| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 6.723871231079102, | |
| "learning_rate": 4.9800000000000004e-05, | |
| "loss": 6.3518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.806936502456665, | |
| "learning_rate": 4.9550000000000005e-05, | |
| "loss": 5.2146, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": 5.464715003967285, | |
| "learning_rate": 4.93e-05, | |
| "loss": 5.3944, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 7.181273937225342, | |
| "learning_rate": 4.905e-05, | |
| "loss": 4.9653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 3.466884136199951, | |
| "learning_rate": 4.88e-05, | |
| "loss": 4.3435, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 6.4920830726623535, | |
| "learning_rate": 4.855e-05, | |
| "loss": 5.0843, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": 6.69465446472168, | |
| "learning_rate": 4.83e-05, | |
| "loss": 5.5838, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 13.27942943572998, | |
| "learning_rate": 4.805e-05, | |
| "loss": 5.4903, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": 7.836321830749512, | |
| "learning_rate": 4.78e-05, | |
| "loss": 6.0388, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 6.168878555297852, | |
| "learning_rate": 4.755e-05, | |
| "loss": 5.1972, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "grad_norm": 4.194369316101074, | |
| "learning_rate": 4.73e-05, | |
| "loss": 4.9553, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 14.01821517944336, | |
| "learning_rate": 4.705e-05, | |
| "loss": 5.059, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "grad_norm": 5.50333309173584, | |
| "learning_rate": 4.6800000000000006e-05, | |
| "loss": 5.1333, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 8.491551399230957, | |
| "learning_rate": 4.655000000000001e-05, | |
| "loss": 5.6745, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 6.9947357177734375, | |
| "learning_rate": 4.630000000000001e-05, | |
| "loss": 5.9163, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 9.96507453918457, | |
| "learning_rate": 4.605e-05, | |
| "loss": 6.2083, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "grad_norm": 4.116439342498779, | |
| "learning_rate": 4.58e-05, | |
| "loss": 4.9216, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 12.154153823852539, | |
| "learning_rate": 4.555e-05, | |
| "loss": 4.8928, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "grad_norm": 5.3574395179748535, | |
| "learning_rate": 4.53e-05, | |
| "loss": 6.1012, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 4.469454288482666, | |
| "learning_rate": 4.5050000000000004e-05, | |
| "loss": 4.9137, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.105, | |
| "grad_norm": 4.144026756286621, | |
| "learning_rate": 4.4800000000000005e-05, | |
| "loss": 4.9198, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 14.926289558410645, | |
| "learning_rate": 4.4550000000000005e-05, | |
| "loss": 5.0548, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.115, | |
| "grad_norm": 3.8435521125793457, | |
| "learning_rate": 4.43e-05, | |
| "loss": 5.5779, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 5.218202114105225, | |
| "learning_rate": 4.405e-05, | |
| "loss": 4.2187, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 3.6816904544830322, | |
| "learning_rate": 4.38e-05, | |
| "loss": 4.8792, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 4.585783004760742, | |
| "learning_rate": 4.355e-05, | |
| "loss": 4.9485, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.135, | |
| "grad_norm": 2.7602925300598145, | |
| "learning_rate": 4.33e-05, | |
| "loss": 4.9472, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 3.877700090408325, | |
| "learning_rate": 4.305e-05, | |
| "loss": 6.275, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.145, | |
| "grad_norm": 3.4372103214263916, | |
| "learning_rate": 4.2800000000000004e-05, | |
| "loss": 5.5237, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 7.72742223739624, | |
| "learning_rate": 4.2550000000000004e-05, | |
| "loss": 5.1829, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.155, | |
| "grad_norm": 3.0909502506256104, | |
| "learning_rate": 4.23e-05, | |
| "loss": 4.9871, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 6.721127033233643, | |
| "learning_rate": 4.205e-05, | |
| "loss": 4.5381, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.165, | |
| "grad_norm": 3.377737522125244, | |
| "learning_rate": 4.18e-05, | |
| "loss": 4.3582, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 5.443429470062256, | |
| "learning_rate": 4.155e-05, | |
| "loss": 4.8136, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "grad_norm": 6.62492036819458, | |
| "learning_rate": 4.13e-05, | |
| "loss": 4.5059, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 3.996607780456543, | |
| "learning_rate": 4.105e-05, | |
| "loss": 5.043, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.185, | |
| "grad_norm": 8.51787281036377, | |
| "learning_rate": 4.08e-05, | |
| "loss": 3.9811, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 32.909263610839844, | |
| "learning_rate": 4.055e-05, | |
| "loss": 5.8957, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.195, | |
| "grad_norm": 14.843151092529297, | |
| "learning_rate": 4.0300000000000004e-05, | |
| "loss": 5.7668, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 16.71015167236328, | |
| "learning_rate": 4.0050000000000004e-05, | |
| "loss": 5.345, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |