| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00299028158484924, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00033225350942769335, | |
| "eval_loss": 2.1395199298858643, | |
| "eval_runtime": 220.9563, | |
| "eval_samples_per_second": 22.941, | |
| "eval_steps_per_second": 2.869, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00099676052828308, | |
| "grad_norm": 5.9584269523620605, | |
| "learning_rate": 1.5e-05, | |
| "loss": 9.4483, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00199352105656616, | |
| "grad_norm": 4.213073253631592, | |
| "learning_rate": 3e-05, | |
| "loss": 7.8813, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00299028158484924, | |
| "grad_norm": 4.823021411895752, | |
| "learning_rate": 4.5e-05, | |
| "loss": 7.9607, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00299028158484924, | |
| "eval_loss": 2.070302963256836, | |
| "eval_runtime": 221.304, | |
| "eval_samples_per_second": 22.905, | |
| "eval_steps_per_second": 2.865, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 803933119315968.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |