| { | |
| "best_metric": 2.404106616973877, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.33044196612969845, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01321767864518794, | |
| "grad_norm": 4.207188129425049, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7816, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01321767864518794, | |
| "eval_loss": 7.090467929840088, | |
| "eval_runtime": 3.1406, | |
| "eval_samples_per_second": 15.921, | |
| "eval_steps_per_second": 4.139, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02643535729037588, | |
| "grad_norm": 4.228733062744141, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4738, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03965303593556382, | |
| "grad_norm": 4.2311201095581055, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 4.8883, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05287071458075176, | |
| "grad_norm": 5.120898723602295, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 4.7821, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06608839322593969, | |
| "grad_norm": 5.7605719566345215, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 4.4246, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07930607187112763, | |
| "grad_norm": 6.000363826751709, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 4.102, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09252375051631558, | |
| "grad_norm": 6.671154975891113, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 3.7691, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10574142916150352, | |
| "grad_norm": 8.927428245544434, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 3.4262, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11895910780669144, | |
| "grad_norm": 8.280679702758789, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 3.3338, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13217678645187939, | |
| "grad_norm": 6.511117458343506, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 3.0752, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14539446509706733, | |
| "grad_norm": 6.048829555511475, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 3.2598, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15861214374225527, | |
| "grad_norm": 7.314631938934326, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 4.6909, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1718298223874432, | |
| "grad_norm": 8.732232093811035, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 3.5604, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18504750103263115, | |
| "grad_norm": 8.049431800842285, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 2.6318, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1982651796778191, | |
| "grad_norm": 5.186059951782227, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 2.2938, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21148285832300703, | |
| "grad_norm": 2.9732935428619385, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 2.1281, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22470053696819495, | |
| "grad_norm": 2.7801878452301025, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 2.0613, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2379182156133829, | |
| "grad_norm": 2.5206377506256104, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 2.0285, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25113589425857086, | |
| "grad_norm": 2.4882333278656006, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 2.0971, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.26435357290375877, | |
| "grad_norm": 2.3352086544036865, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 2.1727, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27757125154894674, | |
| "grad_norm": 3.2300069332122803, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 2.4985, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.29078893019413465, | |
| "grad_norm": 2.572160243988037, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 2.5835, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.30400660883932257, | |
| "grad_norm": 3.5942838191986084, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 2.7205, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.31722428748451054, | |
| "grad_norm": 5.395232200622559, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 3.5118, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.33044196612969845, | |
| "grad_norm": 14.82295036315918, | |
| "learning_rate": 1e-05, | |
| "loss": 4.8754, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33044196612969845, | |
| "eval_loss": 2.404106616973877, | |
| "eval_runtime": 3.2329, | |
| "eval_samples_per_second": 15.466, | |
| "eval_steps_per_second": 4.021, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": 2.984041808658432e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |