| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5596412556053811, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014349775784753363, | |
| "eval_loss": 2.3939390182495117, | |
| "eval_runtime": 1.4295, | |
| "eval_samples_per_second": 328.794, | |
| "eval_steps_per_second": 41.274, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14349775784753363, | |
| "grad_norm": 1.8494077920913696, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.3322, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14349775784753363, | |
| "eval_loss": 2.127523422241211, | |
| "eval_runtime": 1.4206, | |
| "eval_samples_per_second": 330.845, | |
| "eval_steps_per_second": 41.532, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28699551569506726, | |
| "grad_norm": 1.4584089517593384, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9772, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28699551569506726, | |
| "eval_loss": 1.8149807453155518, | |
| "eval_runtime": 1.4797, | |
| "eval_samples_per_second": 317.639, | |
| "eval_steps_per_second": 39.874, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4304932735426009, | |
| "grad_norm": 1.3032526969909668, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.7502, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4304932735426009, | |
| "eval_loss": 1.653484582901001, | |
| "eval_runtime": 1.4493, | |
| "eval_samples_per_second": 324.296, | |
| "eval_steps_per_second": 40.71, | |
| "step": 30 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1294151165411328.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |