| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05473453749315818, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010946907498631637, | |
| "grad_norm": 23.79241371154785, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4398, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010946907498631637, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.1339, | |
| "eval_samples_per_second": 9.739, | |
| "eval_steps_per_second": 2.532, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021893814997263274, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 99634912.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003284072249589491, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004378762999452655, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005473453749315818, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006568144499178982, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007662835249042145, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00875752599890531, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009852216748768473, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010946907498631636, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0120415982484948, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013136288998357963, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014230979748221127, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01532567049808429, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016420361247947456, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01751505199781062, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018609742747673783, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019704433497536946, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02079912424740011, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021893814997263273, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022988505747126436, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0240831964969896, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025177887246852763, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.026272577996715927, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02736726874657909, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02736726874657909, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.3665, | |
| "eval_samples_per_second": 11.451, | |
| "eval_steps_per_second": 2.977, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028461959496442254, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.029556650246305417, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03065134099616858, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.031746031746031744, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03284072249589491, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03393541324575807, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03503010399562124, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0361247947454844, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.037219485495347565, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.038314176245210725, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03940886699507389, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04050355774493705, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04159824849480022, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.042692939244663386, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.043787629994526546, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04488232074438971, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04597701149425287, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04707170224411604, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0481663929939792, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04926108374384237, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05035577449370553, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.051450465243568694, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.052545155993431854, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05363984674329502, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05473453749315818, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05473453749315818, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.3506, | |
| "eval_samples_per_second": 11.493, | |
| "eval_steps_per_second": 2.988, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.155636985124618e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |