| { | |
| "best_metric": 0.015249949879944324, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.2222222222222223, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.044444444444444446, | |
| "grad_norm": 16.34016227722168, | |
| "learning_rate": 5e-05, | |
| "loss": 9.8289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.044444444444444446, | |
| "eval_loss": 13.514202117919922, | |
| "eval_runtime": 8.5195, | |
| "eval_samples_per_second": 5.869, | |
| "eval_steps_per_second": 1.526, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 21.221113204956055, | |
| "learning_rate": 0.0001, | |
| "loss": 12.676, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 27.357635498046875, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 14.1544, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 37.322933197021484, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 12.4999, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 17.118999481201172, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 7.8101, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 52.966583251953125, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.7518, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3111111111111111, | |
| "grad_norm": 71.5065689086914, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 7.0985, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 45.55967712402344, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.9202, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 83.13799285888672, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 5.9406, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 59.92570495605469, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 5.2075, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4888888888888889, | |
| "grad_norm": 24.67129898071289, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.131, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 39.77735900878906, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.1664, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5777777777777777, | |
| "grad_norm": 18.40007972717285, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.6304, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 16.40590476989746, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.3554, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 18.445859909057617, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.8851, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 11.208172798156738, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.0625, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7555555555555555, | |
| "grad_norm": 11.166001319885254, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.6406, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 11.158333778381348, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.561, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8444444444444444, | |
| "grad_norm": 9.224180221557617, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.1925, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 23.98605728149414, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.8318, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9333333333333333, | |
| "grad_norm": 11.465433120727539, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.3753, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 4.563766002655029, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.4548, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0222222222222221, | |
| "grad_norm": 13.37357234954834, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.986, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 5.592074871063232, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.3582, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 4.71364164352417, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.3453, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "eval_loss": 0.447214812040329, | |
| "eval_runtime": 8.5804, | |
| "eval_samples_per_second": 5.827, | |
| "eval_steps_per_second": 1.515, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1555555555555554, | |
| "grad_norm": 12.346272468566895, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6652, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 12.182293891906738, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.5499, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": 2.7045016288757324, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0956, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2888888888888888, | |
| "grad_norm": 6.3735480308532715, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.2023, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 7.7382893562316895, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.1611, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3777777777777778, | |
| "grad_norm": 3.8647775650024414, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0872, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 4.321582317352295, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0772, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4666666666666668, | |
| "grad_norm": 3.3833365440368652, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0712, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.511111111111111, | |
| "grad_norm": 1.7499160766601562, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0332, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": 5.335814952850342, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0531, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.5655996799468994, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0357, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6444444444444444, | |
| "grad_norm": 3.485537052154541, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0309, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.6888888888888889, | |
| "grad_norm": 2.6600377559661865, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0241, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7333333333333334, | |
| "grad_norm": 0.8413442373275757, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.004, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 2.198671340942383, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0167, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8222222222222222, | |
| "grad_norm": 2.00276255607605, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0299, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 0.9371952414512634, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0056, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.911111111111111, | |
| "grad_norm": 0.3950294852256775, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0031, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": 0.4528917372226715, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.003, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.7309563159942627, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0279, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0444444444444443, | |
| "grad_norm": 0.38156214356422424, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0029, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.088888888888889, | |
| "grad_norm": 0.22612902522087097, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0016, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.22579126060009003, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0017, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.1777777777777776, | |
| "grad_norm": 0.3204649090766907, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0015, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.06680531799793243, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0006, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "eval_loss": 0.015249949879944324, | |
| "eval_runtime": 8.5494, | |
| "eval_samples_per_second": 5.848, | |
| "eval_steps_per_second": 1.521, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1.1457518287265464e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |