| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0015218769816106531, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "grad_norm": 0.45045530796051025, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8337, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 0.7358970642089844, | |
| "eval_runtime": 73.8094, | |
| "eval_samples_per_second": 33.736, | |
| "eval_steps_per_second": 16.868, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003381948848023674, | |
| "grad_norm": 0.40704986453056335, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6735, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "grad_norm": 0.44953006505966187, | |
| "learning_rate": 6e-05, | |
| "loss": 0.8433, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "eval_loss": 0.7347161173820496, | |
| "eval_runtime": 73.2045, | |
| "eval_samples_per_second": 34.014, | |
| "eval_steps_per_second": 17.007, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006763897696047348, | |
| "grad_norm": 0.4584774076938629, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8486, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "grad_norm": 0.5321890711784363, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6456, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "grad_norm": 0.4280243217945099, | |
| "learning_rate": 0.00012, | |
| "loss": 0.7778, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "eval_loss": 0.720082700252533, | |
| "eval_runtime": 75.8775, | |
| "eval_samples_per_second": 32.816, | |
| "eval_steps_per_second": 16.408, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011836820968082857, | |
| "grad_norm": 0.44897976517677307, | |
| "learning_rate": 0.00014, | |
| "loss": 0.7276, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013527795392094695, | |
| "grad_norm": 0.41854241490364075, | |
| "learning_rate": 0.00016, | |
| "loss": 0.6267, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "grad_norm": 0.45529505610466003, | |
| "learning_rate": 0.00018, | |
| "loss": 0.7532, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "eval_loss": 0.6932230591773987, | |
| "eval_runtime": 73.2665, | |
| "eval_samples_per_second": 33.985, | |
| "eval_steps_per_second": 16.993, | |
| "step": 9 | |
| } | |
| ], | |
| "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": 155816786657280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |