| { | |
| "best_metric": 11.930744171142578, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.02871912693854107, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005743825387708214, | |
| "grad_norm": 0.01589948683977127, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9326, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005743825387708214, | |
| "eval_loss": 11.932580947875977, | |
| "eval_runtime": 0.1755, | |
| "eval_samples_per_second": 284.959, | |
| "eval_steps_per_second": 74.089, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011487650775416428, | |
| "grad_norm": 0.015951313078403473, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9323, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017231476163124641, | |
| "grad_norm": 0.01507105864584446, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9323, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022975301550832855, | |
| "grad_norm": 0.01573927141726017, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9326, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002871912693854107, | |
| "grad_norm": 0.016259584575891495, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9325, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0034462952326249283, | |
| "grad_norm": 0.015265903435647488, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9328, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00402067777139575, | |
| "grad_norm": 0.015187705866992474, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.933, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004595060310166571, | |
| "grad_norm": 0.017186807468533516, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9326, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005169442848937392, | |
| "grad_norm": 0.018329989165067673, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9317, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005743825387708214, | |
| "grad_norm": 0.017302963882684708, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9327, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006318207926479035, | |
| "grad_norm": 0.019111931324005127, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9328, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0068925904652498565, | |
| "grad_norm": 0.022191539406776428, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9318, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007466973004020678, | |
| "grad_norm": 0.019932497292757034, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9317, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0080413555427915, | |
| "grad_norm": 0.019474569708108902, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9321, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00861573808156232, | |
| "grad_norm": 0.01758241094648838, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9317, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009190120620333142, | |
| "grad_norm": 0.020062938332557678, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9322, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009764503159103963, | |
| "grad_norm": 0.02001391537487507, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9322, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010338885697874785, | |
| "grad_norm": 0.01966371200978756, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9319, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010913268236645606, | |
| "grad_norm": 0.019832884892821312, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9321, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011487650775416428, | |
| "grad_norm": 0.021595092490315437, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9324, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012062033314187249, | |
| "grad_norm": 0.023331984877586365, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9314, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01263641585295807, | |
| "grad_norm": 0.02657157927751541, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9324, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.013210798391728892, | |
| "grad_norm": 0.029394395649433136, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9318, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.013785180930499713, | |
| "grad_norm": 0.029913103207945824, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9326, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014359563469270534, | |
| "grad_norm": 0.033395763486623764, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9318, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014359563469270534, | |
| "eval_loss": 11.931483268737793, | |
| "eval_runtime": 0.1705, | |
| "eval_samples_per_second": 293.322, | |
| "eval_steps_per_second": 76.264, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014933946008041356, | |
| "grad_norm": 0.026962852105498314, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9314, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.015508328546812177, | |
| "grad_norm": 0.02874499186873436, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.9315, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.016082711085583, | |
| "grad_norm": 0.028867153450846672, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9317, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01665709362435382, | |
| "grad_norm": 0.028029875829815865, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.9323, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01723147616312464, | |
| "grad_norm": 0.03006923571228981, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9313, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017805858701895463, | |
| "grad_norm": 0.031214896589517593, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9311, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.018380241240666284, | |
| "grad_norm": 0.03501607105135918, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9312, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.018954623779437105, | |
| "grad_norm": 0.03202120214700699, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9315, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.019529006318207927, | |
| "grad_norm": 0.03382125496864319, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.9313, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.020103388856978748, | |
| "grad_norm": 0.03120032697916031, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.9313, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02067777139574957, | |
| "grad_norm": 0.03863793984055519, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9302, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02125215393452039, | |
| "grad_norm": 0.04094834253191948, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.9311, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.021826536473291212, | |
| "grad_norm": 0.03583959490060806, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.9315, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.022400919012062034, | |
| "grad_norm": 0.031415995210409164, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.931, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.022975301550832855, | |
| "grad_norm": 0.03263179212808609, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.931, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023549684089603676, | |
| "grad_norm": 0.034333061426877975, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9312, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.024124066628374498, | |
| "grad_norm": 0.036884188652038574, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9314, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02469844916714532, | |
| "grad_norm": 0.0348326712846756, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.9313, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02527283170591614, | |
| "grad_norm": 0.04102734848856926, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.9316, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.025847214244686962, | |
| "grad_norm": 0.03495470806956291, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.931, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026421596783457783, | |
| "grad_norm": 0.03532187640666962, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.9313, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.026995979322228605, | |
| "grad_norm": 0.04098067060112953, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.9304, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.027570361860999426, | |
| "grad_norm": 0.038192637264728546, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9313, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.028144744399770247, | |
| "grad_norm": 0.045579973608255386, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.9315, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02871912693854107, | |
| "grad_norm": 0.04336276277899742, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9313, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02871912693854107, | |
| "eval_loss": 11.930744171142578, | |
| "eval_runtime": 0.1654, | |
| "eval_samples_per_second": 302.244, | |
| "eval_steps_per_second": 78.583, | |
| "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": 1043797377024.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |