| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08324661810613944, | |
| "eval_steps": 20, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04162330905306972, | |
| "grad_norm": 2.6779890060424805, | |
| "learning_rate": 0.00019828326180257511, | |
| "loss": 5.368, | |
| "mean_token_accuracy": 0.8072595901787281, | |
| "num_tokens": 161548.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04162330905306972, | |
| "eval_loss": 0.12305498868227005, | |
| "eval_mean_token_accuracy": 0.9847841203212738, | |
| "eval_num_tokens": 161548.0, | |
| "eval_runtime": 68.9772, | |
| "eval_samples_per_second": 2.9, | |
| "eval_steps_per_second": 0.725, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08324661810613944, | |
| "grad_norm": 0.5366652011871338, | |
| "learning_rate": 0.00018969957081545064, | |
| "loss": 0.1516, | |
| "mean_token_accuracy": 0.9917096085846424, | |
| "num_tokens": 323168.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08324661810613944, | |
| "eval_loss": 0.013321125879883766, | |
| "eval_mean_token_accuracy": 0.9938336944580078, | |
| "eval_num_tokens": 323168.0, | |
| "eval_runtime": 68.8811, | |
| "eval_samples_per_second": 2.904, | |
| "eval_steps_per_second": 0.726, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 481, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 40, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8438646910032768.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |