| { | |
| "best_metric": 10.367364883422852, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.05391562205148942, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021566248820595766, | |
| "grad_norm": 0.12822318077087402, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021566248820595766, | |
| "eval_loss": 10.3851900100708, | |
| "eval_runtime": 0.1756, | |
| "eval_samples_per_second": 284.676, | |
| "eval_steps_per_second": 74.016, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004313249764119153, | |
| "grad_norm": 0.1388779729604721, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3855, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00646987464617873, | |
| "grad_norm": 0.13332770764827728, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3869, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008626499528238307, | |
| "grad_norm": 0.13132846355438232, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.386, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010783124410297884, | |
| "grad_norm": 0.13597635924816132, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.3856, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01293974929235746, | |
| "grad_norm": 0.1429922878742218, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3849, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015096374174417037, | |
| "grad_norm": 0.1376379281282425, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3836, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017252999056476613, | |
| "grad_norm": 0.13478346168994904, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3841, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01940962393853619, | |
| "grad_norm": 0.13110879063606262, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3831, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021566248820595768, | |
| "grad_norm": 0.13225792348384857, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3854, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023722873702655346, | |
| "grad_norm": 0.13014426827430725, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3837, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02587949858471492, | |
| "grad_norm": 0.13929449021816254, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3833, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028036123466774497, | |
| "grad_norm": 0.1670524924993515, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3789, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.030192748348834075, | |
| "grad_norm": 0.17455251514911652, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.378, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03234937323089365, | |
| "grad_norm": 0.17001105844974518, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3787, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.034505998112953226, | |
| "grad_norm": 0.18150822818279266, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3771, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03666262299501281, | |
| "grad_norm": 0.18267610669136047, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3771, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03881924787707238, | |
| "grad_norm": 0.1844225376844406, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.377, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.040975872759131955, | |
| "grad_norm": 0.1907738298177719, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.375, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.043132497641191536, | |
| "grad_norm": 0.18495532870292664, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04528912252325111, | |
| "grad_norm": 0.1759462058544159, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3754, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04744574740531069, | |
| "grad_norm": 0.1848379373550415, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3758, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.049602372287370265, | |
| "grad_norm": 0.17522373795509338, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3752, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05175899716942984, | |
| "grad_norm": 0.18354080617427826, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3737, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05391562205148942, | |
| "grad_norm": 0.21231482923030853, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.37, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05391562205148942, | |
| "eval_loss": 10.367364883422852, | |
| "eval_runtime": 0.1759, | |
| "eval_samples_per_second": 284.298, | |
| "eval_steps_per_second": 73.917, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 21390712307712.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |