| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0254602740161991, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000509205480323982, | |
| "grad_norm": 0.3748701512813568, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000509205480323982, | |
| "eval_loss": 1.7874842882156372, | |
| "eval_runtime": 3.1856, | |
| "eval_samples_per_second": 15.696, | |
| "eval_steps_per_second": 4.081, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001018410960647964, | |
| "grad_norm": 0.5964038968086243, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7141, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001527616440971946, | |
| "grad_norm": 0.5587161779403687, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.718, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002036821921295928, | |
| "grad_norm": 0.3342471122741699, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.645, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00254602740161991, | |
| "grad_norm": 0.4013063609600067, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.566, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003055232881943892, | |
| "grad_norm": 0.5646538734436035, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.5331, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0035644383622678738, | |
| "grad_norm": 0.26146721839904785, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.5333, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004073643842591856, | |
| "grad_norm": 0.30147361755371094, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.5599, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004582849322915838, | |
| "grad_norm": 0.37970224022865295, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.5684, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00509205480323982, | |
| "grad_norm": 0.41429415345191956, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.4933, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005601260283563802, | |
| "grad_norm": 0.5373072624206543, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.5144, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006110465763887784, | |
| "grad_norm": 0.7607316374778748, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.4766, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006619671244211766, | |
| "grad_norm": 0.5309444069862366, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.5229, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0071288767245357475, | |
| "grad_norm": 0.6376444697380066, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.3778, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00763808220485973, | |
| "grad_norm": 0.5824431777000427, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.2361, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008147287685183711, | |
| "grad_norm": 0.38122937083244324, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.267, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008656493165507694, | |
| "grad_norm": 0.2554907202720642, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.3699, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009165698645831676, | |
| "grad_norm": 0.30133527517318726, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2751, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009674904126155657, | |
| "grad_norm": 0.24783246219158173, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.366, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01018410960647964, | |
| "grad_norm": 0.311551034450531, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.3862, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010693315086803622, | |
| "grad_norm": 0.3187459111213684, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.3691, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011202520567127604, | |
| "grad_norm": 0.3526560962200165, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.3508, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011711726047451586, | |
| "grad_norm": 0.4195292294025421, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.2983, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012220931527775567, | |
| "grad_norm": 0.4601457715034485, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.2912, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01273013700809955, | |
| "grad_norm": 0.6019033193588257, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.1742, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01273013700809955, | |
| "eval_loss": 1.1895591020584106, | |
| "eval_runtime": 3.2303, | |
| "eval_samples_per_second": 15.478, | |
| "eval_steps_per_second": 4.024, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013239342488423532, | |
| "grad_norm": 0.2677386403083801, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.4179, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013748547968747514, | |
| "grad_norm": 0.33854132890701294, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.152, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.014257753449071495, | |
| "grad_norm": 0.42675265669822693, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.8932, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014766958929395477, | |
| "grad_norm": 0.26116687059402466, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.3545, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01527616440971946, | |
| "grad_norm": 0.24653884768486023, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2111, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015785369890043442, | |
| "grad_norm": 0.2200997769832611, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.2262, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.016294575370367423, | |
| "grad_norm": 0.23955288529396057, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.313, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.016803780850691407, | |
| "grad_norm": 0.24517883360385895, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.3234, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.017312986331015388, | |
| "grad_norm": 0.2714325487613678, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.2972, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01782219181133937, | |
| "grad_norm": 0.30093419551849365, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.2841, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018331397291663352, | |
| "grad_norm": 0.33117982745170593, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.2362, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.018840602771987333, | |
| "grad_norm": 0.4416939914226532, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.2139, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.019349808252311314, | |
| "grad_norm": 0.34697452187538147, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.3128, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019859013732635298, | |
| "grad_norm": 0.2264784425497055, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.3141, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02036821921295928, | |
| "grad_norm": 0.2044232338666916, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.1041, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020877424693283263, | |
| "grad_norm": 0.19597738981246948, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.2327, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.021386630173607243, | |
| "grad_norm": 0.21620656549930573, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3149, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.021895835653931224, | |
| "grad_norm": 0.1993994116783142, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.112, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.022405041134255208, | |
| "grad_norm": 0.21210165321826935, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.3416, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02291424661457919, | |
| "grad_norm": 0.23273739218711853, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.3287, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.023423452094903173, | |
| "grad_norm": 0.23162347078323364, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.3328, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.023932657575227154, | |
| "grad_norm": 0.27658507227897644, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.2636, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.024441863055551134, | |
| "grad_norm": 0.2997262477874756, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.2213, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02495106853587512, | |
| "grad_norm": 0.3726732134819031, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.2438, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0254602740161991, | |
| "grad_norm": 0.5719786286354065, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0469, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0254602740161991, | |
| "eval_loss": 1.1436867713928223, | |
| "eval_runtime": 3.258, | |
| "eval_samples_per_second": 15.347, | |
| "eval_steps_per_second": 3.99, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |