| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023507287259050307, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004701457451810061, | |
| "eval_loss": 10.373299598693848, | |
| "eval_runtime": 2.4626, | |
| "eval_samples_per_second": 363.85, | |
| "eval_steps_per_second": 181.925, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004701457451810061, | |
| "grad_norm": 0.03970923647284508, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 10.3716, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0061118946873530795, | |
| "eval_loss": 10.37249755859375, | |
| "eval_runtime": 2.4308, | |
| "eval_samples_per_second": 368.601, | |
| "eval_steps_per_second": 184.301, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009402914903620122, | |
| "grad_norm": 0.034153059124946594, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 10.3739, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012223789374706159, | |
| "eval_loss": 10.371625900268555, | |
| "eval_runtime": 2.5027, | |
| "eval_samples_per_second": 358.019, | |
| "eval_steps_per_second": 179.009, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.014104372355430184, | |
| "grad_norm": 0.0335276760160923, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 10.3736, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018335684062059238, | |
| "eval_loss": 10.371171951293945, | |
| "eval_runtime": 2.5173, | |
| "eval_samples_per_second": 355.933, | |
| "eval_steps_per_second": 177.966, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018805829807240243, | |
| "grad_norm": 0.034342970699071884, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 10.3721, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023507287259050307, | |
| "grad_norm": 0.0256264079362154, | |
| "learning_rate": 0.0, | |
| "loss": 10.3734, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 740294492160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |