| { | |
| "best_metric": 0.03200618177652359, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.40170725583730854, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008034145116746171, | |
| "grad_norm": 3.3025126457214355, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3269, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008034145116746171, | |
| "eval_loss": 0.24998800456523895, | |
| "eval_runtime": 9.4919, | |
| "eval_samples_per_second": 5.268, | |
| "eval_steps_per_second": 1.37, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016068290233492342, | |
| "grad_norm": 3.2036828994750977, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5196, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024102435350238514, | |
| "grad_norm": 7.4898576736450195, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.1654, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.032136580466984685, | |
| "grad_norm": 2.12864089012146, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.3874, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04017072558373085, | |
| "grad_norm": 1.7909096479415894, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.5476, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04820487070047703, | |
| "grad_norm": 1.976773738861084, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.1148, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.056239015817223195, | |
| "grad_norm": 1.6779401302337646, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.4871, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06427316093396937, | |
| "grad_norm": 3.5678701400756836, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.2382, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07230730605071554, | |
| "grad_norm": 12.771509170532227, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.9397, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0803414511674617, | |
| "grad_norm": 12.436668395996094, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 5.8173, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08837559628420788, | |
| "grad_norm": 12.006640434265137, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.2225, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09640974140095405, | |
| "grad_norm": 14.71074390411377, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.3767, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10444388651770023, | |
| "grad_norm": 6.394194602966309, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.5269, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11247803163444639, | |
| "grad_norm": 5.534221172332764, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.8947, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12051217675119257, | |
| "grad_norm": 3.737447500228882, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.185, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12854632186793874, | |
| "grad_norm": 1.8375308513641357, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.0557, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1365804669846849, | |
| "grad_norm": 1.5251080989837646, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.3718, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1446146121014311, | |
| "grad_norm": 3.733692169189453, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.1194, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15264875721817725, | |
| "grad_norm": 2.7320053577423096, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.4776, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1606829023349234, | |
| "grad_norm": 4.234574317932129, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.8167, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1687170474516696, | |
| "grad_norm": 10.611283302307129, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 5.9641, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17675119256841576, | |
| "grad_norm": 15.97502613067627, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.7862, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18478533768516195, | |
| "grad_norm": 14.298501968383789, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.9832, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1928194828019081, | |
| "grad_norm": 1.9273054599761963, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.2753, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20085362791865427, | |
| "grad_norm": 2.0565435886383057, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.2361, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20085362791865427, | |
| "eval_loss": 0.03677130490541458, | |
| "eval_runtime": 9.4706, | |
| "eval_samples_per_second": 5.28, | |
| "eval_steps_per_second": 1.373, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20888777303540046, | |
| "grad_norm": 1.0484713315963745, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.2505, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.21692191815214662, | |
| "grad_norm": 0.9066623449325562, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.9859, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.22495606326889278, | |
| "grad_norm": 1.164398431777954, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.5357, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23299020838563897, | |
| "grad_norm": 1.3508579730987549, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.3002, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24102435350238513, | |
| "grad_norm": 1.0967586040496826, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.3312, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24905849861913132, | |
| "grad_norm": 1.0712722539901733, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.8359, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2570926437358775, | |
| "grad_norm": 1.9306401014328003, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.1769, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.26512678885262364, | |
| "grad_norm": 6.797326564788818, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.3287, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2731609339693698, | |
| "grad_norm": 8.896469116210938, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 9.3152, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.281195079086116, | |
| "grad_norm": 16.196805953979492, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.3369, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2892292242028622, | |
| "grad_norm": 1.467756748199463, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.103, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.29726336931960834, | |
| "grad_norm": 0.8828189969062805, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0758, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3052975144363545, | |
| "grad_norm": 3.7422118186950684, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.0237, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.31333165955310066, | |
| "grad_norm": 0.6260557770729065, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.9247, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3213658046698468, | |
| "grad_norm": 0.7009216547012329, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.6326, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32939994978659304, | |
| "grad_norm": 0.8966463804244995, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.6609, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3374340949033392, | |
| "grad_norm": 0.7447260618209839, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.3863, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.34546824002008536, | |
| "grad_norm": 1.1738234758377075, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.4486, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3535023851368315, | |
| "grad_norm": 1.7264965772628784, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.7159, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3615365302535777, | |
| "grad_norm": 2.1729681491851807, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.7855, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3695706753703239, | |
| "grad_norm": 8.315459251403809, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 7.1132, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.37760482048707006, | |
| "grad_norm": 7.717396259307861, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.3517, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3856389656038162, | |
| "grad_norm": 0.874803364276886, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0699, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3936731107205624, | |
| "grad_norm": 0.9983109831809998, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0663, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.40170725583730854, | |
| "grad_norm": 0.7316238880157471, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0602, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.40170725583730854, | |
| "eval_loss": 0.03200618177652359, | |
| "eval_runtime": 9.516, | |
| "eval_samples_per_second": 5.254, | |
| "eval_steps_per_second": 1.366, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.083077645738967e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |