| { | |
| "best_metric": 1.5958507061004639, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.012806351950567481, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025612703901134963, | |
| "grad_norm": 0.2620626986026764, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00025612703901134963, | |
| "eval_loss": 2.0089938640594482, | |
| "eval_runtime": 1.3997, | |
| "eval_samples_per_second": 35.722, | |
| "eval_steps_per_second": 9.288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005122540780226993, | |
| "grad_norm": 0.2747054696083069, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3194, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007683811170340488, | |
| "grad_norm": 0.29436272382736206, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.4465, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010245081560453985, | |
| "grad_norm": 0.30683159828186035, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.4909, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012806351950567481, | |
| "grad_norm": 0.4495270848274231, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.5614, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015367622340680977, | |
| "grad_norm": 0.5310289859771729, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.653, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017928892730794475, | |
| "grad_norm": 0.552165150642395, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.7677, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002049016312090797, | |
| "grad_norm": 0.5591002106666565, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.6923, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002305143351102147, | |
| "grad_norm": 0.6837015151977539, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.7793, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025612703901134962, | |
| "grad_norm": 0.9529432654380798, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.9628, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002817397429124846, | |
| "grad_norm": 0.8184969425201416, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.9863, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0030735244681361954, | |
| "grad_norm": 1.0089133977890015, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.0217, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003329651507147545, | |
| "grad_norm": 0.3397619128227234, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.1172, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003585778546158895, | |
| "grad_norm": 0.272462397813797, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.1102, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0038419055851702444, | |
| "grad_norm": 0.2653588354587555, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.2447, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004098032624181594, | |
| "grad_norm": 0.25759148597717285, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.3539, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004354159663192944, | |
| "grad_norm": 0.23896794021129608, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.4263, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004610286702204294, | |
| "grad_norm": 0.27768826484680176, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.491, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004866413741215643, | |
| "grad_norm": 0.22282476723194122, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.5283, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0051225407802269925, | |
| "grad_norm": 0.2642979621887207, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.6005, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005378667819238342, | |
| "grad_norm": 0.3124540150165558, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.6286, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005634794858249692, | |
| "grad_norm": 0.5772589445114136, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.7441, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005890921897261042, | |
| "grad_norm": 0.31767380237579346, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.6356, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006147048936272391, | |
| "grad_norm": 0.46708905696868896, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.8565, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006403175975283741, | |
| "grad_norm": 0.982274055480957, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.261, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006403175975283741, | |
| "eval_loss": 1.617965817451477, | |
| "eval_runtime": 0.6617, | |
| "eval_samples_per_second": 75.557, | |
| "eval_steps_per_second": 19.645, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00665930301429509, | |
| "grad_norm": 0.40817996859550476, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.0082, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00691543005330644, | |
| "grad_norm": 0.4682709872722626, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.1889, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00717155709231779, | |
| "grad_norm": 0.5050235986709595, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.3271, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007427684131329139, | |
| "grad_norm": 0.3686935305595398, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.2991, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007683811170340489, | |
| "grad_norm": 0.2502523362636566, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.3933, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007939938209351838, | |
| "grad_norm": 0.2137083113193512, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.4678, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008196065248363188, | |
| "grad_norm": 0.21022151410579681, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.6702, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008452192287374538, | |
| "grad_norm": 0.24133265018463135, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.632, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008708319326385888, | |
| "grad_norm": 0.3395995795726776, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.5687, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008964446365397238, | |
| "grad_norm": 0.3980751633644104, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.7686, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009220573404408587, | |
| "grad_norm": 0.5121943950653076, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.7378, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009476700443419936, | |
| "grad_norm": 0.6918196082115173, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.8551, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009732827482431285, | |
| "grad_norm": 0.19062906503677368, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.067, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.009988954521442635, | |
| "grad_norm": 0.1364046037197113, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.0974, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010245081560453985, | |
| "grad_norm": 0.1472988724708557, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.1545, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010501208599465335, | |
| "grad_norm": 0.1773543506860733, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.2833, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010757335638476685, | |
| "grad_norm": 0.18720166385173798, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.4385, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011013462677488034, | |
| "grad_norm": 0.1837349832057953, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.4987, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011269589716499384, | |
| "grad_norm": 0.20710361003875732, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.5536, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011525716755510734, | |
| "grad_norm": 0.22093434631824493, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.5326, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011781843794522084, | |
| "grad_norm": 0.21961745619773865, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.5564, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012037970833533432, | |
| "grad_norm": 0.278564453125, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.6989, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012294097872544782, | |
| "grad_norm": 0.24441421031951904, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.6805, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012550224911556131, | |
| "grad_norm": 0.3852005898952484, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.7377, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.012806351950567481, | |
| "grad_norm": 0.9400036334991455, | |
| "learning_rate": 1e-05, | |
| "loss": 1.9483, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012806351950567481, | |
| "eval_loss": 1.5958507061004639, | |
| "eval_runtime": 0.662, | |
| "eval_samples_per_second": 75.531, | |
| "eval_steps_per_second": 19.638, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |