| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016254083838564439, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.2508167677128876e-05, | |
| "eval_loss": 2.526299476623535, | |
| "eval_runtime": 236.8791, | |
| "eval_samples_per_second": 27.343, | |
| "eval_steps_per_second": 13.674, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032508167677128876, | |
| "grad_norm": 2.55745267868042, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 4.5265, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004226061798026754, | |
| "eval_loss": 1.9930803775787354, | |
| "eval_runtime": 237.9288, | |
| "eval_samples_per_second": 27.222, | |
| "eval_steps_per_second": 13.613, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0006501633535425775, | |
| "grad_norm": 3.1354007720947266, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.0836, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008452123596053508, | |
| "eval_loss": 1.9241468906402588, | |
| "eval_runtime": 238.2324, | |
| "eval_samples_per_second": 27.188, | |
| "eval_steps_per_second": 13.596, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0009752450303138663, | |
| "grad_norm": 2.0775413513183594, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 3.8732, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012678185394080263, | |
| "eval_loss": 1.8944792747497559, | |
| "eval_runtime": 237.9216, | |
| "eval_samples_per_second": 27.223, | |
| "eval_steps_per_second": 13.614, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.001300326707085155, | |
| "grad_norm": 2.8236403465270996, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 3.8875, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016254083838564439, | |
| "grad_norm": 2.360555648803711, | |
| "learning_rate": 0.0, | |
| "loss": 3.913, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 2947346413387776.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |