{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 587, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.034122414160801876, "grad_norm": 1.6668727397918701, "learning_rate": 0.00019352640545144804, "loss": 0.7694, "step": 20 }, { "epoch": 0.06824482832160375, "grad_norm": 0.21274727582931519, "learning_rate": 0.00018671209540034071, "loss": 0.5698, "step": 40 }, { "epoch": 0.10236724248240563, "grad_norm": 0.20601236820220947, "learning_rate": 0.00017989778534923342, "loss": 0.5165, "step": 60 }, { "epoch": 0.1364896566432075, "grad_norm": 0.16878707706928253, "learning_rate": 0.00017308347529812606, "loss": 0.4943, "step": 80 }, { "epoch": 0.1706120708040094, "grad_norm": 0.19937162101268768, "learning_rate": 0.00016626916524701874, "loss": 0.4983, "step": 100 }, { "epoch": 0.20473448496481125, "grad_norm": 0.177525132894516, "learning_rate": 0.0001594548551959114, "loss": 0.4832, "step": 120 }, { "epoch": 0.23885689912561314, "grad_norm": 0.18477697670459747, "learning_rate": 0.0001526405451448041, "loss": 0.4726, "step": 140 }, { "epoch": 0.272979313286415, "grad_norm": 0.22934305667877197, "learning_rate": 0.00014582623509369678, "loss": 0.4635, "step": 160 }, { "epoch": 0.30710172744721687, "grad_norm": 0.18813876807689667, "learning_rate": 0.00013901192504258943, "loss": 0.4676, "step": 180 }, { "epoch": 0.3412241416080188, "grad_norm": 0.1780325025320053, "learning_rate": 0.0001321976149914821, "loss": 0.4598, "step": 200 }, { "epoch": 0.37534655576882064, "grad_norm": 0.18301406502723694, "learning_rate": 0.0001253833049403748, "loss": 0.4586, "step": 220 }, { "epoch": 0.4094689699296225, "grad_norm": 0.17943307757377625, "learning_rate": 0.00011856899488926747, "loss": 0.4596, "step": 240 }, { "epoch": 0.4435913840904244, "grad_norm": 0.19352082908153534, "learning_rate": 0.00011175468483816014, "loss": 0.4606, "step": 260 }, { "epoch": 0.4777137982512263, "grad_norm": 0.17654815316200256, "learning_rate": 0.00010494037478705281, "loss": 0.4625, "step": 280 }, { "epoch": 0.5118362124120281, "grad_norm": 0.18599700927734375, "learning_rate": 9.812606473594549e-05, "loss": 0.4565, "step": 300 }, { "epoch": 0.54595862657283, "grad_norm": 0.17508305609226227, "learning_rate": 9.131175468483818e-05, "loss": 0.4507, "step": 320 }, { "epoch": 0.5800810407336319, "grad_norm": 0.17217782139778137, "learning_rate": 8.449744463373084e-05, "loss": 0.4484, "step": 340 }, { "epoch": 0.6142034548944337, "grad_norm": 0.18936365842819214, "learning_rate": 7.768313458262352e-05, "loss": 0.4489, "step": 360 }, { "epoch": 0.6483258690552357, "grad_norm": 0.18922582268714905, "learning_rate": 7.086882453151618e-05, "loss": 0.4562, "step": 380 }, { "epoch": 0.6824482832160376, "grad_norm": 0.19086803495883942, "learning_rate": 6.405451448040887e-05, "loss": 0.4397, "step": 400 }, { "epoch": 0.7165706973768394, "grad_norm": 0.19476929306983948, "learning_rate": 5.724020442930154e-05, "loss": 0.4443, "step": 420 }, { "epoch": 0.7506931115376413, "grad_norm": 0.18943387269973755, "learning_rate": 5.0425894378194205e-05, "loss": 0.4493, "step": 440 }, { "epoch": 0.7848155256984432, "grad_norm": 0.21053119003772736, "learning_rate": 4.3611584327086886e-05, "loss": 0.4449, "step": 460 }, { "epoch": 0.818937939859245, "grad_norm": 0.19237090647220612, "learning_rate": 3.679727427597956e-05, "loss": 0.4491, "step": 480 }, { "epoch": 0.8530603540200469, "grad_norm": 0.20494739711284637, "learning_rate": 2.9982964224872234e-05, "loss": 0.4437, "step": 500 }, { "epoch": 0.8871827681808488, "grad_norm": 0.19343893229961395, "learning_rate": 2.3168654173764907e-05, "loss": 0.4365, "step": 520 }, { "epoch": 0.9213051823416507, "grad_norm": 0.19793441891670227, "learning_rate": 1.635434412265758e-05, "loss": 0.4443, "step": 540 }, { "epoch": 0.9554275965024526, "grad_norm": 0.19290302693843842, "learning_rate": 9.540034071550257e-06, "loss": 0.4369, "step": 560 }, { "epoch": 0.9895500106632544, "grad_norm": 0.2006407529115677, "learning_rate": 2.7257240204429304e-06, "loss": 0.4445, "step": 580 } ], "logging_steps": 20, "max_steps": 587, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 8.080141922913485e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }