| { | |
| "best_metric": 0.29548346996307373, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.5810276679841897, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03162055335968379, | |
| "grad_norm": 11.844106674194336, | |
| "learning_rate": 5e-05, | |
| "loss": 12.4387, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03162055335968379, | |
| "eval_loss": 13.357632637023926, | |
| "eval_runtime": 6.5658, | |
| "eval_samples_per_second": 32.441, | |
| "eval_steps_per_second": 4.112, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06324110671936758, | |
| "grad_norm": 11.92176342010498, | |
| "learning_rate": 0.0001, | |
| "loss": 12.507, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09486166007905138, | |
| "grad_norm": 12.75086784362793, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.1684, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12648221343873517, | |
| "grad_norm": 16.455303192138672, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 9.4942, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15810276679841898, | |
| "grad_norm": 18.619556427001953, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.0416, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18972332015810275, | |
| "grad_norm": 13.420661926269531, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.1246, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22134387351778656, | |
| "grad_norm": 12.566791534423828, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.7653, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25296442687747034, | |
| "grad_norm": 8.71569538116455, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9055, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2845849802371542, | |
| "grad_norm": 33.23107147216797, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6997, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.31620553359683795, | |
| "grad_norm": 16.292945861816406, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9683, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 5.986809730529785, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5793, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3794466403162055, | |
| "grad_norm": 9.57590103149414, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5424, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41106719367588934, | |
| "grad_norm": 4.424511909484863, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.4851, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4426877470355731, | |
| "grad_norm": 7.18330717086792, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.459, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4743083003952569, | |
| "grad_norm": 3.1667606830596924, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3343, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5059288537549407, | |
| "grad_norm": 6.0077948570251465, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5273, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5375494071146245, | |
| "grad_norm": 7.812488555908203, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6356, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5691699604743083, | |
| "grad_norm": 3.925651788711548, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5472, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6007905138339921, | |
| "grad_norm": 6.442537784576416, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5183, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6324110671936759, | |
| "grad_norm": 3.8656249046325684, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4004, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6640316205533597, | |
| "grad_norm": 3.0123801231384277, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4251, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 1.8808037042617798, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.355, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 1.733313798904419, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3059, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.758893280632411, | |
| "grad_norm": 2.559690475463867, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4047, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7905138339920948, | |
| "grad_norm": 3.5482497215270996, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4567, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7905138339920948, | |
| "eval_loss": 0.40562108159065247, | |
| "eval_runtime": 6.555, | |
| "eval_samples_per_second": 32.494, | |
| "eval_steps_per_second": 4.119, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8221343873517787, | |
| "grad_norm": 3.445368528366089, | |
| "learning_rate": 5e-05, | |
| "loss": 0.448, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8537549407114624, | |
| "grad_norm": 2.0446903705596924, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3686, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8853754940711462, | |
| "grad_norm": 2.180802822113037, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.3829, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9169960474308301, | |
| "grad_norm": 2.177382469177246, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3715, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9486166007905138, | |
| "grad_norm": 1.3226820230484009, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3066, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9802371541501976, | |
| "grad_norm": 2.0610783100128174, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2111, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0118577075098814, | |
| "grad_norm": 4.565697193145752, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5298, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0434782608695652, | |
| "grad_norm": 2.319690704345703, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4085, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.075098814229249, | |
| "grad_norm": 1.3422417640686035, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2987, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.1067193675889329, | |
| "grad_norm": 2.624420404434204, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2566, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1383399209486167, | |
| "grad_norm": 1.8034946918487549, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.281, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1699604743083003, | |
| "grad_norm": 4.372071266174316, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3521, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2015810276679841, | |
| "grad_norm": 3.8450584411621094, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2495, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.233201581027668, | |
| "grad_norm": 1.1193829774856567, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1677, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2648221343873518, | |
| "grad_norm": 2.4760582447052, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3147, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2964426877470356, | |
| "grad_norm": 1.6052770614624023, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.307, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3280632411067192, | |
| "grad_norm": 1.8670191764831543, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3078, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.359683794466403, | |
| "grad_norm": 2.709547281265259, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2934, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.391304347826087, | |
| "grad_norm": 3.421477794647217, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.252, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4229249011857708, | |
| "grad_norm": 3.747044324874878, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.3245, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 1.8317062854766846, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2493, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4861660079051384, | |
| "grad_norm": 1.9713412523269653, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.212, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5177865612648223, | |
| "grad_norm": 1.5141923427581787, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2669, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5494071146245059, | |
| "grad_norm": 1.7601076364517212, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.3634, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5810276679841897, | |
| "grad_norm": 2.3023111820220947, | |
| "learning_rate": 0.0, | |
| "loss": 0.3262, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5810276679841897, | |
| "eval_loss": 0.29548346996307373, | |
| "eval_runtime": 6.5505, | |
| "eval_samples_per_second": 32.517, | |
| "eval_steps_per_second": 4.122, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |