| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0001841629105106377, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.841629105106377e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.841629105106377e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 868.7925, | |
| "eval_samples_per_second": 26.317, | |
| "eval_steps_per_second": 13.158, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.683258210212754e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.5248873153191314e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.5248873153191314e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 867.5434, | |
| "eval_samples_per_second": 26.355, | |
| "eval_steps_per_second": 13.177, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.366516420425509e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 9.208145525531885e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00011049774630638263, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011049774630638263, | |
| "eval_loss": NaN, | |
| "eval_runtime": 867.8234, | |
| "eval_samples_per_second": 26.346, | |
| "eval_steps_per_second": 13.173, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001289140373574464, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00014733032840851017, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00016574661945957395, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00016574661945957395, | |
| "eval_loss": NaN, | |
| "eval_runtime": 867.5958, | |
| "eval_samples_per_second": 26.353, | |
| "eval_steps_per_second": 13.177, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001841629105106377, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2358194416386048.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |