| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 363, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08307372793354102, | |
| "grad_norm": 1.962915062904358, | |
| "learning_rate": 0.0001950413223140496, | |
| "loss": 2.3273, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16614745586708204, | |
| "grad_norm": 1.6449666023254395, | |
| "learning_rate": 0.00018953168044077135, | |
| "loss": 1.7616, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24922118380062305, | |
| "grad_norm": 1.6963361501693726, | |
| "learning_rate": 0.0001840220385674931, | |
| "loss": 1.6516, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3322949117341641, | |
| "grad_norm": 1.6359336376190186, | |
| "learning_rate": 0.00017851239669421489, | |
| "loss": 1.7249, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4153686396677051, | |
| "grad_norm": 1.0282535552978516, | |
| "learning_rate": 0.00017300275482093664, | |
| "loss": 1.4954, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4984423676012461, | |
| "grad_norm": 1.546828031539917, | |
| "learning_rate": 0.00016749311294765842, | |
| "loss": 1.5683, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5815160955347871, | |
| "grad_norm": 1.2639796733856201, | |
| "learning_rate": 0.00016198347107438017, | |
| "loss": 1.5565, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6645898234683282, | |
| "grad_norm": 1.4530669450759888, | |
| "learning_rate": 0.00015647382920110195, | |
| "loss": 1.5476, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 1.5613621473312378, | |
| "learning_rate": 0.0001509641873278237, | |
| "loss": 1.6268, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8307372793354102, | |
| "grad_norm": 1.1224900484085083, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 1.4214, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9138110072689511, | |
| "grad_norm": 1.2382973432540894, | |
| "learning_rate": 0.0001399449035812672, | |
| "loss": 1.5272, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9968847352024922, | |
| "grad_norm": 1.1352381706237793, | |
| "learning_rate": 0.000134435261707989, | |
| "loss": 1.5175, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.074766355140187, | |
| "grad_norm": 1.2595607042312622, | |
| "learning_rate": 0.00012892561983471074, | |
| "loss": 1.3016, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.1578400830737279, | |
| "grad_norm": 1.5770200490951538, | |
| "learning_rate": 0.00012341597796143252, | |
| "loss": 1.1656, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2409138110072688, | |
| "grad_norm": 1.405395269393921, | |
| "learning_rate": 0.00011790633608815427, | |
| "loss": 1.1271, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.32398753894081, | |
| "grad_norm": 1.5035831928253174, | |
| "learning_rate": 0.00011239669421487604, | |
| "loss": 1.2738, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.407061266874351, | |
| "grad_norm": 1.508670687675476, | |
| "learning_rate": 0.0001068870523415978, | |
| "loss": 1.0836, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.490134994807892, | |
| "grad_norm": 1.6092171669006348, | |
| "learning_rate": 0.00010137741046831957, | |
| "loss": 1.2497, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.573208722741433, | |
| "grad_norm": 1.9516901969909668, | |
| "learning_rate": 9.586776859504133e-05, | |
| "loss": 1.0104, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.656282450674974, | |
| "grad_norm": 2.2300827503204346, | |
| "learning_rate": 9.035812672176309e-05, | |
| "loss": 1.222, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.739356178608515, | |
| "grad_norm": 1.575886845588684, | |
| "learning_rate": 8.484848484848486e-05, | |
| "loss": 1.1406, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.8224299065420562, | |
| "grad_norm": 1.5145474672317505, | |
| "learning_rate": 7.933884297520661e-05, | |
| "loss": 1.1102, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.9055036344755971, | |
| "grad_norm": 1.6717817783355713, | |
| "learning_rate": 7.382920110192838e-05, | |
| "loss": 1.0944, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.988577362409138, | |
| "grad_norm": 1.488754391670227, | |
| "learning_rate": 6.831955922865014e-05, | |
| "loss": 1.1411, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0664589823468327, | |
| "grad_norm": 1.4546184539794922, | |
| "learning_rate": 6.280991735537191e-05, | |
| "loss": 0.901, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.149532710280374, | |
| "grad_norm": 1.7998638153076172, | |
| "learning_rate": 5.730027548209367e-05, | |
| "loss": 0.8269, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.232606438213915, | |
| "grad_norm": 2.519369125366211, | |
| "learning_rate": 5.179063360881543e-05, | |
| "loss": 0.8049, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.3156801661474558, | |
| "grad_norm": 1.6863124370574951, | |
| "learning_rate": 4.6280991735537196e-05, | |
| "loss": 0.7497, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.398753894080997, | |
| "grad_norm": 2.0962462425231934, | |
| "learning_rate": 4.0771349862258955e-05, | |
| "loss": 0.818, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.4818276220145377, | |
| "grad_norm": 1.8604388236999512, | |
| "learning_rate": 3.526170798898072e-05, | |
| "loss": 0.8271, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.564901349948079, | |
| "grad_norm": 1.9913501739501953, | |
| "learning_rate": 2.975206611570248e-05, | |
| "loss": 0.8242, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.64797507788162, | |
| "grad_norm": 2.3578224182128906, | |
| "learning_rate": 2.4242424242424244e-05, | |
| "loss": 0.8672, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.7310488058151607, | |
| "grad_norm": 2.1878502368927, | |
| "learning_rate": 1.8732782369146007e-05, | |
| "loss": 0.7965, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.814122533748702, | |
| "grad_norm": 2.113407850265503, | |
| "learning_rate": 1.322314049586777e-05, | |
| "loss": 0.777, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.897196261682243, | |
| "grad_norm": 1.9864745140075684, | |
| "learning_rate": 7.713498622589533e-06, | |
| "loss": 0.8083, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.980269989615784, | |
| "grad_norm": 2.161090135574341, | |
| "learning_rate": 2.203856749311295e-06, | |
| "loss": 0.746, | |
| "step": 360 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 363, | |
| "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": 2884024074461184.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |