| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00035430839002267573, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.5430839002267575e-05, | |
| "grad_norm": 0.5061426162719727, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7808, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.5430839002267575e-05, | |
| "eval_loss": 1.7351099252700806, | |
| "eval_runtime": 413.8304, | |
| "eval_samples_per_second": 28.717, | |
| "eval_steps_per_second": 14.359, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.086167800453515e-05, | |
| "grad_norm": 0.49216797947883606, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7578, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010629251700680272, | |
| "grad_norm": 0.37747350335121155, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7345, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010629251700680272, | |
| "eval_loss": 1.7343388795852661, | |
| "eval_runtime": 412.5091, | |
| "eval_samples_per_second": 28.809, | |
| "eval_steps_per_second": 14.405, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001417233560090703, | |
| "grad_norm": 0.9286957383155823, | |
| "learning_rate": 8e-05, | |
| "loss": 1.801, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00017715419501133787, | |
| "grad_norm": 0.5991570353507996, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9955, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00021258503401360543, | |
| "grad_norm": 0.8438509702682495, | |
| "learning_rate": 0.00012, | |
| "loss": 1.551, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00021258503401360543, | |
| "eval_loss": 1.7245092391967773, | |
| "eval_runtime": 413.1198, | |
| "eval_samples_per_second": 28.766, | |
| "eval_steps_per_second": 14.383, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000248015873015873, | |
| "grad_norm": 0.7378438115119934, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8651, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002834467120181406, | |
| "grad_norm": 0.816046953201294, | |
| "learning_rate": 0.00016, | |
| "loss": 2.4483, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00031887755102040814, | |
| "grad_norm": 0.7346668243408203, | |
| "learning_rate": 0.00018, | |
| "loss": 1.5634, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00031887755102040814, | |
| "eval_loss": 1.6762374639511108, | |
| "eval_runtime": 413.3924, | |
| "eval_samples_per_second": 28.748, | |
| "eval_steps_per_second": 14.374, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00035430839002267573, | |
| "grad_norm": 1.7053476572036743, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7112, | |
| "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": 2173237991571456.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |