| { | |
| "best_metric": 1.7648556232452393, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03478412104874125, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000695682420974825, | |
| "grad_norm": 1.1342545747756958, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4554, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000695682420974825, | |
| "eval_loss": 2.2368407249450684, | |
| "eval_runtime": 116.6606, | |
| "eval_samples_per_second": 83.01, | |
| "eval_steps_per_second": 10.381, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00139136484194965, | |
| "grad_norm": 1.5682674646377563, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7494, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002087047262924475, | |
| "grad_norm": 1.4035800695419312, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.675, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0027827296838993, | |
| "grad_norm": 1.235330581665039, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7973, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0034784121048741247, | |
| "grad_norm": 1.32366144657135, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.801, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00417409452584895, | |
| "grad_norm": 1.2439812421798706, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.844, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004869776946823775, | |
| "grad_norm": 1.2312966585159302, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.842, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0055654593677986, | |
| "grad_norm": 1.2126609086990356, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.813, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006261141788773425, | |
| "grad_norm": 1.3095048666000366, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9568, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0069568242097482495, | |
| "grad_norm": 1.3273837566375732, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0323, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007652506630723075, | |
| "grad_norm": 1.5259008407592773, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.9703, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0083481890516979, | |
| "grad_norm": 2.0334529876708984, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.2705, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009043871472672724, | |
| "grad_norm": 2.46689772605896, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.7122, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00973955389364755, | |
| "grad_norm": 3.0119881629943848, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7618, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010435236314622376, | |
| "grad_norm": 2.653355360031128, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.7364, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0111309187355972, | |
| "grad_norm": 1.9882702827453613, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.6445, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011826601156572025, | |
| "grad_norm": 1.464145541191101, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.6928, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01252228357754685, | |
| "grad_norm": 1.0981156826019287, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6624, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013217965998521675, | |
| "grad_norm": 1.1159366369247437, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.7358, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013913648419496499, | |
| "grad_norm": 1.339706301689148, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.7587, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014609330840471325, | |
| "grad_norm": 1.782918930053711, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.7778, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01530501326144615, | |
| "grad_norm": 2.0185258388519287, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.9297, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.016000695682420976, | |
| "grad_norm": 2.3750715255737305, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.055, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0166963781033958, | |
| "grad_norm": 2.592625856399536, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.1534, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017392060524370624, | |
| "grad_norm": 3.7186667919158936, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.6153, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017392060524370624, | |
| "eval_loss": 1.806847095489502, | |
| "eval_runtime": 64.9513, | |
| "eval_samples_per_second": 149.096, | |
| "eval_steps_per_second": 18.645, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018087742945345448, | |
| "grad_norm": 0.7948551177978516, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3773, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.018783425366320276, | |
| "grad_norm": 0.9543845057487488, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5167, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0194791077872951, | |
| "grad_norm": 1.0091980695724487, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.5544, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.020174790208269924, | |
| "grad_norm": 0.9797640442848206, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.5987, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02087047262924475, | |
| "grad_norm": 0.9876408576965332, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6911, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021566155050219575, | |
| "grad_norm": 0.9446225762367249, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.6043, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0222618374711944, | |
| "grad_norm": 0.9013808369636536, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6271, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.022957519892169223, | |
| "grad_norm": 0.9713707566261292, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.7478, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02365320231314405, | |
| "grad_norm": 1.0794121026992798, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.8939, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.024348884734118875, | |
| "grad_norm": 1.1999931335449219, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.8444, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0250445671550937, | |
| "grad_norm": 1.5557571649551392, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.0035, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.025740249576068526, | |
| "grad_norm": 1.9696677923202515, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.156, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02643593199704335, | |
| "grad_norm": 0.7454894781112671, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.474, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.027131614418018174, | |
| "grad_norm": 0.6688861846923828, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5058, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.027827296838992998, | |
| "grad_norm": 0.6627126336097717, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5299, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028522979259967825, | |
| "grad_norm": 0.6978307366371155, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.6032, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02921866168094265, | |
| "grad_norm": 0.69942706823349, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.5194, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.029914344101917473, | |
| "grad_norm": 0.7876566052436829, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.611, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0306100265228923, | |
| "grad_norm": 0.8018432855606079, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7057, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.031305708943867125, | |
| "grad_norm": 0.9367215037345886, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.7791, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03200139136484195, | |
| "grad_norm": 1.0166224241256714, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.7631, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03269707378581677, | |
| "grad_norm": 1.1936722993850708, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.9144, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0333927562067916, | |
| "grad_norm": 1.4344217777252197, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.8318, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03408843862776643, | |
| "grad_norm": 1.8004794120788574, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.9568, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03478412104874125, | |
| "grad_norm": 2.483407497406006, | |
| "learning_rate": 0.0, | |
| "loss": 2.2513, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03478412104874125, | |
| "eval_loss": 1.7648556232452393, | |
| "eval_runtime": 64.9608, | |
| "eval_samples_per_second": 149.075, | |
| "eval_steps_per_second": 18.642, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 2.9539319471407104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |