| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 30, |
| "global_step": 225, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.044444444444444446, |
| "grad_norm": 0.2802587151527405, |
| "learning_rate": 9.951340343707852e-05, |
| "loss": 0.3045, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.08888888888888889, |
| "grad_norm": 0.021381886675953865, |
| "learning_rate": 9.806308479691595e-05, |
| "loss": 0.0054, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13333333333333333, |
| "grad_norm": 0.017750784754753113, |
| "learning_rate": 9.567727288213005e-05, |
| "loss": 0.0039, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.13333333333333333, |
| "eval_loss": 0.0036237684544175863, |
| "eval_runtime": 53.377, |
| "eval_samples_per_second": 18.735, |
| "eval_steps_per_second": 0.468, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.17777777777777778, |
| "grad_norm": 0.009207488968968391, |
| "learning_rate": 9.24024048078213e-05, |
| "loss": 0.0036, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 0.03058847412467003, |
| "learning_rate": 8.83022221559489e-05, |
| "loss": 0.0037, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.26666666666666666, |
| "grad_norm": 0.023914409801363945, |
| "learning_rate": 8.345653031794292e-05, |
| "loss": 0.0038, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.26666666666666666, |
| "eval_loss": 0.0036710596177726984, |
| "eval_runtime": 53.396, |
| "eval_samples_per_second": 18.728, |
| "eval_steps_per_second": 0.468, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.3111111111111111, |
| "grad_norm": 0.0324842669069767, |
| "learning_rate": 7.795964517353735e-05, |
| "loss": 0.0036, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 0.002750804414972663, |
| "learning_rate": 7.191855733945387e-05, |
| "loss": 0.0036, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.0023576547391712666, |
| "learning_rate": 6.545084971874738e-05, |
| "loss": 0.0036, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 0.003560666460543871, |
| "eval_runtime": 53.4786, |
| "eval_samples_per_second": 18.699, |
| "eval_steps_per_second": 0.467, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 0.016149163246154785, |
| "learning_rate": 5.868240888334653e-05, |
| "loss": 0.0036, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4888888888888889, |
| "grad_norm": 0.0039548748172819614, |
| "learning_rate": 5.174497483512506e-05, |
| "loss": 0.0035, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 0.0059623029083013535, |
| "learning_rate": 4.477357683661734e-05, |
| "loss": 0.0036, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "eval_loss": 0.00353414099663496, |
| "eval_runtime": 53.3696, |
| "eval_samples_per_second": 18.737, |
| "eval_steps_per_second": 0.468, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5777777777777777, |
| "grad_norm": 0.01755256950855255, |
| "learning_rate": 3.790390522001662e-05, |
| "loss": 0.0035, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.6222222222222222, |
| "grad_norm": 0.005563901271671057, |
| "learning_rate": 3.12696703292044e-05, |
| "loss": 0.0035, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.004853326827287674, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 0.0036, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "eval_loss": 0.0035362462513148785, |
| "eval_runtime": 53.3856, |
| "eval_samples_per_second": 18.732, |
| "eval_steps_per_second": 0.468, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.0062214070931077, |
| "learning_rate": 1.9216926233717085e-05, |
| "loss": 0.0036, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.7555555555555555, |
| "grad_norm": 0.0025808655191212893, |
| "learning_rate": 1.4033009983067452e-05, |
| "loss": 0.0035, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.00887165404856205, |
| "learning_rate": 9.549150281252633e-06, |
| "loss": 0.0035, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 0.0035414749290794134, |
| "eval_runtime": 53.35, |
| "eval_samples_per_second": 18.744, |
| "eval_steps_per_second": 0.469, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.8444444444444444, |
| "grad_norm": 0.005598729941993952, |
| "learning_rate": 5.852620357053651e-06, |
| "loss": 0.0035, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 0.010787834413349628, |
| "learning_rate": 3.0153689607045845e-06, |
| "loss": 0.0035, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9333333333333333, |
| "grad_norm": 0.00533076049759984, |
| "learning_rate": 1.0926199633097157e-06, |
| "loss": 0.0035, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.9333333333333333, |
| "eval_loss": 0.003532670671120286, |
| "eval_runtime": 53.3444, |
| "eval_samples_per_second": 18.746, |
| "eval_steps_per_second": 0.469, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.9777777777777777, |
| "grad_norm": 0.006618449930101633, |
| "learning_rate": 1.2179748700879012e-07, |
| "loss": 0.0035, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 225, |
| "total_flos": 7.559164517091901e+17, |
| "train_loss": 0.017044952660799025, |
| "train_runtime": 1944.9953, |
| "train_samples_per_second": 4.627, |
| "train_steps_per_second": 0.116 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 225, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 2000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.559164517091901e+17, |
| "train_batch_size": 10, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
