| { | |
| "best_metric": 0.0017724342178553343, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.12726694241170855, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002545338848234171, | |
| "grad_norm": 141.46109008789062, | |
| "learning_rate": 5e-05, | |
| "loss": 114.6845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002545338848234171, | |
| "eval_loss": 7.069381237030029, | |
| "eval_runtime": 63.9596, | |
| "eval_samples_per_second": 41.386, | |
| "eval_steps_per_second": 5.175, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005090677696468342, | |
| "grad_norm": 132.96115112304688, | |
| "learning_rate": 0.0001, | |
| "loss": 109.0972, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007636016544702514, | |
| "grad_norm": 133.06570434570312, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 108.3083, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010181355392936684, | |
| "grad_norm": 122.5729751586914, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 86.1523, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012726694241170856, | |
| "grad_norm": 128.8125457763672, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 59.2911, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015272033089405028, | |
| "grad_norm": 106.09700012207031, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 38.47, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017817371937639197, | |
| "grad_norm": 98.86592864990234, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 23.3594, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02036271078587337, | |
| "grad_norm": 54.551883697509766, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.7119, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02290804963410754, | |
| "grad_norm": 32.16505432128906, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 6.3253, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025453388482341712, | |
| "grad_norm": 24.694622039794922, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.0641, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027998727330575884, | |
| "grad_norm": 8.788134574890137, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.8959, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.030544066178810055, | |
| "grad_norm": 10.397048950195312, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6319, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03308940502704422, | |
| "grad_norm": 2.6033473014831543, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.1445, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.035634743875278395, | |
| "grad_norm": 0.5861253142356873, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0199, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.038180082723512566, | |
| "grad_norm": 0.08569266647100449, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0038, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04072542157174674, | |
| "grad_norm": 0.02687235362827778, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0014, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04327076041998091, | |
| "grad_norm": 0.013966704718768597, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0006, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04581609926821508, | |
| "grad_norm": 2.1637065410614014, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0201, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04836143811644925, | |
| "grad_norm": 0.009754261933267117, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0004, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.050906776964683424, | |
| "grad_norm": 0.007793113123625517, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.053452115812917596, | |
| "grad_norm": 0.008098183199763298, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0003, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05599745466115177, | |
| "grad_norm": 0.013156173750758171, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0004, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05854279350938594, | |
| "grad_norm": 0.014168317429721355, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0004, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06108813235762011, | |
| "grad_norm": 13.05016040802002, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.183, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06363347120585428, | |
| "grad_norm": 0.31949782371520996, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0028, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06363347120585428, | |
| "eval_loss": 0.0021165155339986086, | |
| "eval_runtime": 64.0153, | |
| "eval_samples_per_second": 41.349, | |
| "eval_steps_per_second": 5.171, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06617881005408845, | |
| "grad_norm": 0.02505287528038025, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0005, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06872414890232262, | |
| "grad_norm": 0.09753460437059402, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0009, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07126948775055679, | |
| "grad_norm": 0.07497745752334595, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0007, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07381482659879096, | |
| "grad_norm": 0.04772750288248062, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0005, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07636016544702513, | |
| "grad_norm": 0.02046908438205719, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0003, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0789055042952593, | |
| "grad_norm": 0.026618817821145058, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0004, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08145084314349348, | |
| "grad_norm": 0.018914973363280296, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0003, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08399618199172765, | |
| "grad_norm": 0.010556931607425213, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0003, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08654152083996182, | |
| "grad_norm": 0.012361941859126091, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0003, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08908685968819599, | |
| "grad_norm": 0.010758999735116959, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0003, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09163219853643016, | |
| "grad_norm": 0.012884964235126972, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0003, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09417753738466433, | |
| "grad_norm": 8.187239646911621, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0799, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0967228762328985, | |
| "grad_norm": 0.14753367006778717, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0006, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09926821508113268, | |
| "grad_norm": 0.006080153398215771, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0002, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10181355392936685, | |
| "grad_norm": 0.005331439431756735, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0002, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10435889277760102, | |
| "grad_norm": 0.005517337471246719, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0002, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10690423162583519, | |
| "grad_norm": 0.0055676475167274475, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0002, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10944957047406936, | |
| "grad_norm": 0.00436694361269474, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0002, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11199490932230353, | |
| "grad_norm": 0.00402417266741395, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0001, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1145402481705377, | |
| "grad_norm": 0.004294692073017359, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0001, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11708558701877188, | |
| "grad_norm": 0.0037219019141048193, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0001, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11963092586700605, | |
| "grad_norm": 0.004236804321408272, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0002, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12217626471524022, | |
| "grad_norm": 0.010510016232728958, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0003, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12472160356347439, | |
| "grad_norm": 0.014029012061655521, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0003, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12726694241170855, | |
| "grad_norm": 10.742281913757324, | |
| "learning_rate": 0.0, | |
| "loss": 1.1588, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12726694241170855, | |
| "eval_loss": 0.0017724342178553343, | |
| "eval_runtime": 64.0427, | |
| "eval_samples_per_second": 41.332, | |
| "eval_steps_per_second": 5.168, | |
| "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": 5.260799806149755e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |