| { | |
| "best_metric": 0.12096888571977615, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01936061566757823, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003872123133515646, | |
| "grad_norm": 18.427871704101562, | |
| "learning_rate": 5e-05, | |
| "loss": 3.8428, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003872123133515646, | |
| "eval_loss": 3.816296339035034, | |
| "eval_runtime": 1.2522, | |
| "eval_samples_per_second": 39.928, | |
| "eval_steps_per_second": 10.381, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007744246267031292, | |
| "grad_norm": 22.974451065063477, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4935, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011616369400546938, | |
| "grad_norm": 19.45110321044922, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.6111, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015488492534062584, | |
| "grad_norm": 23.882034301757812, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.4094, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001936061566757823, | |
| "grad_norm": 20.992429733276367, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.6488, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0023232738801093875, | |
| "grad_norm": 10.908239364624023, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.2417, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002710486193460952, | |
| "grad_norm": 2.6740472316741943, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.059, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0030976985068125167, | |
| "grad_norm": 0.971660315990448, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0142, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003484910820164081, | |
| "grad_norm": 0.23529735207557678, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0017, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003872123133515646, | |
| "grad_norm": 0.04244418814778328, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0004, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00425933544686721, | |
| "grad_norm": 27.48731803894043, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.8628, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004646547760218775, | |
| "grad_norm": 68.8835220336914, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 5.1609, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00503376007357034, | |
| "grad_norm": 36.057044982910156, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.8459, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005420972386921904, | |
| "grad_norm": 0.17858703434467316, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0013, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005808184700273469, | |
| "grad_norm": 0.2483503371477127, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0017, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0061953970136250334, | |
| "grad_norm": 0.07233485579490662, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0006, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006582609326976598, | |
| "grad_norm": 0.031193960458040237, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0003, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006969821640328162, | |
| "grad_norm": 0.02067120373249054, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0002, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007357033953679727, | |
| "grad_norm": 0.01805349811911583, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0002, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007744246267031292, | |
| "grad_norm": 0.020172208547592163, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0001, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008131458580382856, | |
| "grad_norm": 0.019413195550441742, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00851867089373442, | |
| "grad_norm": 0.012640492059290409, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008905883207085985, | |
| "grad_norm": 3.7326242923736572, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1703, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00929309552043755, | |
| "grad_norm": 22.277650833129883, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.8563, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009680307833789115, | |
| "grad_norm": 19.738676071166992, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.2722, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009680307833789115, | |
| "eval_loss": 0.22734582424163818, | |
| "eval_runtime": 0.749, | |
| "eval_samples_per_second": 66.752, | |
| "eval_steps_per_second": 17.356, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01006752014714068, | |
| "grad_norm": 20.296913146972656, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.5689, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.010454732460492243, | |
| "grad_norm": 16.466005325317383, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.3623, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010841944773843808, | |
| "grad_norm": 11.937307357788086, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.1949, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.011229157087195372, | |
| "grad_norm": 4.361509799957275, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0386, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011616369400546937, | |
| "grad_norm": 0.3395012319087982, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0033, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012003581713898502, | |
| "grad_norm": 0.09539712965488434, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.001, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.012390794027250067, | |
| "grad_norm": 0.04306734725832939, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0005, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012778006340601632, | |
| "grad_norm": 0.02652687579393387, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0003, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.013165218653953197, | |
| "grad_norm": 0.01844121888279915, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0002, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01355243096730476, | |
| "grad_norm": 0.01470676064491272, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0002, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013939643280656324, | |
| "grad_norm": 5.602317810058594, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3781, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01432685559400789, | |
| "grad_norm": 14.764276504516602, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.0644, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014714067907359454, | |
| "grad_norm": 9.552111625671387, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.1546, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.015101280220711019, | |
| "grad_norm": 0.046891260892152786, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0006, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.015488492534062584, | |
| "grad_norm": 0.07456453889608383, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0009, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015875704847414147, | |
| "grad_norm": 0.10584703087806702, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0013, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01626291716076571, | |
| "grad_norm": 0.13033287227153778, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0017, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.016650129474117276, | |
| "grad_norm": 0.14958032965660095, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.002, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01703734178746884, | |
| "grad_norm": 0.15836258232593536, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0021, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.017424554100820406, | |
| "grad_norm": 0.1604108363389969, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0022, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01781176641417197, | |
| "grad_norm": 0.15006719529628754, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.002, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.018198978727523536, | |
| "grad_norm": 0.13892512023448944, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0019, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0185861910408751, | |
| "grad_norm": 0.12713688611984253, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0017, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.018973403354226665, | |
| "grad_norm": 8.707756996154785, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.5475, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01936061566757823, | |
| "grad_norm": 8.732000350952148, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5323, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01936061566757823, | |
| "eval_loss": 0.12096888571977615, | |
| "eval_runtime": 0.7605, | |
| "eval_samples_per_second": 65.748, | |
| "eval_steps_per_second": 17.094, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |