| { | |
| "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": 19.441320419311523, | |
| "learning_rate": 9.94459753267812e-05, | |
| "loss": 8.7724, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1553398058252427, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.8175, | |
| "eval_samples_per_second": 13.097, | |
| "eval_steps_per_second": 3.405, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.3106796116504854, | |
| "grad_norm": 18.9566593170166, | |
| "learning_rate": 9.779754323328192e-05, | |
| "loss": 6.075, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.46601941747572817, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.509529358847655e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.6213592233009708, | |
| "grad_norm": 21.98307991027832, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 2.9483, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7766990291262136, | |
| "grad_norm": 15.767587661743164, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.5892, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.9320388349514563, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.14503363531613e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.116504854368932, | |
| "grad_norm": 10.572171211242676, | |
| "learning_rate": 7.542957248827961e-05, | |
| "loss": 2.0754, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.2718446601941746, | |
| "grad_norm": 2.2752199172973633, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.6063, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.4271844660194175, | |
| "grad_norm": 1.6019366979599, | |
| "learning_rate": 6.203955092681039e-05, | |
| "loss": 1008.5142, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.5825242718446602, | |
| "grad_norm": 2.708893060684204, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7441, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.737864077669903, | |
| "grad_norm": 2.626690626144409, | |
| "learning_rate": 4.7960449073189606e-05, | |
| "loss": 0.4843, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.8932038834951457, | |
| "grad_norm": 1.4577161073684692, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 1189.1025, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.0776699029126213, | |
| "grad_norm": 6.316683292388916, | |
| "learning_rate": 3.45704275117204e-05, | |
| "loss": 1.3963, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.233009708737864, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.854966364683872e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.3883495145631066, | |
| "grad_norm": 2.5094077587127686, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 173.9385, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.5436893203883493, | |
| "grad_norm": 2.281064510345459, | |
| "learning_rate": 1.8594235253127375e-05, | |
| "loss": 0.6918, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.6990291262135924, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.490470641152345e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.854368932038835, | |
| "grad_norm": 1.1867280006408691, | |
| "learning_rate": 1.2202456766718093e-05, | |
| "loss": 173.6783, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.0388349514563107, | |
| "grad_norm": 3.729489803314209, | |
| "learning_rate": 1.0554024673218807e-05, | |
| "loss": 1.3079, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.1941747572815533, | |
| "grad_norm": 1.3411588668823242, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1733, | |
| "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 | |
| } | |