| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012099213551119177, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024198427102238354, | |
| "eval_loss": 1.6885727643966675, | |
| "eval_runtime": 33.8261, | |
| "eval_samples_per_second": 51.44, | |
| "eval_steps_per_second": 25.72, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024198427102238356, | |
| "grad_norm": 2.8956966400146484, | |
| "learning_rate": 0.0002, | |
| "loss": 6.2532, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003145795523290986, | |
| "eval_loss": 1.5225188732147217, | |
| "eval_runtime": 33.6233, | |
| "eval_samples_per_second": 51.75, | |
| "eval_steps_per_second": 25.875, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004839685420447671, | |
| "grad_norm": 3.5267632007598877, | |
| "learning_rate": 0.0002, | |
| "loss": 6.0738, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006291591046581972, | |
| "eval_loss": 1.4543232917785645, | |
| "eval_runtime": 33.6487, | |
| "eval_samples_per_second": 51.711, | |
| "eval_steps_per_second": 25.855, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007259528130671506, | |
| "grad_norm": 2.896638870239258, | |
| "learning_rate": 0.0002, | |
| "loss": 5.5457, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009437386569872959, | |
| "eval_loss": 1.4132994413375854, | |
| "eval_runtime": 33.6179, | |
| "eval_samples_per_second": 51.758, | |
| "eval_steps_per_second": 25.879, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009679370840895343, | |
| "grad_norm": 4.2689433097839355, | |
| "learning_rate": 0.0002, | |
| "loss": 5.7251, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012099213551119177, | |
| "grad_norm": 3.8046035766601562, | |
| "learning_rate": 0.0002, | |
| "loss": 5.2778, | |
| "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": 1910863162245120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |