| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0021595007234327425, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.319001446865485e-05, | |
| "eval_loss": 2.5810272693634033, | |
| "eval_runtime": 230.9421, | |
| "eval_samples_per_second": 21.109, | |
| "eval_steps_per_second": 10.557, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004319001446865485, | |
| "grad_norm": 2.164936065673828, | |
| "learning_rate": 0.0002, | |
| "loss": 4.8205, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000561470188092513, | |
| "eval_loss": 2.2967779636383057, | |
| "eval_runtime": 229.5334, | |
| "eval_samples_per_second": 21.239, | |
| "eval_steps_per_second": 10.622, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000863800289373097, | |
| "grad_norm": 1.3639366626739502, | |
| "learning_rate": 0.0002, | |
| "loss": 4.5318, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001122940376185026, | |
| "eval_loss": 2.1809253692626953, | |
| "eval_runtime": 229.5626, | |
| "eval_samples_per_second": 21.236, | |
| "eval_steps_per_second": 10.62, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0012957004340596453, | |
| "grad_norm": 1.3415583372116089, | |
| "learning_rate": 0.0002, | |
| "loss": 4.4065, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001684410564277539, | |
| "eval_loss": 2.131037473678589, | |
| "eval_runtime": 230.2945, | |
| "eval_samples_per_second": 21.169, | |
| "eval_steps_per_second": 10.586, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.001727600578746194, | |
| "grad_norm": 1.7444703578948975, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1676, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0021595007234327425, | |
| "grad_norm": 1.4239596128463745, | |
| "learning_rate": 0.0002, | |
| "loss": 3.9287, | |
| "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": 8059705647955968.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |