| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0028187872167999718, | |
| "eval_steps": 10, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002818787216799972, | |
| "grad_norm": 0.8318862915039062, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3917, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002818787216799972, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.938, | |
| "eval_samples_per_second": 214.378, | |
| "eval_steps_per_second": 107.189, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005637574433599944, | |
| "grad_norm": 0.7252686619758606, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3956, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008456361650399915, | |
| "grad_norm": 0.7244169116020203, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.4002, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011275148867199887, | |
| "grad_norm": 0.6884745955467224, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3849, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014093936083999859, | |
| "grad_norm": 0.7329391241073608, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3938, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001691272330079983, | |
| "grad_norm": 0.7550716400146484, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3866, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019731510517599802, | |
| "grad_norm": 0.739791214466095, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3834, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022550297734399774, | |
| "grad_norm": 0.7560977935791016, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3823, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025369084951199746, | |
| "grad_norm": 0.7639404535293579, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3748, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028187872167999718, | |
| "grad_norm": 0.7689390182495117, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3804, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028187872167999718, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.9503, | |
| "eval_samples_per_second": 214.19, | |
| "eval_steps_per_second": 107.095, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1082566508544.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |