| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.45599635202918376, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022799817601459188, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 5.7819, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.045599635202918376, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.6693, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06839945280437756, | |
| "grad_norm": 0.021484375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0543, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09119927040583675, | |
| "grad_norm": 0.02978515625, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0068, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11399908800729594, | |
| "grad_norm": 0.072265625, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.003, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.13679890560875513, | |
| "grad_norm": 0.007110595703125, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0028, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15959872321021432, | |
| "grad_norm": 0.012939453125, | |
| "learning_rate": 0.00019840738971173754, | |
| "loss": 0.001, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1823985408116735, | |
| "grad_norm": 0.00201416015625, | |
| "learning_rate": 0.00019681477942347508, | |
| "loss": 0.0009, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2051983584131327, | |
| "grad_norm": 0.005706787109375, | |
| "learning_rate": 0.00019522216913521264, | |
| "loss": 0.0023, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.22799817601459188, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 0.00019362955884695015, | |
| "loss": 0.0022, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2507979936160511, | |
| "grad_norm": 0.0015106201171875, | |
| "learning_rate": 0.0001920369485586877, | |
| "loss": 0.0021, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.27359781121751026, | |
| "grad_norm": 0.023193359375, | |
| "learning_rate": 0.00019044433827042522, | |
| "loss": 0.0015, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.29639762881896947, | |
| "grad_norm": 0.07421875, | |
| "learning_rate": 0.00018885172798216278, | |
| "loss": 0.0011, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.31919744642042863, | |
| "grad_norm": 0.00177001953125, | |
| "learning_rate": 0.0001872591176939003, | |
| "loss": 0.0019, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.34199726402188785, | |
| "grad_norm": 0.0230712890625, | |
| "learning_rate": 0.00018566650740563785, | |
| "loss": 0.0008, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.364797081623347, | |
| "grad_norm": 0.00101470947265625, | |
| "learning_rate": 0.0001840738971173754, | |
| "loss": 0.001, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.3875968992248062, | |
| "grad_norm": 0.0216064453125, | |
| "learning_rate": 0.00018248128682911291, | |
| "loss": 0.0011, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.4103967168262654, | |
| "grad_norm": 7.43865966796875e-05, | |
| "learning_rate": 0.00018088867654085048, | |
| "loss": 0.001, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4331965344277246, | |
| "grad_norm": 4.315376281738281e-05, | |
| "learning_rate": 0.00017929606625258798, | |
| "loss": 0.0009, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.45599635202918376, | |
| "grad_norm": 0.0012969970703125, | |
| "learning_rate": 0.00017770345596432554, | |
| "loss": 0.0008, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 6579, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "total_flos": 0.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |