| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.1941747572815533, | |
| "eval_steps": 25, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1553398058252427, | |
| "grad_norm": 19.7596492767334, | |
| "learning_rate": 9.94459753267812e-05, | |
| "loss": 8.7874, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1553398058252427, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.6496, | |
| "eval_samples_per_second": 18.871, | |
| "eval_steps_per_second": 4.906, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.3106796116504854, | |
| "grad_norm": 18.19023895263672, | |
| "learning_rate": 9.779754323328192e-05, | |
| "loss": 6.0922, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.46601941747572817, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.509529358847655e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.6213592233009708, | |
| "grad_norm": 22.119525909423828, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 2.951, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7766990291262136, | |
| "grad_norm": 22.115385055541992, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6998, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.9320388349514563, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.14503363531613e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.116504854368932, | |
| "grad_norm": 9.77929973602295, | |
| "learning_rate": 7.542957248827961e-05, | |
| "loss": 2.0242, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.2718446601941746, | |
| "grad_norm": 2.2395355701446533, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.5973, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.4271844660194175, | |
| "grad_norm": 1.8061139583587646, | |
| "learning_rate": 6.203955092681039e-05, | |
| "loss": 1035.125, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.5825242718446602, | |
| "grad_norm": 2.724635362625122, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7392, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.737864077669903, | |
| "grad_norm": 3.078632116317749, | |
| "learning_rate": 4.7960449073189606e-05, | |
| "loss": 0.4918, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.8932038834951457, | |
| "grad_norm": 1.6221729516983032, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 1166.0234, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.0776699029126213, | |
| "grad_norm": 6.7978363037109375, | |
| "learning_rate": 3.45704275117204e-05, | |
| "loss": 1.3819, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.233009708737864, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.854966364683872e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.3883495145631066, | |
| "grad_norm": 3.1250314712524414, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 176.7784, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.5436893203883493, | |
| "grad_norm": 2.3520195484161377, | |
| "learning_rate": 1.8594235253127375e-05, | |
| "loss": 0.6963, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.6990291262135924, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.490470641152345e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.854368932038835, | |
| "grad_norm": 1.6122820377349854, | |
| "learning_rate": 1.2202456766718093e-05, | |
| "loss": 171.616, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.0388349514563107, | |
| "grad_norm": 4.5468645095825195, | |
| "learning_rate": 1.0554024673218807e-05, | |
| "loss": 1.3126, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.1941747572815533, | |
| "grad_norm": 1.470098853111267, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1748, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3872334469267456e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |