| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 18819, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07970667941973537, | |
| "grad_norm": 14.617377281188965, | |
| "learning_rate": 4.867155534300441e-05, | |
| "loss": 4.5164, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15941335883947075, | |
| "grad_norm": 13.107848167419434, | |
| "learning_rate": 4.7343110686008824e-05, | |
| "loss": 2.9043, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2391200382592061, | |
| "grad_norm": 18.4104061126709, | |
| "learning_rate": 4.601466602901323e-05, | |
| "loss": 2.5306, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.3188267176789415, | |
| "grad_norm": 11.45405101776123, | |
| "learning_rate": 4.4686221372017646e-05, | |
| "loss": 2.3636, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.39853339709867686, | |
| "grad_norm": 12.057182312011719, | |
| "learning_rate": 4.335777671502205e-05, | |
| "loss": 2.2193, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.4782400765184122, | |
| "grad_norm": 21.33402442932129, | |
| "learning_rate": 4.202933205802647e-05, | |
| "loss": 2.1756, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.5579467559381476, | |
| "grad_norm": 12.961982727050781, | |
| "learning_rate": 4.070088740103087e-05, | |
| "loss": 2.1019, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.637653435357883, | |
| "grad_norm": 13.711081504821777, | |
| "learning_rate": 3.937244274403529e-05, | |
| "loss": 2.0309, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.7173601147776184, | |
| "grad_norm": 10.16848087310791, | |
| "learning_rate": 3.8043998087039694e-05, | |
| "loss": 2.0221, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.7970667941973537, | |
| "grad_norm": 15.42959976196289, | |
| "learning_rate": 3.6715553430044105e-05, | |
| "loss": 1.968, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.8767734736170891, | |
| "grad_norm": 11.260416030883789, | |
| "learning_rate": 3.5387108773048516e-05, | |
| "loss": 1.9626, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.9564801530368244, | |
| "grad_norm": 14.895442008972168, | |
| "learning_rate": 3.405866411605293e-05, | |
| "loss": 1.9793, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.03618683245656, | |
| "grad_norm": 10.09549617767334, | |
| "learning_rate": 3.273021945905734e-05, | |
| "loss": 1.8907, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.1158935118762952, | |
| "grad_norm": 12.858028411865234, | |
| "learning_rate": 3.140177480206174e-05, | |
| "loss": 1.8524, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.1956001912960306, | |
| "grad_norm": 12.280284881591797, | |
| "learning_rate": 3.007333014506616e-05, | |
| "loss": 1.8517, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.275306870715766, | |
| "grad_norm": 10.79765796661377, | |
| "learning_rate": 2.8744885488070568e-05, | |
| "loss": 1.8522, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.3550135501355014, | |
| "grad_norm": 12.524330139160156, | |
| "learning_rate": 2.741644083107498e-05, | |
| "loss": 1.827, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.4347202295552366, | |
| "grad_norm": 13.051765441894531, | |
| "learning_rate": 2.6087996174079386e-05, | |
| "loss": 1.8092, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.514426908974972, | |
| "grad_norm": 11.686491012573242, | |
| "learning_rate": 2.4759551517083797e-05, | |
| "loss": 1.8128, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.5941335883947074, | |
| "grad_norm": 10.523648262023926, | |
| "learning_rate": 2.3431106860088208e-05, | |
| "loss": 1.7951, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.6738402678144428, | |
| "grad_norm": 12.37237548828125, | |
| "learning_rate": 2.210266220309262e-05, | |
| "loss": 1.7592, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.7535469472341783, | |
| "grad_norm": 13.389715194702148, | |
| "learning_rate": 2.077421754609703e-05, | |
| "loss": 1.7428, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.8332536266539137, | |
| "grad_norm": 10.13847541809082, | |
| "learning_rate": 1.944577288910144e-05, | |
| "loss": 1.7337, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.912960306073649, | |
| "grad_norm": 9.493837356567383, | |
| "learning_rate": 1.8117328232105852e-05, | |
| "loss": 1.7224, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.9926669854933845, | |
| "grad_norm": 9.915449142456055, | |
| "learning_rate": 1.6788883575110263e-05, | |
| "loss": 1.7306, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.07237366491312, | |
| "grad_norm": 10.596574783325195, | |
| "learning_rate": 1.5460438918114674e-05, | |
| "loss": 1.6675, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.152080344332855, | |
| "grad_norm": 11.658182144165039, | |
| "learning_rate": 1.4131994261119083e-05, | |
| "loss": 1.671, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.2317870237525903, | |
| "grad_norm": 10.158458709716797, | |
| "learning_rate": 1.2803549604123494e-05, | |
| "loss": 1.6658, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.3114937031723257, | |
| "grad_norm": 11.206422805786133, | |
| "learning_rate": 1.1475104947127904e-05, | |
| "loss": 1.666, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.391200382592061, | |
| "grad_norm": 10.595658302307129, | |
| "learning_rate": 1.0146660290132313e-05, | |
| "loss": 1.6523, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.4709070620117966, | |
| "grad_norm": 8.99512004852295, | |
| "learning_rate": 8.818215633136724e-06, | |
| "loss": 1.6529, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.550613741431532, | |
| "grad_norm": 8.853923797607422, | |
| "learning_rate": 7.489770976141135e-06, | |
| "loss": 1.6617, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.6303204208512674, | |
| "grad_norm": 9.30465316772461, | |
| "learning_rate": 6.161326319145545e-06, | |
| "loss": 1.6566, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.710027100271003, | |
| "grad_norm": 10.036943435668945, | |
| "learning_rate": 4.832881662149955e-06, | |
| "loss": 1.6423, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.789733779690738, | |
| "grad_norm": 12.505424499511719, | |
| "learning_rate": 3.504437005154365e-06, | |
| "loss": 1.6528, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.869440459110473, | |
| "grad_norm": 9.32070255279541, | |
| "learning_rate": 2.1759923481587757e-06, | |
| "loss": 1.6388, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.9491471385302086, | |
| "grad_norm": 13.217713356018066, | |
| "learning_rate": 8.475476911631861e-07, | |
| "loss": 1.6282, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 18819, | |
| "total_flos": 1.5511823227634976e+16, | |
| "train_loss": 1.9410085403942658, | |
| "train_runtime": 9037.5655, | |
| "train_samples_per_second": 8.329, | |
| "train_steps_per_second": 2.082 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 18819, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5511823227634976e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |