| { | |
| "best_metric": 0.08785244822502136, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.9768009768009768, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03907203907203907, | |
| "grad_norm": 4.342593193054199, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03907203907203907, | |
| "eval_loss": 3.825854778289795, | |
| "eval_runtime": 3.0175, | |
| "eval_samples_per_second": 16.57, | |
| "eval_steps_per_second": 4.308, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07814407814407814, | |
| "grad_norm": 4.329413414001465, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8601, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11721611721611722, | |
| "grad_norm": 4.38667106628418, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.769, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1562881562881563, | |
| "grad_norm": 3.8900246620178223, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.1385, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19536019536019536, | |
| "grad_norm": 3.678853750228882, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.9752, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23443223443223443, | |
| "grad_norm": 4.750513553619385, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2588, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 3.6628079414367676, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.9933, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3125763125763126, | |
| "grad_norm": 4.424605369567871, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.4886, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3516483516483517, | |
| "grad_norm": 1.0797154903411865, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.1462, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3907203907203907, | |
| "grad_norm": 1.7442551851272583, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.217, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4297924297924298, | |
| "grad_norm": 1.6925084590911865, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.1901, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.46886446886446886, | |
| "grad_norm": 3.2824654579162598, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.2443, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5079365079365079, | |
| "grad_norm": 2.0940823554992676, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.127, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.7476776838302612, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.1301, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5860805860805861, | |
| "grad_norm": 0.8936842679977417, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1412, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6251526251526252, | |
| "grad_norm": 1.3796156644821167, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1416, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6642246642246642, | |
| "grad_norm": 0.7006492614746094, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.1111, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7032967032967034, | |
| "grad_norm": 0.7903730869293213, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0685, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7423687423687424, | |
| "grad_norm": 0.6418982148170471, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.1016, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7814407814407814, | |
| "grad_norm": 0.6355842351913452, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0779, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.4654819071292877, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0757, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8595848595848596, | |
| "grad_norm": 0.5091500878334045, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0628, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8986568986568987, | |
| "grad_norm": 0.33425307273864746, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0648, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9377289377289377, | |
| "grad_norm": 0.5528669357299805, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1092, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9768009768009768, | |
| "grad_norm": 0.08286019414663315, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0024, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9768009768009768, | |
| "eval_loss": 0.08785244822502136, | |
| "eval_runtime": 2.9575, | |
| "eval_samples_per_second": 16.906, | |
| "eval_steps_per_second": 4.396, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2.66009604784128e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |