| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06255864873318737, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012511729746637473, | |
| "eval_loss": 5.3348588943481445, | |
| "eval_runtime": 21.6661, | |
| "eval_samples_per_second": 15.554, | |
| "eval_steps_per_second": 7.8, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006255864873318737, | |
| "grad_norm": 2.4197850227355957, | |
| "learning_rate": 5e-05, | |
| "loss": 5.3435, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012511729746637473, | |
| "grad_norm": 3.464526414871216, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9746, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012511729746637473, | |
| "eval_loss": 4.500220775604248, | |
| "eval_runtime": 21.066, | |
| "eval_samples_per_second": 15.997, | |
| "eval_steps_per_second": 8.022, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01876759461995621, | |
| "grad_norm": 3.124346971511841, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.8447, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025023459493274947, | |
| "grad_norm": 4.356178283691406, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.8011, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025023459493274947, | |
| "eval_loss": 2.1410269737243652, | |
| "eval_runtime": 20.9938, | |
| "eval_samples_per_second": 16.052, | |
| "eval_steps_per_second": 8.05, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03127932436659368, | |
| "grad_norm": 3.253753900527954, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9288, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03753518923991242, | |
| "grad_norm": 3.5155556201934814, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8595, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03753518923991242, | |
| "eval_loss": 1.6997840404510498, | |
| "eval_runtime": 21.0783, | |
| "eval_samples_per_second": 15.988, | |
| "eval_steps_per_second": 8.018, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.043791054113231156, | |
| "grad_norm": 2.9763023853302, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4677, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05004691898654989, | |
| "grad_norm": 3.466015100479126, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5134, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05004691898654989, | |
| "eval_loss": 1.595062017440796, | |
| "eval_runtime": 21.0937, | |
| "eval_samples_per_second": 15.976, | |
| "eval_steps_per_second": 8.012, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05630278385986863, | |
| "grad_norm": 2.9902255535125732, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6106, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06255864873318737, | |
| "grad_norm": 3.0252177715301514, | |
| "learning_rate": 0.0, | |
| "loss": 1.5417, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06255864873318737, | |
| "eval_loss": 1.5778958797454834, | |
| "eval_runtime": 21.0448, | |
| "eval_samples_per_second": 16.013, | |
| "eval_steps_per_second": 8.031, | |
| "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": 8713180230451200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |