| { |
| "best_global_step": 4800, |
| "best_metric": 5.383272171020508, |
| "best_model_checkpoint": null, |
| "epoch": 15.0, |
| "eval_steps": 500, |
| "global_step": 6000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0025, |
| "grad_norm": 16.100624084472656, |
| "learning_rate": 0.0, |
| "loss": 10.3279, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.404994249343872, |
| "learning_rate": 7.98e-05, |
| "loss": 7.0427, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 6.198990345001221, |
| "eval_runtime": 42.1632, |
| "eval_samples_per_second": 609.275, |
| "eval_steps_per_second": 2.395, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.2766317129135132, |
| "learning_rate": 9.600267379679145e-05, |
| "loss": 5.9607, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 5.85300350189209, |
| "eval_runtime": 44.0748, |
| "eval_samples_per_second": 582.85, |
| "eval_steps_per_second": 2.292, |
| "step": 800 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.36733078956604, |
| "learning_rate": 9.065508021390375e-05, |
| "loss": 5.7343, |
| "step": 1200 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 5.715977668762207, |
| "eval_runtime": 44.0451, |
| "eval_samples_per_second": 583.243, |
| "eval_steps_per_second": 2.293, |
| "step": 1200 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.3367751836776733, |
| "learning_rate": 8.530748663101604e-05, |
| "loss": 5.6009, |
| "step": 1600 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 5.622774600982666, |
| "eval_runtime": 43.8815, |
| "eval_samples_per_second": 585.417, |
| "eval_steps_per_second": 2.302, |
| "step": 1600 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 1.3959336280822754, |
| "learning_rate": 7.995989304812834e-05, |
| "loss": 5.4929, |
| "step": 2000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 5.5484700202941895, |
| "eval_runtime": 43.9851, |
| "eval_samples_per_second": 584.039, |
| "eval_steps_per_second": 2.296, |
| "step": 2000 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 1.500172734260559, |
| "learning_rate": 7.461229946524065e-05, |
| "loss": 5.3999, |
| "step": 2400 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 5.494987964630127, |
| "eval_runtime": 44.1149, |
| "eval_samples_per_second": 582.32, |
| "eval_steps_per_second": 2.289, |
| "step": 2400 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 1.5156828165054321, |
| "learning_rate": 6.926470588235294e-05, |
| "loss": 5.3184, |
| "step": 2800 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 5.4551777839660645, |
| "eval_runtime": 44.0519, |
| "eval_samples_per_second": 583.153, |
| "eval_steps_per_second": 2.293, |
| "step": 2800 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 1.7039804458618164, |
| "learning_rate": 6.391711229946524e-05, |
| "loss": 5.2448, |
| "step": 3200 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 5.4279961585998535, |
| "eval_runtime": 43.9751, |
| "eval_samples_per_second": 584.172, |
| "eval_steps_per_second": 2.297, |
| "step": 3200 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 1.7658451795578003, |
| "learning_rate": 5.8569518716577545e-05, |
| "loss": 5.1772, |
| "step": 3600 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 5.405717372894287, |
| "eval_runtime": 43.8709, |
| "eval_samples_per_second": 585.559, |
| "eval_steps_per_second": 2.302, |
| "step": 3600 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 1.9227123260498047, |
| "learning_rate": 5.322192513368984e-05, |
| "loss": 5.1132, |
| "step": 4000 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 5.394469738006592, |
| "eval_runtime": 44.0522, |
| "eval_samples_per_second": 583.149, |
| "eval_steps_per_second": 2.293, |
| "step": 4000 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 2.014274835586548, |
| "learning_rate": 4.787433155080214e-05, |
| "loss": 5.0533, |
| "step": 4400 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 5.386741638183594, |
| "eval_runtime": 43.9434, |
| "eval_samples_per_second": 584.593, |
| "eval_steps_per_second": 2.298, |
| "step": 4400 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 2.2169082164764404, |
| "learning_rate": 4.2526737967914444e-05, |
| "loss": 4.9969, |
| "step": 4800 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 5.383272171020508, |
| "eval_runtime": 42.2904, |
| "eval_samples_per_second": 607.443, |
| "eval_steps_per_second": 2.388, |
| "step": 4800 |
| }, |
| { |
| "epoch": 13.0, |
| "grad_norm": 2.3257579803466797, |
| "learning_rate": 3.717914438502674e-05, |
| "loss": 4.9436, |
| "step": 5200 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 5.384706020355225, |
| "eval_runtime": 43.5224, |
| "eval_samples_per_second": 590.247, |
| "eval_steps_per_second": 2.321, |
| "step": 5200 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 2.463223934173584, |
| "learning_rate": 3.1831550802139034e-05, |
| "loss": 4.8924, |
| "step": 5600 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 5.388067245483398, |
| "eval_runtime": 44.0507, |
| "eval_samples_per_second": 583.168, |
| "eval_steps_per_second": 2.293, |
| "step": 5600 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 8000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.0012743327744e+17, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
