| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0032508167677128877, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.501633535425775e-05, | |
| "eval_loss": 2.350724220275879, | |
| "eval_runtime": 495.2406, | |
| "eval_samples_per_second": 13.078, | |
| "eval_steps_per_second": 6.54, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032508167677128876, | |
| "grad_norm": 21.5816707611084, | |
| "learning_rate": 5e-05, | |
| "loss": 8.7887, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006501633535425775, | |
| "grad_norm": 21.14899444580078, | |
| "learning_rate": 0.0001, | |
| "loss": 9.016, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006501633535425775, | |
| "eval_loss": 2.096869468688965, | |
| "eval_runtime": 496.257, | |
| "eval_samples_per_second": 13.052, | |
| "eval_steps_per_second": 6.527, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009752450303138663, | |
| "grad_norm": 16.973087310791016, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 8.1053, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001300326707085155, | |
| "grad_norm": 22.431562423706055, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.9263, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001300326707085155, | |
| "eval_loss": 1.9268721342086792, | |
| "eval_runtime": 499.0126, | |
| "eval_samples_per_second": 12.98, | |
| "eval_steps_per_second": 6.491, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016254083838564439, | |
| "grad_norm": 18.05548858642578, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 7.7338, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0019504900606277327, | |
| "grad_norm": 16.280115127563477, | |
| "learning_rate": 5e-05, | |
| "loss": 7.1957, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0019504900606277327, | |
| "eval_loss": 1.8266757726669312, | |
| "eval_runtime": 497.0156, | |
| "eval_samples_per_second": 13.032, | |
| "eval_steps_per_second": 6.517, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022755717373990213, | |
| "grad_norm": 14.88451862335205, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 7.3993, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00260065341417031, | |
| "grad_norm": 15.47500228881836, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.9907, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00260065341417031, | |
| "eval_loss": 1.8122162818908691, | |
| "eval_runtime": 498.3665, | |
| "eval_samples_per_second": 12.996, | |
| "eval_steps_per_second": 6.499, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002925735090941599, | |
| "grad_norm": 19.3575496673584, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 7.0011, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0032508167677128877, | |
| "grad_norm": 15.406116485595703, | |
| "learning_rate": 0.0, | |
| "loss": 7.6624, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0032508167677128877, | |
| "eval_loss": 1.8033350706100464, | |
| "eval_runtime": 499.5132, | |
| "eval_samples_per_second": 12.967, | |
| "eval_steps_per_second": 6.484, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0340763615363072e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |