| { | |
| "best_metric": 11.926763534545898, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.5151515151515151, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.030303030303030304, | |
| "grad_norm": 0.04918564483523369, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9298, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.030303030303030304, | |
| "eval_loss": 11.934499740600586, | |
| "eval_runtime": 0.1456, | |
| "eval_samples_per_second": 343.363, | |
| "eval_steps_per_second": 89.274, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 0.051335081458091736, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9292, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 0.05042542144656181, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9287, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 0.06154028698801994, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9304, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15151515151515152, | |
| "grad_norm": 0.05323319882154465, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.929, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.059848275035619736, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9277, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21212121212121213, | |
| "grad_norm": 0.060108814388513565, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9256, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 0.06351973116397858, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9266, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 0.05737443268299103, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9293, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 0.06326352804899216, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.07109250128269196, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9267, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.07182971388101578, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9254, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3939393939393939, | |
| "grad_norm": 0.07381259649991989, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9265, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.42424242424242425, | |
| "grad_norm": 0.06559983640909195, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9294, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.07534347474575043, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9261, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.09406156092882156, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9252, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5151515151515151, | |
| "grad_norm": 0.07827135920524597, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9287, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.0862497091293335, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9281, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5757575757575758, | |
| "grad_norm": 0.08495012670755386, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9286, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 0.10257178544998169, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9219, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 0.10436329245567322, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9215, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.10915786027908325, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9256, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.696969696969697, | |
| "grad_norm": 0.09748965501785278, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9244, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.09861434251070023, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9259, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": 0.11815156042575836, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9219, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "eval_loss": 11.929944038391113, | |
| "eval_runtime": 0.1502, | |
| "eval_samples_per_second": 332.811, | |
| "eval_steps_per_second": 86.531, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7878787878787878, | |
| "grad_norm": 0.1273133009672165, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9205, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 0.10962895303964615, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.9237, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": 0.12553489208221436, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9252, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8787878787878788, | |
| "grad_norm": 0.1279001533985138, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.9228, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.1351960301399231, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9208, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9393939393939394, | |
| "grad_norm": 0.12530995905399323, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9252, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.14163988828659058, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.922, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.13867436349391937, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9221, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0303030303030303, | |
| "grad_norm": 0.15008845925331116, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.9209, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0606060606060606, | |
| "grad_norm": 0.15957288444042206, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.9171, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 0.14019732177257538, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9241, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.121212121212121, | |
| "grad_norm": 0.14304937422275543, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.921, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1515151515151516, | |
| "grad_norm": 0.15103910863399506, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.9189, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 0.15454430878162384, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.9222, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2121212121212122, | |
| "grad_norm": 0.1565762460231781, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.919, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2424242424242424, | |
| "grad_norm": 0.16164128482341766, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9206, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 0.14624446630477905, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9241, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.303030303030303, | |
| "grad_norm": 0.16123437881469727, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.9206, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.15028682351112366, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.9227, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 0.16800500452518463, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.921, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.393939393939394, | |
| "grad_norm": 0.15440353751182556, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.923, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4242424242424243, | |
| "grad_norm": 0.18006780743598938, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.9169, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 0.1780731976032257, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9175, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.4848484848484849, | |
| "grad_norm": 0.16222211718559265, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.9235, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5151515151515151, | |
| "grad_norm": 0.16308805346488953, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9198, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5151515151515151, | |
| "eval_loss": 11.926763534545898, | |
| "eval_runtime": 0.1448, | |
| "eval_samples_per_second": 345.406, | |
| "eval_steps_per_second": 89.806, | |
| "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": 1047055171584.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |