| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.040537116797567774, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008107423359513554, | |
| "eval_loss": NaN, | |
| "eval_runtime": 570.4037, | |
| "eval_samples_per_second": 14.569, | |
| "eval_steps_per_second": 1.822, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008107423359513555, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008107423359513555, | |
| "eval_loss": NaN, | |
| "eval_runtime": 567.6362, | |
| "eval_samples_per_second": 14.64, | |
| "eval_steps_per_second": 1.83, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01621484671902711, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01621484671902711, | |
| "eval_loss": NaN, | |
| "eval_runtime": 567.1332, | |
| "eval_samples_per_second": 14.653, | |
| "eval_steps_per_second": 1.832, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024322270078540664, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.024322270078540664, | |
| "eval_loss": NaN, | |
| "eval_runtime": 566.1102, | |
| "eval_samples_per_second": 14.679, | |
| "eval_steps_per_second": 1.835, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03242969343805422, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03242969343805422, | |
| "eval_loss": NaN, | |
| "eval_runtime": 567.0942, | |
| "eval_samples_per_second": 14.654, | |
| "eval_steps_per_second": 1.832, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.040537116797567774, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.040537116797567774, | |
| "eval_loss": NaN, | |
| "eval_runtime": 565.2586, | |
| "eval_samples_per_second": 14.701, | |
| "eval_steps_per_second": 1.838, | |
| "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": 1.464141918114939e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |