| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00701877522372346, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007018775223723461, | |
| "eval_loss": 10.378314971923828, | |
| "eval_runtime": 5.2226, | |
| "eval_samples_per_second": 459.545, | |
| "eval_steps_per_second": 57.443, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002105632567117038, | |
| "grad_norm": 0.07227218896150589, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00350938761186173, | |
| "eval_loss": 10.377897262573242, | |
| "eval_runtime": 5.2366, | |
| "eval_samples_per_second": 458.312, | |
| "eval_steps_per_second": 57.289, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004211265134234076, | |
| "grad_norm": 0.0682116374373436, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3798, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0063168977013511145, | |
| "grad_norm": 0.077728271484375, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3792, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00701877522372346, | |
| "eval_loss": 10.376399040222168, | |
| "eval_runtime": 5.2739, | |
| "eval_samples_per_second": 455.068, | |
| "eval_steps_per_second": 56.884, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1143394271232.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |