| { | |
| "best_metric": 0.1907738745212555, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1688119856509812, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0033762397130196243, | |
| "grad_norm": 21.04863166809082, | |
| "learning_rate": 5e-05, | |
| "loss": 13.2321, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033762397130196243, | |
| "eval_loss": 13.565424919128418, | |
| "eval_runtime": 54.9319, | |
| "eval_samples_per_second": 36.318, | |
| "eval_steps_per_second": 4.551, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006752479426039249, | |
| "grad_norm": 19.532649993896484, | |
| "learning_rate": 0.0001, | |
| "loss": 13.7413, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010128719139058873, | |
| "grad_norm": 21.91816520690918, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 13.3678, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013504958852078497, | |
| "grad_norm": 18.732440948486328, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 9.8617, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01688119856509812, | |
| "grad_norm": 20.958824157714844, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 8.1752, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020257438278117747, | |
| "grad_norm": 21.34650993347168, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.5195, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023633677991137372, | |
| "grad_norm": 14.311793327331543, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.0051, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027009917704156994, | |
| "grad_norm": 15.527531623840332, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.5978, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03038615741717662, | |
| "grad_norm": 11.401641845703125, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6281, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03376239713019624, | |
| "grad_norm": 7.532580375671387, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7721, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03713863684321587, | |
| "grad_norm": 3.6801764965057373, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.4646, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04051487655623549, | |
| "grad_norm": 3.9017598628997803, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.461, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04389111626925512, | |
| "grad_norm": 4.528001308441162, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6619, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.047267355982274745, | |
| "grad_norm": 4.240943431854248, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8591, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05064359569529436, | |
| "grad_norm": 3.5743143558502197, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6423, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05401983540831399, | |
| "grad_norm": 3.264251947402954, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.435, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.057396075121333615, | |
| "grad_norm": 2.502185344696045, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3563, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06077231483435324, | |
| "grad_norm": 6.309056758880615, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7801, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06414855454737287, | |
| "grad_norm": 2.805271625518799, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.582, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06752479426039248, | |
| "grad_norm": 16.07535171508789, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3338, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07090103397341212, | |
| "grad_norm": 4.402841091156006, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3699, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07427727368643174, | |
| "grad_norm": 2.3994719982147217, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.307, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07765351339945135, | |
| "grad_norm": 1.618458867073059, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2161, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08102975311247099, | |
| "grad_norm": 1.4847005605697632, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1934, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0844059928254906, | |
| "grad_norm": 1.1013414859771729, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0668, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0844059928254906, | |
| "eval_loss": 0.3402710258960724, | |
| "eval_runtime": 54.9188, | |
| "eval_samples_per_second": 36.326, | |
| "eval_steps_per_second": 4.552, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08778223253851024, | |
| "grad_norm": 3.0682921409606934, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4922, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09115847225152986, | |
| "grad_norm": 2.6181204319000244, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3891, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09453471196454949, | |
| "grad_norm": 2.052562713623047, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.264, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09791095167756911, | |
| "grad_norm": 1.5420339107513428, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1613, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10128719139058873, | |
| "grad_norm": 3.7188830375671387, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2916, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10466343110360836, | |
| "grad_norm": 3.411963939666748, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3516, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10803967081662798, | |
| "grad_norm": 11.465725898742676, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2923, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11141591052964761, | |
| "grad_norm": 5.158927917480469, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5667, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11479215024266723, | |
| "grad_norm": 0.8077765703201294, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0768, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11816838995568685, | |
| "grad_norm": 1.4526370763778687, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1387, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12154462966870648, | |
| "grad_norm": 3.2545902729034424, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3294, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1249208693817261, | |
| "grad_norm": 1.122367024421692, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1178, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12829710909474573, | |
| "grad_norm": 1.5557242631912231, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2367, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13167334880776535, | |
| "grad_norm": 1.4077110290527344, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2404, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13504958852078497, | |
| "grad_norm": 1.0390076637268066, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1126, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1384258282338046, | |
| "grad_norm": 0.6616483330726624, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0689, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.14180206794682423, | |
| "grad_norm": 0.7459376454353333, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0661, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14517830765984385, | |
| "grad_norm": 1.7347726821899414, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2198, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14855454737286347, | |
| "grad_norm": 1.3913830518722534, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.115, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1519307870858831, | |
| "grad_norm": 5.454977989196777, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7133, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1553070267989027, | |
| "grad_norm": 1.3282166719436646, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0953, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15868326651192236, | |
| "grad_norm": 0.687819242477417, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0587, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16205950622494197, | |
| "grad_norm": 0.6925812363624573, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1267, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1654357459379616, | |
| "grad_norm": 1.8676002025604248, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1939, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1688119856509812, | |
| "grad_norm": 0.3576854169368744, | |
| "learning_rate": 0.0, | |
| "loss": 0.0117, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1688119856509812, | |
| "eval_loss": 0.1907738745212555, | |
| "eval_runtime": 54.784, | |
| "eval_samples_per_second": 36.416, | |
| "eval_steps_per_second": 4.563, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |