| { | |
| "best_metric": 0.6850450038909912, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.061595318755774564, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012319063751154912, | |
| "grad_norm": 1.5515329837799072, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8128, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012319063751154912, | |
| "eval_loss": 2.4635820388793945, | |
| "eval_runtime": 3.8415, | |
| "eval_samples_per_second": 13.016, | |
| "eval_steps_per_second": 3.384, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024638127502309825, | |
| "grad_norm": 1.8287774324417114, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1289, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0036957191253464737, | |
| "grad_norm": 1.983467936515808, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.1509, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004927625500461965, | |
| "grad_norm": 1.7819783687591553, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.834, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006159531875577456, | |
| "grad_norm": 1.5915882587432861, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.6107, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0073914382506929475, | |
| "grad_norm": 2.1919822692871094, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.5127, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008623344625808438, | |
| "grad_norm": 1.8671609163284302, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.4235, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00985525100092393, | |
| "grad_norm": 2.084320306777954, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.3095, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01108715737603942, | |
| "grad_norm": 1.7241137027740479, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.1285, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012319063751154912, | |
| "grad_norm": 1.785744547843933, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.0819, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013550970126270403, | |
| "grad_norm": 1.4599878787994385, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.0287, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014782876501385895, | |
| "grad_norm": 1.6522572040557861, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.0985, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016014782876501387, | |
| "grad_norm": 1.7559229135513306, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.0441, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017246689251616876, | |
| "grad_norm": 1.3839433193206787, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.8959, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.018478595626732368, | |
| "grad_norm": 1.0673543214797974, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.8556, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01971050200184786, | |
| "grad_norm": 0.9284916520118713, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.8754, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020942408376963352, | |
| "grad_norm": 0.8481524586677551, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.8121, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02217431475207884, | |
| "grad_norm": 0.9322280287742615, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.8514, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.023406221127194333, | |
| "grad_norm": 0.9435703158378601, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.8297, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.024638127502309825, | |
| "grad_norm": 0.8691505193710327, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.8126, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025870033877425317, | |
| "grad_norm": 0.9489830136299133, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.8262, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.027101940252540806, | |
| "grad_norm": 0.9045710563659668, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.8205, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.028333846627656298, | |
| "grad_norm": 0.9778980612754822, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.831, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02956575300277179, | |
| "grad_norm": 1.0618224143981934, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.8711, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.030797659377887282, | |
| "grad_norm": 1.1619422435760498, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.9345, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.030797659377887282, | |
| "eval_loss": 0.7934057116508484, | |
| "eval_runtime": 3.5199, | |
| "eval_samples_per_second": 14.205, | |
| "eval_steps_per_second": 3.693, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.032029565753002774, | |
| "grad_norm": 1.4556480646133423, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.8112, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.033261472128118266, | |
| "grad_norm": 1.612951636314392, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.7809, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03449337850323375, | |
| "grad_norm": 1.323860764503479, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.7672, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.035725284878349244, | |
| "grad_norm": 1.0248310565948486, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.7685, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.036957191253464736, | |
| "grad_norm": 0.8862748742103577, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.7488, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03818909762858023, | |
| "grad_norm": 0.9572337865829468, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.7286, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03942100400369572, | |
| "grad_norm": 0.8555094003677368, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.6902, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04065291037881121, | |
| "grad_norm": 0.8972882032394409, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.7359, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.041884816753926704, | |
| "grad_norm": 0.848060131072998, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.7489, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.043116723129042196, | |
| "grad_norm": 0.8404566645622253, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.7202, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04434862950415768, | |
| "grad_norm": 0.920179545879364, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.7751, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.045580535879273174, | |
| "grad_norm": 1.0430974960327148, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.8446, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.046812442254388666, | |
| "grad_norm": 0.8427203893661499, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.79, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04804434862950416, | |
| "grad_norm": 0.8341359496116638, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.6782, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04927625500461965, | |
| "grad_norm": 0.8260400295257568, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.6713, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05050816137973514, | |
| "grad_norm": 0.8403255939483643, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.6926, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.051740067754850634, | |
| "grad_norm": 0.7738561034202576, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.6656, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05297197412996612, | |
| "grad_norm": 0.770875096321106, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.7192, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05420388050508161, | |
| "grad_norm": 0.7651665806770325, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.7163, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.055435786880197103, | |
| "grad_norm": 0.7298194169998169, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.6863, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.056667693255312596, | |
| "grad_norm": 0.8660922050476074, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.7219, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05789959963042809, | |
| "grad_norm": 0.7966043949127197, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.6923, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05913150600554358, | |
| "grad_norm": 0.9422286152839661, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.7498, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06036341238065907, | |
| "grad_norm": 0.9889546036720276, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.7543, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.061595318755774564, | |
| "grad_norm": 1.1552159786224365, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8377, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.061595318755774564, | |
| "eval_loss": 0.6850450038909912, | |
| "eval_runtime": 3.5123, | |
| "eval_samples_per_second": 14.236, | |
| "eval_steps_per_second": 3.701, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |