| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.009472219755498328, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00018944439510996654, | |
| "grad_norm": 3.264355182647705, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1199, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00018944439510996654, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.4634, | |
| "eval_samples_per_second": 9.152, | |
| "eval_steps_per_second": 9.152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003788887902199331, | |
| "grad_norm": 4.2460713386535645, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2707, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005683331853298996, | |
| "grad_norm": 3.954056978225708, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.0906, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007577775804398662, | |
| "grad_norm": 3.6541836261749268, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.0425, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009472219755498328, | |
| "grad_norm": 3.752495050430298, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.6957, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011366663706597992, | |
| "grad_norm": 6.510428428649902, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.4514, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013261107657697659, | |
| "grad_norm": 4.765082836151123, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.4753, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0015155551608797323, | |
| "grad_norm": 5.17319917678833, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.3487, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001704999555989699, | |
| "grad_norm": 6.483305931091309, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.8691, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018944439510996656, | |
| "grad_norm": 5.846699237823486, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.6593, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002083888346209632, | |
| "grad_norm": 5.230606555938721, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.7168, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0022733327413195985, | |
| "grad_norm": 6.455722332000732, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.1, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0024627771364295653, | |
| "grad_norm": 3.4264791011810303, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.5991, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0026522215315395318, | |
| "grad_norm": 5.551114082336426, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.3684, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002841665926649498, | |
| "grad_norm": 8.614983558654785, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.4897, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0030311103217594646, | |
| "grad_norm": 5.568994045257568, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.6835, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0032205547168694315, | |
| "grad_norm": 6.834268093109131, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.7415, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003409999111979398, | |
| "grad_norm": 6.758293628692627, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.3813, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0035994435070893643, | |
| "grad_norm": 7.973887920379639, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.2036, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003788887902199331, | |
| "grad_norm": 5.2876996994018555, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.0686, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003978332297309297, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004167776692419264, | |
| "grad_norm": 8.569087982177734, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.0977, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004357221087529231, | |
| "grad_norm": 5.491764068603516, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.2723, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004546665482639197, | |
| "grad_norm": 12.329565048217773, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.3138, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004736109877749164, | |
| "grad_norm": 13.543659210205078, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.946, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004736109877749164, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.4757, | |
| "eval_samples_per_second": 9.131, | |
| "eval_steps_per_second": 9.131, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004925554272859131, | |
| "grad_norm": 8.170857429504395, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.8941, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005114998667969097, | |
| "grad_norm": 7.001986503601074, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.068, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0053044430630790635, | |
| "grad_norm": 6.956447601318359, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.83, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00549388745818903, | |
| "grad_norm": 16.064136505126953, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.3823, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005683331853298996, | |
| "grad_norm": 7.477011680603027, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.2673, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005872776248408963, | |
| "grad_norm": 9.061140060424805, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.8978, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006062220643518929, | |
| "grad_norm": 11.521283149719238, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.6095, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006251665038628896, | |
| "grad_norm": 18.75054168701172, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.9312, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006441109433738863, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006630553828848829, | |
| "grad_norm": 12.122861862182617, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.6679, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006819998223958796, | |
| "grad_norm": 13.706648826599121, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.0586, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007009442619068763, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007198887014178729, | |
| "grad_norm": 16.214313507080078, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.4707, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0073883314092886955, | |
| "grad_norm": 9.249471664428711, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.3148, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007577775804398662, | |
| "grad_norm": 6.823072910308838, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.3958, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007767220199508628, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007956664594618594, | |
| "grad_norm": 8.052329063415527, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.8573, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008146108989728562, | |
| "grad_norm": 14.712080955505371, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.1297, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008335553384838528, | |
| "grad_norm": 10.332724571228027, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.4763, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.008524997779948494, | |
| "grad_norm": 16.205141067504883, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.3307, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008714442175058462, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.008903886570168428, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.009093330965278394, | |
| "grad_norm": 11.246818542480469, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.285, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.009282775360388362, | |
| "grad_norm": 57.88637924194336, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 7.4546, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.009472219755498328, | |
| "grad_norm": 13.0756254196167, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6765, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009472219755498328, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.7587, | |
| "eval_samples_per_second": 8.683, | |
| "eval_steps_per_second": 8.683, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7382522816102400.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |