| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007700934219582513, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.700934219582514e-05, | |
| "grad_norm": 0.44221264123916626, | |
| "learning_rate": 1e-05, | |
| "loss": 0.918, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.700934219582514e-05, | |
| "eval_loss": 1.0547187328338623, | |
| "eval_runtime": 980.5874, | |
| "eval_samples_per_second": 22.304, | |
| "eval_steps_per_second": 11.152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015401868439165027, | |
| "grad_norm": 0.40297988057136536, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9651, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002310280265874754, | |
| "grad_norm": 0.6582609415054321, | |
| "learning_rate": 3e-05, | |
| "loss": 1.003, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002310280265874754, | |
| "eval_loss": 1.0451246500015259, | |
| "eval_runtime": 846.3252, | |
| "eval_samples_per_second": 25.842, | |
| "eval_steps_per_second": 12.922, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00030803736878330055, | |
| "grad_norm": 0.6603010892868042, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0077, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00038504671097912567, | |
| "grad_norm": 0.45248380303382874, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9375, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004620560531749508, | |
| "grad_norm": 0.43786242604255676, | |
| "learning_rate": 6e-05, | |
| "loss": 0.8561, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004620560531749508, | |
| "eval_loss": 1.0127555131912231, | |
| "eval_runtime": 848.2642, | |
| "eval_samples_per_second": 25.783, | |
| "eval_steps_per_second": 12.892, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000539065395370776, | |
| "grad_norm": 0.5223966240882874, | |
| "learning_rate": 7e-05, | |
| "loss": 0.8814, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006160747375666011, | |
| "grad_norm": 0.4434320628643036, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7536, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006930840797624262, | |
| "grad_norm": 0.4289049208164215, | |
| "learning_rate": 9e-05, | |
| "loss": 0.8456, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006930840797624262, | |
| "eval_loss": 0.9601964950561523, | |
| "eval_runtime": 847.8338, | |
| "eval_samples_per_second": 25.796, | |
| "eval_steps_per_second": 12.899, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007700934219582513, | |
| "grad_norm": 0.527527391910553, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9335, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.227876234952704e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |