| { | |
| "best_metric": 1.9283413887023926, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.07955449482895784, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0031821797931583136, | |
| "grad_norm": 2.3604540824890137, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9129, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031821797931583136, | |
| "eval_loss": 4.457443714141846, | |
| "eval_runtime": 5.2375, | |
| "eval_samples_per_second": 9.546, | |
| "eval_steps_per_second": 2.482, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006364359586316627, | |
| "grad_norm": 2.89908766746521, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1085, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00954653937947494, | |
| "grad_norm": 2.604163646697998, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.374, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012728719172633254, | |
| "grad_norm": 1.7334256172180176, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.0802, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015910898965791568, | |
| "grad_norm": 1.8126518726348877, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.7966, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01909307875894988, | |
| "grad_norm": 2.014775037765503, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.7963, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022275258552108195, | |
| "grad_norm": 1.833253264427185, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.6223, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02545743834526651, | |
| "grad_norm": 1.45881986618042, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4993, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028639618138424822, | |
| "grad_norm": 1.478446125984192, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.2777, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.031821797931583136, | |
| "grad_norm": 1.5528243780136108, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.2477, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.035003977724741446, | |
| "grad_norm": 1.934772253036499, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.4066, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03818615751789976, | |
| "grad_norm": 2.332120895385742, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.3715, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04136833731105807, | |
| "grad_norm": 2.1776576042175293, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.1069, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04455051710421639, | |
| "grad_norm": 2.0863003730773926, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.9897, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0477326968973747, | |
| "grad_norm": 1.6731739044189453, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.9037, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05091487669053302, | |
| "grad_norm": 1.252953290939331, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.9587, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05409705648369133, | |
| "grad_norm": 1.3898706436157227, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.953, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.057279236276849645, | |
| "grad_norm": 1.6184477806091309, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.9186, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.060461416070007955, | |
| "grad_norm": 1.361803412437439, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.9848, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06364359586316627, | |
| "grad_norm": 1.2994287014007568, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.9378, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06682577565632458, | |
| "grad_norm": 1.3868275880813599, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.8243, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07000795544948289, | |
| "grad_norm": 1.3576418161392212, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.842, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07319013524264122, | |
| "grad_norm": 1.5749825239181519, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.8902, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07637231503579953, | |
| "grad_norm": 1.9519647359848022, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.9456, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07955449482895784, | |
| "grad_norm": 2.802651882171631, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.1709, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07955449482895784, | |
| "eval_loss": 1.9283413887023926, | |
| "eval_runtime": 5.22, | |
| "eval_samples_per_second": 9.579, | |
| "eval_steps_per_second": 2.49, | |
| "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": 3.315690861756416e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |