Invalid JSON:Unexpected token 'I', ..."ad_norm": Infinity,
"... is not valid JSON
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 130, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007692307692307693, | |
| "grad_norm": Infinity, | |
| "learning_rate": 0.0, | |
| "loss": 3.1196, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.038461538461538464, | |
| "grad_norm": Infinity, | |
| "learning_rate": 6.153846153846155e-06, | |
| "loss": 3.1223, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.3846153846153847e-05, | |
| "loss": 3.1246, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11538461538461539, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.9996395276708856e-05, | |
| "loss": 3.1264, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 35.01002883911133, | |
| "learning_rate": 1.9870502626379127e-05, | |
| "loss": 2.9981, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19230769230769232, | |
| "grad_norm": 11.861149787902832, | |
| "learning_rate": 1.9566964208274254e-05, | |
| "loss": 2.531, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 7.360829830169678, | |
| "learning_rate": 1.909124299802724e-05, | |
| "loss": 2.2014, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2692307692307692, | |
| "grad_norm": 6.061845779418945, | |
| "learning_rate": 1.845190085543795e-05, | |
| "loss": 2.0137, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 3.25486421585083, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 1.8515, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34615384615384615, | |
| "grad_norm": 2.8577518463134766, | |
| "learning_rate": 1.67311180742757e-05, | |
| "loss": 1.7909, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 3.2024171352386475, | |
| "learning_rate": 1.568064746731156e-05, | |
| "loss": 1.7104, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4230769230769231, | |
| "grad_norm": 2.368898630142212, | |
| "learning_rate": 1.4527938603696376e-05, | |
| "loss": 1.6393, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 2.016225814819336, | |
| "learning_rate": 1.3293737524320798e-05, | |
| "loss": 1.5979, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 2.3714423179626465, | |
| "learning_rate": 1.2000256937760446e-05, | |
| "loss": 1.5492, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 2.853393793106079, | |
| "learning_rate": 1.0670776443910024e-05, | |
| "loss": 1.5275, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 1.7769665718078613, | |
| "learning_rate": 9.329223556089976e-06, | |
| "loss": 1.4923, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 2.4375193119049072, | |
| "learning_rate": 7.999743062239557e-06, | |
| "loss": 1.4681, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6538461538461539, | |
| "grad_norm": 2.583644151687622, | |
| "learning_rate": 6.706262475679205e-06, | |
| "loss": 1.4528, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 2.249284267425537, | |
| "learning_rate": 5.47206139630363e-06, | |
| "loss": 1.4174, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7307692307692307, | |
| "grad_norm": 2.0346739292144775, | |
| "learning_rate": 4.319352532688444e-06, | |
| "loss": 1.4044, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 1.5525047779083252, | |
| "learning_rate": 3.2688819257242963e-06, | |
| "loss": 1.3924, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "eval_loss": 1.3881758451461792, | |
| "eval_runtime": 2.1626, | |
| "eval_samples_per_second": 413.847, | |
| "eval_steps_per_second": 3.237, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8076923076923077, | |
| "grad_norm": 1.5717474222183228, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 1.38, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 1.4260509014129639, | |
| "learning_rate": 1.5480991445620541e-06, | |
| "loss": 1.375, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8846153846153846, | |
| "grad_norm": 1.3539237976074219, | |
| "learning_rate": 9.08757001972762e-07, | |
| "loss": 1.3491, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 1.4586122035980225, | |
| "learning_rate": 4.3303579172574884e-07, | |
| "loss": 1.3533, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9615384615384616, | |
| "grad_norm": 1.3738539218902588, | |
| "learning_rate": 1.2949737362087156e-07, | |
| "loss": 1.3503, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.3676426410675049, | |
| "learning_rate": 3.6047232911462506e-09, | |
| "loss": 1.3395, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 130, | |
| "total_flos": 4.795466914988032e+16, | |
| "train_loss": 1.8291644793290358, | |
| "train_runtime": 404.0129, | |
| "train_samples_per_second": 40.88, | |
| "train_steps_per_second": 0.322 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.795466914988032e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |