| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006167985073476123, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.167985073476122e-05, | |
| "grad_norm": 286.3718566894531, | |
| "learning_rate": 2e-05, | |
| "loss": 10.4703, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.167985073476122e-05, | |
| "eval_loss": 2.628553867340088, | |
| "eval_runtime": 56.8954, | |
| "eval_samples_per_second": 119.992, | |
| "eval_steps_per_second": 60.005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012335970146952244, | |
| "grad_norm": 190.42103576660156, | |
| "learning_rate": 4e-05, | |
| "loss": 10.472, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00018503955220428367, | |
| "grad_norm": 223.15805053710938, | |
| "learning_rate": 6e-05, | |
| "loss": 9.7684, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00018503955220428367, | |
| "eval_loss": 2.628936529159546, | |
| "eval_runtime": 55.2339, | |
| "eval_samples_per_second": 123.602, | |
| "eval_steps_per_second": 61.81, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002467194029390449, | |
| "grad_norm": 157.56570434570312, | |
| "learning_rate": 8e-05, | |
| "loss": 11.4229, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00030839925367380614, | |
| "grad_norm": 247.71270751953125, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3866, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00037007910440856734, | |
| "grad_norm": 184.63584899902344, | |
| "learning_rate": 0.00012, | |
| "loss": 7.938, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00037007910440856734, | |
| "eval_loss": 2.6228034496307373, | |
| "eval_runtime": 55.0574, | |
| "eval_samples_per_second": 123.998, | |
| "eval_steps_per_second": 62.008, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00043175895514332855, | |
| "grad_norm": 163.31253051757812, | |
| "learning_rate": 0.00014, | |
| "loss": 11.0275, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0004934388058780898, | |
| "grad_norm": 163.90606689453125, | |
| "learning_rate": 0.00016, | |
| "loss": 9.5341, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.000555118656612851, | |
| "grad_norm": 163.04898071289062, | |
| "learning_rate": 0.00018, | |
| "loss": 8.9825, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000555118656612851, | |
| "eval_loss": 2.6047780513763428, | |
| "eval_runtime": 55.0856, | |
| "eval_samples_per_second": 123.934, | |
| "eval_steps_per_second": 61.976, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006167985073476123, | |
| "grad_norm": 197.9041748046875, | |
| "learning_rate": 0.0002, | |
| "loss": 11.1085, | |
| "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": 55238102876160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |