| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10064412238325282, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002012882447665056, | |
| "grad_norm": 22.921390533447266, | |
| "learning_rate": 6.5e-06, | |
| "loss": 1.3427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004025764895330112, | |
| "grad_norm": 14.772722244262695, | |
| "learning_rate": 1.3e-05, | |
| "loss": 1.3647, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006038647342995169, | |
| "grad_norm": 11.458742141723633, | |
| "learning_rate": 1.9499999999999996e-05, | |
| "loss": 1.2841, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008051529790660225, | |
| "grad_norm": 4.747677326202393, | |
| "learning_rate": 2.6e-05, | |
| "loss": 1.1644, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010064412238325281, | |
| "grad_norm": 3.687121629714966, | |
| "learning_rate": 3.25e-05, | |
| "loss": 1.1084, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012077294685990338, | |
| "grad_norm": 3.178232431411743, | |
| "learning_rate": 3.899999999999999e-05, | |
| "loss": 1.0753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014090177133655395, | |
| "grad_norm": 2.476033926010132, | |
| "learning_rate": 4.5499999999999995e-05, | |
| "loss": 1.075, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01610305958132045, | |
| "grad_norm": 1.9162139892578125, | |
| "learning_rate": 5.2e-05, | |
| "loss": 1.0195, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018115942028985508, | |
| "grad_norm": 1.797377109527588, | |
| "learning_rate": 5.85e-05, | |
| "loss": 0.9884, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020128824476650563, | |
| "grad_norm": 1.816100835800171, | |
| "learning_rate": 6.5e-05, | |
| "loss": 0.9945, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02214170692431562, | |
| "grad_norm": 1.843664526939392, | |
| "learning_rate": 6.499932098548219e-05, | |
| "loss": 0.8802, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.024154589371980676, | |
| "grad_norm": 1.7202250957489014, | |
| "learning_rate": 6.49972839703017e-05, | |
| "loss": 0.9833, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.026167471819645734, | |
| "grad_norm": 1.4981484413146973, | |
| "learning_rate": 6.499388903957628e-05, | |
| "loss": 0.9481, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02818035426731079, | |
| "grad_norm": 1.4716213941574097, | |
| "learning_rate": 6.498913633516483e-05, | |
| "loss": 0.8809, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.030193236714975844, | |
| "grad_norm": 1.3817026615142822, | |
| "learning_rate": 6.498302605566152e-05, | |
| "loss": 0.9264, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0322061191626409, | |
| "grad_norm": 1.509097695350647, | |
| "learning_rate": 6.497555845638748e-05, | |
| "loss": 0.8829, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03421900161030596, | |
| "grad_norm": 1.5498337745666504, | |
| "learning_rate": 6.496673384938014e-05, | |
| "loss": 0.9227, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.036231884057971016, | |
| "grad_norm": 1.527828574180603, | |
| "learning_rate": 6.49565526033802e-05, | |
| "loss": 0.9488, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.038244766505636074, | |
| "grad_norm": 1.4578592777252197, | |
| "learning_rate": 6.494501514381621e-05, | |
| "loss": 0.8845, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.040257648953301126, | |
| "grad_norm": 1.4198046922683716, | |
| "learning_rate": 6.493212195278678e-05, | |
| "loss": 0.8809, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.042270531400966184, | |
| "grad_norm": 1.4455400705337524, | |
| "learning_rate": 6.491787356904047e-05, | |
| "loss": 0.8686, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04428341384863124, | |
| "grad_norm": 1.5711616277694702, | |
| "learning_rate": 6.490227058795323e-05, | |
| "loss": 0.96, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.046296296296296294, | |
| "grad_norm": 1.4603729248046875, | |
| "learning_rate": 6.488531366150359e-05, | |
| "loss": 0.9026, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04830917874396135, | |
| "grad_norm": 1.4184608459472656, | |
| "learning_rate": 6.48670034982453e-05, | |
| "loss": 0.9426, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05032206119162641, | |
| "grad_norm": 1.4080291986465454, | |
| "learning_rate": 6.484734086327788e-05, | |
| "loss": 0.8857, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05233494363929147, | |
| "grad_norm": 1.4739091396331787, | |
| "learning_rate": 6.482632657821454e-05, | |
| "loss": 0.8897, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05434782608695652, | |
| "grad_norm": 1.320746898651123, | |
| "learning_rate": 6.480396152114787e-05, | |
| "loss": 0.8512, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05636070853462158, | |
| "grad_norm": 1.4142905473709106, | |
| "learning_rate": 6.478024662661315e-05, | |
| "loss": 0.9459, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05837359098228664, | |
| "grad_norm": 1.3830432891845703, | |
| "learning_rate": 6.47551828855493e-05, | |
| "loss": 0.8605, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06038647342995169, | |
| "grad_norm": 1.3653528690338135, | |
| "learning_rate": 6.472877134525753e-05, | |
| "loss": 0.8446, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06239935587761675, | |
| "grad_norm": 1.3041807413101196, | |
| "learning_rate": 6.470101310935746e-05, | |
| "loss": 0.8407, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0644122383252818, | |
| "grad_norm": 1.3803820610046387, | |
| "learning_rate": 6.467190933774112e-05, | |
| "loss": 0.8505, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06642512077294686, | |
| "grad_norm": 1.3407087326049805, | |
| "learning_rate": 6.464146124652441e-05, | |
| "loss": 0.794, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06843800322061191, | |
| "grad_norm": 1.4283268451690674, | |
| "learning_rate": 6.460967010799629e-05, | |
| "loss": 0.9139, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07045088566827697, | |
| "grad_norm": 1.3512784242630005, | |
| "learning_rate": 6.457653725056568e-05, | |
| "loss": 0.807, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07246376811594203, | |
| "grad_norm": 1.3088512420654297, | |
| "learning_rate": 6.454206405870587e-05, | |
| "loss": 0.8968, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07447665056360708, | |
| "grad_norm": 1.2908034324645996, | |
| "learning_rate": 6.450625197289675e-05, | |
| "loss": 0.8447, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07648953301127215, | |
| "grad_norm": 1.3444992303848267, | |
| "learning_rate": 6.446910248956453e-05, | |
| "loss": 0.8891, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0785024154589372, | |
| "grad_norm": 1.2567275762557983, | |
| "learning_rate": 6.443061716101926e-05, | |
| "loss": 0.8134, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08051529790660225, | |
| "grad_norm": 1.3401930332183838, | |
| "learning_rate": 6.439079759539e-05, | |
| "loss": 0.8751, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08252818035426732, | |
| "grad_norm": 1.3348793983459473, | |
| "learning_rate": 6.434964545655754e-05, | |
| "loss": 0.7942, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08454106280193237, | |
| "grad_norm": 1.311357021331787, | |
| "learning_rate": 6.430716246408493e-05, | |
| "loss": 0.8461, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08655394524959742, | |
| "grad_norm": 1.3319345712661743, | |
| "learning_rate": 6.426335039314566e-05, | |
| "loss": 0.8821, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08856682769726248, | |
| "grad_norm": 1.304795742034912, | |
| "learning_rate": 6.421821107444936e-05, | |
| "loss": 0.8655, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09057971014492754, | |
| "grad_norm": 1.422869086265564, | |
| "learning_rate": 6.417174639416547e-05, | |
| "loss": 0.9261, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "grad_norm": 1.2931973934173584, | |
| "learning_rate": 6.412395829384427e-05, | |
| "loss": 0.8157, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09460547504025765, | |
| "grad_norm": 1.2984646558761597, | |
| "learning_rate": 6.407484877033586e-05, | |
| "loss": 0.7919, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0966183574879227, | |
| "grad_norm": 1.2596486806869507, | |
| "learning_rate": 6.402441987570665e-05, | |
| "loss": 0.7682, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09863123993558776, | |
| "grad_norm": 1.3544796705245972, | |
| "learning_rate": 6.397267371715368e-05, | |
| "loss": 0.9084, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10064412238325282, | |
| "grad_norm": 1.2623202800750732, | |
| "learning_rate": 6.391961245691652e-05, | |
| "loss": 0.8482, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 496, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.877172627557581e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |