| { | |
| "best_metric": 11.929415702819824, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.014155283459551277, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005662113383820511, | |
| "grad_norm": 0.014313064515590668, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005662113383820511, | |
| "eval_loss": 11.930351257324219, | |
| "eval_runtime": 0.1793, | |
| "eval_samples_per_second": 278.83, | |
| "eval_steps_per_second": 72.496, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011324226767641021, | |
| "grad_norm": 0.013985024765133858, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9302, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016986340151461533, | |
| "grad_norm": 0.01707862690091133, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9294, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022648453535282042, | |
| "grad_norm": 0.016713785007596016, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9304, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028310566919102554, | |
| "grad_norm": 0.017722394317388535, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9312, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0033972680302923066, | |
| "grad_norm": 0.017210278660058975, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9308, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003963479368674357, | |
| "grad_norm": 0.019824953749775887, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.929, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0045296907070564085, | |
| "grad_norm": 0.01971767097711563, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9303, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00509590204543846, | |
| "grad_norm": 0.019251316785812378, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9315, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005662113383820511, | |
| "grad_norm": 0.01913530007004738, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006228324722202562, | |
| "grad_norm": 0.025022396817803383, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9297, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006794536060584613, | |
| "grad_norm": 0.02492283657193184, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9327, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007360747398966664, | |
| "grad_norm": 0.016085179522633553, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9288, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007926958737348715, | |
| "grad_norm": 0.012558051384985447, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.93, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008493170075730767, | |
| "grad_norm": 0.013234994374215603, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9295, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009059381414112817, | |
| "grad_norm": 0.01846655271947384, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.93, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009625592752494869, | |
| "grad_norm": 0.017039023339748383, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9297, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01019180409087692, | |
| "grad_norm": 0.01856965199112892, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9287, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010758015429258971, | |
| "grad_norm": 0.022288938984274864, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.93, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011324226767641022, | |
| "grad_norm": 0.017395729199051857, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9321, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011890438106023074, | |
| "grad_norm": 0.017993543297052383, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9297, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012456649444405124, | |
| "grad_norm": 0.022735625505447388, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9294, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.013022860782787176, | |
| "grad_norm": 0.023601284250617027, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9292, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.013589072121169226, | |
| "grad_norm": 0.02474777214229107, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9324, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014155283459551277, | |
| "grad_norm": 0.030384186655282974, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9304, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014155283459551277, | |
| "eval_loss": 11.929415702819824, | |
| "eval_runtime": 0.1799, | |
| "eval_samples_per_second": 277.931, | |
| "eval_steps_per_second": 72.262, | |
| "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": 521247129600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |