| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7001983895437041, | |
| "eval_steps": 250, | |
| "global_step": 750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2333994631812347, | |
| "grad_norm": 3.488569974899292, | |
| "learning_rate": 8.978253703087328e-05, | |
| "loss": 0.2689, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2333994631812347, | |
| "eval_loss": 0.14780883491039276, | |
| "eval_runtime": 39.2591, | |
| "eval_samples_per_second": 2.216, | |
| "eval_steps_per_second": 2.216, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "grad_norm": 4.226513385772705, | |
| "learning_rate": 5.813544178200335e-05, | |
| "loss": 0.1128, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "eval_loss": 0.12125887721776962, | |
| "eval_runtime": 39.3412, | |
| "eval_samples_per_second": 2.211, | |
| "eval_steps_per_second": 2.211, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "grad_norm": 2.6956961154937744, | |
| "learning_rate": 2.2048719230965166e-05, | |
| "loss": 0.099, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "eval_loss": 0.10832132399082184, | |
| "eval_runtime": 39.1571, | |
| "eval_samples_per_second": 2.222, | |
| "eval_steps_per_second": 2.222, | |
| "step": 750 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 1071, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.120673935538176e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |