| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0001279795232762758, | |
| "eval_steps": 3, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.1329920546045965e-05, | |
| "grad_norm": 0.6783462762832642, | |
| "learning_rate": 2e-05, | |
| "loss": 3.7093, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.1329920546045965e-05, | |
| "eval_loss": 1.0025582313537598, | |
| "eval_runtime": 1333.4521, | |
| "eval_samples_per_second": 14.804, | |
| "eval_steps_per_second": 7.402, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.265984109209193e-05, | |
| "grad_norm": 0.6208311319351196, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9313, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.39897616381379e-05, | |
| "grad_norm": 0.5849103927612305, | |
| "learning_rate": 6e-05, | |
| "loss": 4.7468, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.39897616381379e-05, | |
| "eval_loss": 1.0020983219146729, | |
| "eval_runtime": 1335.4679, | |
| "eval_samples_per_second": 14.781, | |
| "eval_steps_per_second": 7.391, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.531968218418386e-05, | |
| "grad_norm": 0.5509039163589478, | |
| "learning_rate": 8e-05, | |
| "loss": 3.7766, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00010664960273022984, | |
| "grad_norm": 0.8875170946121216, | |
| "learning_rate": 0.0001, | |
| "loss": 5.6163, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001279795232762758, | |
| "grad_norm": 0.7614824771881104, | |
| "learning_rate": 0.00012, | |
| "loss": 3.6377, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001279795232762758, | |
| "eval_loss": 0.9959754347801208, | |
| "eval_runtime": 1336.9501, | |
| "eval_samples_per_second": 14.765, | |
| "eval_steps_per_second": 7.382, | |
| "step": 6 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1954499090448384.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |