| { | |
| "best_metric": 0.579126238822937, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-600", | |
| "epoch": 0.15643332029722332, | |
| "eval_steps": 50, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00026072220049537216, | |
| "eval_loss": 2.0383806228637695, | |
| "eval_runtime": 508.8695, | |
| "eval_samples_per_second": 12.695, | |
| "eval_steps_per_second": 3.174, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026072220049537216, | |
| "grad_norm": 14.43869400024414, | |
| "learning_rate": 0.0002, | |
| "loss": 4.3187, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005214444009907443, | |
| "grad_norm": 16.409202575683594, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 3.3223, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007821666014861166, | |
| "grad_norm": 17.23414421081543, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 3.5692, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010428888019814887, | |
| "grad_norm": 21.548076629638672, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 3.5142, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013036110024768609, | |
| "grad_norm": 25.257431030273438, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 4.3892, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013036110024768609, | |
| "eval_loss": 0.8825841546058655, | |
| "eval_runtime": 512.9624, | |
| "eval_samples_per_second": 12.594, | |
| "eval_steps_per_second": 3.148, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01564333202972233, | |
| "grad_norm": 13.57625961303711, | |
| "learning_rate": 0.0001964767868814516, | |
| "loss": 3.0624, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.018250554034676052, | |
| "grad_norm": 13.32381820678711, | |
| "learning_rate": 0.00019493976084683813, | |
| "loss": 2.9754, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.020857776039629773, | |
| "grad_norm": 14.278241157531738, | |
| "learning_rate": 0.00019313361774523385, | |
| "loss": 3.3012, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.023464998044583497, | |
| "grad_norm": 50.32378387451172, | |
| "learning_rate": 0.00019106347728549135, | |
| "loss": 3.306, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.026072220049537218, | |
| "grad_norm": 20.243038177490234, | |
| "learning_rate": 0.00018873520750565718, | |
| "loss": 3.9649, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.026072220049537218, | |
| "eval_loss": 0.7839609384536743, | |
| "eval_runtime": 513.4664, | |
| "eval_samples_per_second": 12.581, | |
| "eval_steps_per_second": 3.145, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02867944205449094, | |
| "grad_norm": 13.500850677490234, | |
| "learning_rate": 0.0001861554081393806, | |
| "loss": 2.5316, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03128666405944466, | |
| "grad_norm": 8.94965934753418, | |
| "learning_rate": 0.0001833313919082515, | |
| "loss": 2.7797, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03389388606439838, | |
| "grad_norm": 15.162632942199707, | |
| "learning_rate": 0.00018027116379309638, | |
| "loss": 3.0097, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.036501108069352105, | |
| "grad_norm": 15.734134674072266, | |
| "learning_rate": 0.00017698339834299061, | |
| "loss": 2.8637, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03910833007430583, | |
| "grad_norm": 24.522480010986328, | |
| "learning_rate": 0.00017347741508630672, | |
| "loss": 3.661, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03910833007430583, | |
| "eval_loss": 0.770531177520752, | |
| "eval_runtime": 513.902, | |
| "eval_samples_per_second": 12.57, | |
| "eval_steps_per_second": 3.143, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.041715552079259546, | |
| "grad_norm": 10.44023609161377, | |
| "learning_rate": 0.0001697631521134985, | |
| "loss": 2.5952, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04432277408421327, | |
| "grad_norm": 13.444787979125977, | |
| "learning_rate": 0.00016585113790650388, | |
| "loss": 2.6771, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.046929996089166995, | |
| "grad_norm": 15.03112506866455, | |
| "learning_rate": 0.0001617524614946192, | |
| "loss": 3.0433, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04953721809412071, | |
| "grad_norm": 13.681419372558594, | |
| "learning_rate": 0.0001574787410214407, | |
| "loss": 3.3614, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.052144440099074436, | |
| "grad_norm": 25.215314865112305, | |
| "learning_rate": 0.00015304209081197425, | |
| "loss": 3.507, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.052144440099074436, | |
| "eval_loss": 0.7421609163284302, | |
| "eval_runtime": 513.024, | |
| "eval_samples_per_second": 12.592, | |
| "eval_steps_per_second": 3.148, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05475166210402816, | |
| "grad_norm": 9.96532917022705, | |
| "learning_rate": 0.00014845508703326504, | |
| "loss": 2.2643, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.05735888410898188, | |
| "grad_norm": 12.444780349731445, | |
| "learning_rate": 0.00014373073204588556, | |
| "loss": 2.6161, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.0599661061139356, | |
| "grad_norm": 13.275497436523438, | |
| "learning_rate": 0.00013888241754733208, | |
| "loss": 2.9035, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.06257332811888933, | |
| "grad_norm": 22.568071365356445, | |
| "learning_rate": 0.00013392388661180303, | |
| "loss": 3.1491, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.06518055012384305, | |
| "grad_norm": 18.894039154052734, | |
| "learning_rate": 0.0001288691947339621, | |
| "loss": 3.6063, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06518055012384305, | |
| "eval_loss": 0.7025501132011414, | |
| "eval_runtime": 512.1493, | |
| "eval_samples_per_second": 12.614, | |
| "eval_steps_per_second": 3.153, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06778777212879676, | |
| "grad_norm": 9.569221496582031, | |
| "learning_rate": 0.0001237326699871115, | |
| "loss": 2.3234, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.07039499413375049, | |
| "grad_norm": 12.406023979187012, | |
| "learning_rate": 0.00011852887240871145, | |
| "loss": 2.2466, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.07300221613870421, | |
| "grad_norm": 14.062081336975098, | |
| "learning_rate": 0.00011327255272837221, | |
| "loss": 2.8102, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.07560943814365793, | |
| "grad_norm": 12.484160423278809, | |
| "learning_rate": 0.00010797861055530831, | |
| "loss": 2.9179, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.07821666014861166, | |
| "grad_norm": 19.24785804748535, | |
| "learning_rate": 0.00010266205214377748, | |
| "loss": 3.4329, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07821666014861166, | |
| "eval_loss": 0.6793892979621887, | |
| "eval_runtime": 512.6051, | |
| "eval_samples_per_second": 12.602, | |
| "eval_steps_per_second": 3.151, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08082388215356538, | |
| "grad_norm": 7.278568744659424, | |
| "learning_rate": 9.733794785622253e-05, | |
| "loss": 2.2598, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.08343110415851909, | |
| "grad_norm": 11.45936393737793, | |
| "learning_rate": 9.202138944469168e-05, | |
| "loss": 2.221, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.08603832616347282, | |
| "grad_norm": 11.150221824645996, | |
| "learning_rate": 8.672744727162781e-05, | |
| "loss": 2.7018, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.08864554816842654, | |
| "grad_norm": 14.54114055633545, | |
| "learning_rate": 8.147112759128859e-05, | |
| "loss": 2.7212, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.09125277017338027, | |
| "grad_norm": 39.82421112060547, | |
| "learning_rate": 7.626733001288851e-05, | |
| "loss": 3.3754, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.09125277017338027, | |
| "eval_loss": 0.6544287800788879, | |
| "eval_runtime": 512.4276, | |
| "eval_samples_per_second": 12.607, | |
| "eval_steps_per_second": 3.152, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.09385999217833399, | |
| "grad_norm": 10.35319709777832, | |
| "learning_rate": 7.113080526603792e-05, | |
| "loss": 2.0052, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.0964672141832877, | |
| "grad_norm": 11.164114952087402, | |
| "learning_rate": 6.607611338819697e-05, | |
| "loss": 2.3054, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.09907443618824142, | |
| "grad_norm": 10.16714859008789, | |
| "learning_rate": 6.111758245266794e-05, | |
| "loss": 2.4965, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.10168165819319515, | |
| "grad_norm": 10.978752136230469, | |
| "learning_rate": 5.626926795411447e-05, | |
| "loss": 2.8824, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.10428888019814887, | |
| "grad_norm": 19.6451473236084, | |
| "learning_rate": 5.1544912966734994e-05, | |
| "loss": 3.0805, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.10428888019814887, | |
| "eval_loss": 0.6194283962249756, | |
| "eval_runtime": 512.9361, | |
| "eval_samples_per_second": 12.594, | |
| "eval_steps_per_second": 3.149, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1068961022031026, | |
| "grad_norm": 8.461108207702637, | |
| "learning_rate": 4.695790918802576e-05, | |
| "loss": 1.9141, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.10950332420805632, | |
| "grad_norm": 10.8994140625, | |
| "learning_rate": 4.252125897855932e-05, | |
| "loss": 2.2111, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.11211054621301003, | |
| "grad_norm": 9.634496688842773, | |
| "learning_rate": 3.824753850538082e-05, | |
| "loss": 2.1574, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.11471776821796376, | |
| "grad_norm": 12.223336219787598, | |
| "learning_rate": 3.414886209349615e-05, | |
| "loss": 2.7663, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.11732499022291748, | |
| "grad_norm": 20.796768188476562, | |
| "learning_rate": 3.0236847886501542e-05, | |
| "loss": 3.095, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.11732499022291748, | |
| "eval_loss": 0.598429799079895, | |
| "eval_runtime": 512.9195, | |
| "eval_samples_per_second": 12.595, | |
| "eval_steps_per_second": 3.149, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1199322122278712, | |
| "grad_norm": 7.045400619506836, | |
| "learning_rate": 2.6522584913693294e-05, | |
| "loss": 1.9138, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.12253943423282493, | |
| "grad_norm": 8.932710647583008, | |
| "learning_rate": 2.301660165700936e-05, | |
| "loss": 2.1108, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.12514665623777865, | |
| "grad_norm": 14.591238975524902, | |
| "learning_rate": 1.9728836206903656e-05, | |
| "loss": 2.394, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.12775387824273238, | |
| "grad_norm": 11.373315811157227, | |
| "learning_rate": 1.6668608091748495e-05, | |
| "loss": 2.4359, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.1303611002476861, | |
| "grad_norm": 18.106515884399414, | |
| "learning_rate": 1.3844591860619383e-05, | |
| "loss": 2.9492, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1303611002476861, | |
| "eval_loss": 0.5898227095603943, | |
| "eval_runtime": 514.4469, | |
| "eval_samples_per_second": 12.557, | |
| "eval_steps_per_second": 3.139, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13296832225263983, | |
| "grad_norm": 9.076396942138672, | |
| "learning_rate": 1.1264792494342857e-05, | |
| "loss": 2.0251, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.13557554425759352, | |
| "grad_norm": 11.412988662719727, | |
| "learning_rate": 8.936522714508678e-06, | |
| "loss": 2.2448, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.13818276626254725, | |
| "grad_norm": 10.8418550491333, | |
| "learning_rate": 6.866382254766157e-06, | |
| "loss": 2.3559, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.14078998826750097, | |
| "grad_norm": 9.6925687789917, | |
| "learning_rate": 5.060239153161872e-06, | |
| "loss": 2.4988, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.1433972102724547, | |
| "grad_norm": 18.714468002319336, | |
| "learning_rate": 3.5232131185484076e-06, | |
| "loss": 2.8972, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.1433972102724547, | |
| "eval_loss": 0.5796568989753723, | |
| "eval_runtime": 514.4013, | |
| "eval_samples_per_second": 12.558, | |
| "eval_steps_per_second": 3.14, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.14600443227740842, | |
| "grad_norm": 8.010424613952637, | |
| "learning_rate": 2.259661018213333e-06, | |
| "loss": 1.7564, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.14861165428236214, | |
| "grad_norm": 8.445106506347656, | |
| "learning_rate": 1.2731645278655445e-06, | |
| "loss": 2.0401, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.15121887628731587, | |
| "grad_norm": 10.118414878845215, | |
| "learning_rate": 5.665199789862907e-07, | |
| "loss": 2.3152, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1538260982922696, | |
| "grad_norm": 11.436360359191895, | |
| "learning_rate": 1.4173043232380557e-07, | |
| "loss": 2.4145, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.15643332029722332, | |
| "grad_norm": 14.37455940246582, | |
| "learning_rate": 0.0, | |
| "loss": 2.9678, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.15643332029722332, | |
| "eval_loss": 0.579126238822937, | |
| "eval_runtime": 512.7083, | |
| "eval_samples_per_second": 12.6, | |
| "eval_steps_per_second": 3.15, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.982119101916774e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |