| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10810080399972975, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002162016079994595, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 112969080.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002162016079994595, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3145, | |
| "eval_samples_per_second": 21.603, | |
| "eval_steps_per_second": 5.617, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00432403215998919, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006486048239983785, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00864806431997838, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010810080399972975, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01297209647996757, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015134112559962165, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01729612863995676, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019458144719951356, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02162016079994595, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023782176879940546, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02594419295993514, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028106209039929733, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03026822511992433, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03243024119991893, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03459225727991352, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.036754273359908114, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03891628943990271, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0410783055198973, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0432403215998919, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.045402337679886495, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04756435375988109, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04972636983987568, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05188838591987028, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.054050401999864876, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.054050401999864876, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5382, | |
| "eval_samples_per_second": 32.506, | |
| "eval_steps_per_second": 8.451, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.056212418079859466, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05837443415985406, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06053645023984866, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06269846631984326, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06486048239983785, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06702249847983244, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06918451455982703, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07134653063982163, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07350854671981623, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07567056279981083, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07783257887980542, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07999459495980002, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0821566110397946, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0843186271197892, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0864806431997838, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0886426592797784, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09080467535977299, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09296669143976759, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09512870751976218, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09729072359975677, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09945273967975136, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10161475575974596, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10377677183974056, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10593878791973516, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10810080399972975, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10810080399972975, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4679, | |
| "eval_samples_per_second": 34.062, | |
| "eval_steps_per_second": 8.856, | |
| "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": 1.2620071305425715e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |