| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.21929824561403508, | |
| "eval_steps": 4, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008771929824561403, | |
| "grad_norm": 0.04607681930065155, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3709, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008771929824561403, | |
| "eval_loss": 10.366873741149902, | |
| "eval_runtime": 0.3801, | |
| "eval_samples_per_second": 252.546, | |
| "eval_steps_per_second": 31.568, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": 0.05227380245923996, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3737, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 0.04080989211797714, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3745, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 0.04684830084443092, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3609, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "eval_loss": 10.36682415008545, | |
| "eval_runtime": 0.3809, | |
| "eval_samples_per_second": 252.032, | |
| "eval_steps_per_second": 31.504, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.043859649122807015, | |
| "grad_norm": 0.04237261414527893, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3705, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 0.048150435090065, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3758, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06140350877192982, | |
| "grad_norm": 0.047420039772987366, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3704, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 0.040635328739881516, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3729, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "eval_loss": 10.36666202545166, | |
| "eval_runtime": 0.3913, | |
| "eval_samples_per_second": 245.355, | |
| "eval_steps_per_second": 30.669, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 0.05289788916707039, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3734, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08771929824561403, | |
| "grad_norm": 0.046568162739276886, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3704, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09649122807017543, | |
| "grad_norm": 0.052418533712625504, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3717, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 0.043847937136888504, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3713, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "eval_loss": 10.3663911819458, | |
| "eval_runtime": 0.3833, | |
| "eval_samples_per_second": 250.43, | |
| "eval_steps_per_second": 31.304, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11403508771929824, | |
| "grad_norm": 0.038415372371673584, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3704, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12280701754385964, | |
| "grad_norm": 0.04817876219749451, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 10.3738, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 0.040750179439783096, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.371, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 0.044922247529029846, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3723, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "eval_loss": 10.36613655090332, | |
| "eval_runtime": 0.3908, | |
| "eval_samples_per_second": 245.634, | |
| "eval_steps_per_second": 30.704, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14912280701754385, | |
| "grad_norm": 0.05719387158751488, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 10.3761, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 0.050080783665180206, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 10.3609, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.04289044439792633, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 10.3657, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 0.04916112497448921, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3717, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "eval_loss": 10.36597728729248, | |
| "eval_runtime": 0.3838, | |
| "eval_samples_per_second": 250.111, | |
| "eval_steps_per_second": 31.264, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18421052631578946, | |
| "grad_norm": 0.04252730309963226, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 10.3725, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19298245614035087, | |
| "grad_norm": 0.04862263426184654, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.37, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20175438596491227, | |
| "grad_norm": 0.04755020886659622, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 10.3738, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.04188994690775871, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 10.3727, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "eval_loss": 10.365944862365723, | |
| "eval_runtime": 0.3811, | |
| "eval_samples_per_second": 251.914, | |
| "eval_steps_per_second": 31.489, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21929824561403508, | |
| "grad_norm": 0.04175039008259773, | |
| "learning_rate": 0.0, | |
| "loss": 10.3705, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": 1307561164800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |