3596262417839255e-05, | |
| "loss": 0.0713, | |
| "mean_token_accuracy": 0.971445506811142, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.11239537596702576, | |
| "learning_rate": 1.5327580077171587e-05, | |
| "loss": 0.0705, | |
| "mean_token_accuracy": 0.9732583463191986, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.06490039080381393, | |
| "learning_rate": 8.72167349386811e-06, | |
| "loss": 0.0712, | |
| "mean_token_accuracy": 0.9731930553913116, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.07825157046318054, | |
| "learning_rate": 3.908267805490051e-06, | |
| "loss": 0.0705, | |
| "mean_token_accuracy": 0.9729720294475556, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.10481598228216171, | |
| "learning_rate": 9.818874663554357e-07, | |
| "loss": 0.0697, | |
| "mean_token_accuracy": 0.9719029128551483, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.12130062282085419, | |
| "learning_rate": 0.0, | |
| "loss": 0.0704, | |
| "mean_token_accuracy": 0.9729031443595886, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.07161793857812881, | |
| "eval_mean_token_accuracy": 0.9721314153671264, | |
| "eval_runtime": 39.9967, | |
| "eval_samples_per_second": 50.004, | |
| "eval_steps_per_second": 6.251, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 125, | |
| "total_flos": 948716719046656.0, | |
| "train_loss": 0.24438688468933106, | |
| "train_runtime": 137.7503, | |
| "train_samples_per_second": 7.26, | |
| "train_steps_per_second": 0.907 | |
| } | |
| ], | |
| "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": 948716719046656.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |