| { | |
| "best_metric": 0.37203922867774963, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1235955056179776, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02247191011235955, | |
| "grad_norm": 34.62396240234375, | |
| "learning_rate": 5e-05, | |
| "loss": 11.179, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02247191011235955, | |
| "eval_loss": 12.88409423828125, | |
| "eval_runtime": 0.8329, | |
| "eval_samples_per_second": 60.033, | |
| "eval_steps_per_second": 15.609, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0449438202247191, | |
| "grad_norm": 35.18650436401367, | |
| "learning_rate": 0.0001, | |
| "loss": 11.1435, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06741573033707865, | |
| "grad_norm": 29.5134334564209, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 9.7103, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "grad_norm": 18.440298080444336, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.3484, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11235955056179775, | |
| "grad_norm": 15.49881362915039, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.0166, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1348314606741573, | |
| "grad_norm": 14.950522422790527, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.4349, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15730337078651685, | |
| "grad_norm": 10.69368839263916, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.7895, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "grad_norm": 11.975858688354492, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.804, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20224719101123595, | |
| "grad_norm": 22.834827423095703, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.762, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2247191011235955, | |
| "grad_norm": 8.895463943481445, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.2891, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24719101123595505, | |
| "grad_norm": 12.911870002746582, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.2874, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2696629213483146, | |
| "grad_norm": 21.241043090820312, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.0808, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.29213483146067415, | |
| "grad_norm": 14.634261131286621, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.0181, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3146067415730337, | |
| "grad_norm": 11.363051414489746, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.7877, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.33707865168539325, | |
| "grad_norm": 5.684723377227783, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.6298, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3595505617977528, | |
| "grad_norm": 11.971399307250977, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.7522, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.38202247191011235, | |
| "grad_norm": 6.652386665344238, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.6313, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4044943820224719, | |
| "grad_norm": 7.810791969299316, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.6626, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.42696629213483145, | |
| "grad_norm": 9.458895683288574, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.7961, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.449438202247191, | |
| "grad_norm": 5.859529495239258, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.6503, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.47191011235955055, | |
| "grad_norm": 2.585972547531128, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.5193, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4943820224719101, | |
| "grad_norm": 8.680390357971191, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6679, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5168539325842697, | |
| "grad_norm": 5.057220458984375, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.542, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5393258426966292, | |
| "grad_norm": 4.271576881408691, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4761, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5617977528089888, | |
| "grad_norm": 2.5204758644104004, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.468, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5617977528089888, | |
| "eval_loss": 0.552042543888092, | |
| "eval_runtime": 0.859, | |
| "eval_samples_per_second": 58.207, | |
| "eval_steps_per_second": 15.134, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5842696629213483, | |
| "grad_norm": 2.733752727508545, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.4433, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6067415730337079, | |
| "grad_norm": 4.73248291015625, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.5019, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6292134831460674, | |
| "grad_norm": 3.2187206745147705, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.4837, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.651685393258427, | |
| "grad_norm": 2.7652924060821533, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4799, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6741573033707865, | |
| "grad_norm": 5.405097961425781, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.4394, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6966292134831461, | |
| "grad_norm": 3.7862300872802734, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4753, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7191011235955056, | |
| "grad_norm": 3.122354030609131, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.4543, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7415730337078652, | |
| "grad_norm": 5.204441547393799, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.4658, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7640449438202247, | |
| "grad_norm": 3.460355043411255, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.4973, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7865168539325843, | |
| "grad_norm": 5.4133172035217285, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.4528, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8089887640449438, | |
| "grad_norm": 4.1577839851379395, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.4119, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8314606741573034, | |
| "grad_norm": 1.967371940612793, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.407, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8539325842696629, | |
| "grad_norm": 2.243610382080078, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.395, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8764044943820225, | |
| "grad_norm": 4.601099967956543, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4377, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.898876404494382, | |
| "grad_norm": 5.425273418426514, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.484, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9213483146067416, | |
| "grad_norm": 4.3527936935424805, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.4335, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9438202247191011, | |
| "grad_norm": 3.8460605144500732, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.434, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9662921348314607, | |
| "grad_norm": 3.1695282459259033, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.4288, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9887640449438202, | |
| "grad_norm": 5.085464000701904, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.4407, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0112359550561798, | |
| "grad_norm": 5.431034564971924, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.635, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0337078651685394, | |
| "grad_norm": 3.2243857383728027, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.3833, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0561797752808988, | |
| "grad_norm": 3.8108878135681152, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.348, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0786516853932584, | |
| "grad_norm": 3.8203694820404053, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.3689, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.101123595505618, | |
| "grad_norm": 2.19366455078125, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.3809, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1235955056179776, | |
| "grad_norm": 2.593107223510742, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3927, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1235955056179776, | |
| "eval_loss": 0.37203922867774963, | |
| "eval_runtime": 0.8469, | |
| "eval_samples_per_second": 59.04, | |
| "eval_steps_per_second": 15.35, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.589463780163584e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |