| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9993343687597072, | |
| "eval_steps": 500, | |
| "global_step": 1126, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.74387526512146, | |
| "learning_rate": 6.106194690265487e-06, | |
| "loss": 10.8673, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 2.843221426010132, | |
| "learning_rate": 1.2743362831858408e-05, | |
| "loss": 10.3682, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 2.8696110248565674, | |
| "learning_rate": 1.9380530973451328e-05, | |
| "loss": 9.237, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 1.3768067359924316, | |
| "learning_rate": 2.601769911504425e-05, | |
| "loss": 7.662, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 1.8718193769454956, | |
| "learning_rate": 2.9703849950641657e-05, | |
| "loss": 6.5011, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 1.3883230686187744, | |
| "learning_rate": 2.899308983218164e-05, | |
| "loss": 5.4884, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.0601733922958374, | |
| "learning_rate": 2.8252714708785782e-05, | |
| "loss": 4.8107, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.9832029938697815, | |
| "learning_rate": 2.7512339585389932e-05, | |
| "loss": 4.384, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.0105878114700317, | |
| "learning_rate": 2.677196446199408e-05, | |
| "loss": 4.1117, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1.2003360986709595, | |
| "learning_rate": 2.6031589338598225e-05, | |
| "loss": 3.8207, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 1.0249788761138916, | |
| "learning_rate": 2.529121421520237e-05, | |
| "loss": 3.6499, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 1.2118958234786987, | |
| "learning_rate": 2.4550839091806515e-05, | |
| "loss": 3.5689, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 1.0994243621826172, | |
| "learning_rate": 2.3810463968410662e-05, | |
| "loss": 3.4153, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 1.3940232992172241, | |
| "learning_rate": 2.307008884501481e-05, | |
| "loss": 3.2788, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 1.3793669939041138, | |
| "learning_rate": 2.2329713721618955e-05, | |
| "loss": 3.0424, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 1.6049970388412476, | |
| "learning_rate": 2.15893385982231e-05, | |
| "loss": 3.0105, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 1.6481398344039917, | |
| "learning_rate": 2.0848963474827245e-05, | |
| "loss": 2.9522, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.9402527809143066, | |
| "learning_rate": 2.010858835143139e-05, | |
| "loss": 2.8484, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 3.9975693225860596, | |
| "learning_rate": 1.9368213228035538e-05, | |
| "loss": 2.7488, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 2.3999898433685303, | |
| "learning_rate": 1.8627838104639688e-05, | |
| "loss": 2.6719, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 2.681518077850342, | |
| "learning_rate": 1.788746298124383e-05, | |
| "loss": 2.5165, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 3.2228667736053467, | |
| "learning_rate": 1.7147087857847977e-05, | |
| "loss": 2.4539, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 2.7527260780334473, | |
| "learning_rate": 1.6406712734452124e-05, | |
| "loss": 2.4722, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 2.6381165981292725, | |
| "learning_rate": 1.5666337611056267e-05, | |
| "loss": 2.331, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 2.7754085063934326, | |
| "learning_rate": 1.4925962487660415e-05, | |
| "loss": 2.2549, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 2.6391360759735107, | |
| "learning_rate": 1.4185587364264562e-05, | |
| "loss": 2.214, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.563453197479248, | |
| "learning_rate": 1.3445212240868707e-05, | |
| "loss": 2.262, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 2.6172292232513428, | |
| "learning_rate": 1.2704837117472853e-05, | |
| "loss": 2.1302, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 2.8900041580200195, | |
| "learning_rate": 1.1964461994077e-05, | |
| "loss": 2.0746, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 2.4479780197143555, | |
| "learning_rate": 1.1224086870681145e-05, | |
| "loss": 1.9904, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 2.833683967590332, | |
| "learning_rate": 1.0483711747285293e-05, | |
| "loss": 2.1597, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 2.8591232299804688, | |
| "learning_rate": 9.743336623889438e-06, | |
| "loss": 2.0252, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 2.5961415767669678, | |
| "learning_rate": 9.002961500493583e-06, | |
| "loss": 2.0082, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 3.318519353866577, | |
| "learning_rate": 8.26258637709773e-06, | |
| "loss": 1.9316, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 2.528031826019287, | |
| "learning_rate": 7.522211253701876e-06, | |
| "loss": 2.0105, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 2.732753038406372, | |
| "learning_rate": 6.7818361303060216e-06, | |
| "loss": 1.9798, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 3.0377025604248047, | |
| "learning_rate": 6.041461006910168e-06, | |
| "loss": 1.928, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 2.2801241874694824, | |
| "learning_rate": 5.301085883514315e-06, | |
| "loss": 1.9888, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 2.3720247745513916, | |
| "learning_rate": 4.56071076011846e-06, | |
| "loss": 1.8992, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 2.735081195831299, | |
| "learning_rate": 3.820335636722606e-06, | |
| "loss": 1.8668, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 2.3813605308532715, | |
| "learning_rate": 3.0799605133267522e-06, | |
| "loss": 2.0131, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 2.1669371128082275, | |
| "learning_rate": 2.3395853899308984e-06, | |
| "loss": 1.9027, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 3.2110283374786377, | |
| "learning_rate": 1.5992102665350445e-06, | |
| "loss": 1.7928, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 2.6622347831726074, | |
| "learning_rate": 8.588351431391905e-07, | |
| "loss": 1.8259, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.6261448860168457, | |
| "learning_rate": 1.1846001974333663e-07, | |
| "loss": 1.8333, | |
| "step": 1125 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1126, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 1.992942617100288e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |