| { | |
| "best_metric": 11.935344696044922, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.013632568205442803, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002726513641088561, | |
| "grad_norm": 0.06683540344238281, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9353, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002726513641088561, | |
| "eval_loss": 11.939288139343262, | |
| "eval_runtime": 105.067, | |
| "eval_samples_per_second": 235.174, | |
| "eval_steps_per_second": 29.4, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005453027282177122, | |
| "grad_norm": 0.05441287159919739, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9452, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008179540923265681, | |
| "grad_norm": 0.0542253702878952, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.948, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010906054564354243, | |
| "grad_norm": 0.05546192079782486, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9359, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013632568205442803, | |
| "grad_norm": 0.04851478710770607, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9374, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016359081846531363, | |
| "grad_norm": 0.08121281117200851, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.934, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019085595487619924, | |
| "grad_norm": 0.05987578630447388, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9413, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0021812109128708486, | |
| "grad_norm": 0.053494490683078766, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9387, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024538622769797046, | |
| "grad_norm": 0.056421395391225815, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9448, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027265136410885606, | |
| "grad_norm": 0.06969709694385529, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0029991650051974165, | |
| "grad_norm": 0.07090578228235245, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9343, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0032718163693062725, | |
| "grad_norm": 0.08282779157161713, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.937, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003544467733415129, | |
| "grad_norm": 0.06570498645305634, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9308, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003817119097523985, | |
| "grad_norm": 0.0746464878320694, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9384, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004089770461632841, | |
| "grad_norm": 0.06106943264603615, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.945, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004362421825741697, | |
| "grad_norm": 0.0641741156578064, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9439, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004635073189850553, | |
| "grad_norm": 0.0463690385222435, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9327, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004907724553959409, | |
| "grad_norm": 0.0639299675822258, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9392, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005180375918068265, | |
| "grad_norm": 0.061709675937891006, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9369, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005453027282177121, | |
| "grad_norm": 0.05760058015584946, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9361, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0057256786462859775, | |
| "grad_norm": 0.060040686279535294, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9424, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005998330010394833, | |
| "grad_norm": 0.08672542870044708, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9367, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0062709813745036895, | |
| "grad_norm": 0.08303763717412949, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9304, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006543632738612545, | |
| "grad_norm": 0.08946041762828827, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9338, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006816284102721401, | |
| "grad_norm": 0.08901721984148026, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9395, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006816284102721401, | |
| "eval_loss": 11.936413764953613, | |
| "eval_runtime": 105.4372, | |
| "eval_samples_per_second": 234.348, | |
| "eval_steps_per_second": 29.297, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007088935466830258, | |
| "grad_norm": 0.07601311802864075, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9352, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007361586830939113, | |
| "grad_norm": 0.05736768618226051, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.9408, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00763423819504797, | |
| "grad_norm": 0.0675104558467865, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9415, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007906889559156825, | |
| "grad_norm": 0.06402797251939774, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9409, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008179540923265682, | |
| "grad_norm": 0.06155916303396225, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9298, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008452192287374538, | |
| "grad_norm": 0.08942660689353943, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9303, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008724843651483394, | |
| "grad_norm": 0.08944093436002731, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9482, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00899749501559225, | |
| "grad_norm": 0.06475299596786499, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.9365, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009270146379701106, | |
| "grad_norm": 0.07812382280826569, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9407, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009542797743809962, | |
| "grad_norm": 0.08350091427564621, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.9416, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009815449107918818, | |
| "grad_norm": 0.0940701887011528, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.928, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010088100472027675, | |
| "grad_norm": 0.08712836354970932, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.9316, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01036075183613653, | |
| "grad_norm": 0.08466362208127975, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9293, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010633403200245386, | |
| "grad_norm": 0.06831790506839752, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.9335, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010906054564354242, | |
| "grad_norm": 0.06954491883516312, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.9384, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011178705928463099, | |
| "grad_norm": 0.10085248202085495, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.9408, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011451357292571955, | |
| "grad_norm": 0.05636737868189812, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9306, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01172400865668081, | |
| "grad_norm": 0.07049186527729034, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9382, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011996660020789666, | |
| "grad_norm": 0.0855134129524231, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9295, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012269311384898523, | |
| "grad_norm": 0.10347723960876465, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9361, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012541962749007379, | |
| "grad_norm": 0.06473658233880997, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.9392, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012814614113116235, | |
| "grad_norm": 0.09248223900794983, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.9402, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01308726547722509, | |
| "grad_norm": 0.08586801588535309, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.9338, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013359916841333946, | |
| "grad_norm": 0.1005331352353096, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.9279, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013632568205442803, | |
| "grad_norm": 0.08666856586933136, | |
| "learning_rate": 0.0, | |
| "loss": 11.9394, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013632568205442803, | |
| "eval_loss": 11.935344696044922, | |
| "eval_runtime": 105.0647, | |
| "eval_samples_per_second": 235.179, | |
| "eval_steps_per_second": 29.401, | |
| "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": 1042494259200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |