| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006253664256400234, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015634160641000586, | |
| "grad_norm": 7.24638032913208, | |
| "learning_rate": 1e-05, | |
| "loss": 15.5069, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015634160641000586, | |
| "eval_loss": 1.0162768363952637, | |
| "eval_runtime": 86.2019, | |
| "eval_samples_per_second": 12.506, | |
| "eval_steps_per_second": 6.253, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003126832128200117, | |
| "grad_norm": 5.943104267120361, | |
| "learning_rate": 2e-05, | |
| "loss": 14.4315, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003126832128200117, | |
| "eval_loss": 0.9916371703147888, | |
| "eval_runtime": 67.5561, | |
| "eval_samples_per_second": 15.957, | |
| "eval_steps_per_second": 7.979, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004690248192300176, | |
| "grad_norm": 9.09329891204834, | |
| "learning_rate": 3e-05, | |
| "loss": 18.3182, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006253664256400234, | |
| "grad_norm": 7.477109909057617, | |
| "learning_rate": 4e-05, | |
| "loss": 17.3828, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006253664256400234, | |
| "eval_loss": 0.9752212166786194, | |
| "eval_runtime": 64.2806, | |
| "eval_samples_per_second": 16.77, | |
| "eval_steps_per_second": 8.385, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6094943032442880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |