| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4, | |
| "eval_steps": 50, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.05632242560386658, | |
| "learning_rate": 0.00013297872340425532, | |
| "loss": 1.8852, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.7156720161437988, | |
| "eval_runtime": 149.1859, | |
| "eval_samples_per_second": 3.352, | |
| "eval_steps_per_second": 0.422, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.02606302499771118, | |
| "learning_rate": 0.0002632978723404255, | |
| "loss": 1.6036, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.5024453401565552, | |
| "eval_runtime": 149.3514, | |
| "eval_samples_per_second": 3.348, | |
| "eval_steps_per_second": 0.422, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.034023039042949677, | |
| "learning_rate": 0.00039627659574468084, | |
| "loss": 1.5186, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.4826966524124146, | |
| "eval_runtime": 149.1669, | |
| "eval_samples_per_second": 3.352, | |
| "eval_steps_per_second": 0.422, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.04070857912302017, | |
| "learning_rate": 0.0004967397747480735, | |
| "loss": 1.4822, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.4759048223495483, | |
| "eval_runtime": 149.1268, | |
| "eval_samples_per_second": 3.353, | |
| "eval_steps_per_second": 0.422, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1875, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.595221717180416e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |