| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0019907826762091516, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.981565352418303e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 586.0966, | |
| "eval_samples_per_second": 18.045, | |
| "eval_steps_per_second": 9.022, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039815653524183034, | |
| "grad_norm": 2.249063730239868, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 12.163, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005176034958143794, | |
| "eval_loss": NaN, | |
| "eval_runtime": 581.5592, | |
| "eval_samples_per_second": 18.186, | |
| "eval_steps_per_second": 9.093, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0007963130704836607, | |
| "grad_norm": 2.475959300994873, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.0534, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010352069916287588, | |
| "eval_loss": NaN, | |
| "eval_runtime": 582.57, | |
| "eval_samples_per_second": 18.154, | |
| "eval_steps_per_second": 9.077, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001194469605725491, | |
| "grad_norm": 3.356778144836426, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 4.097, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015528104874431383, | |
| "eval_loss": NaN, | |
| "eval_runtime": 582.9175, | |
| "eval_samples_per_second": 18.143, | |
| "eval_steps_per_second": 9.072, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0015926261409673213, | |
| "grad_norm": 1.3857320547103882, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 3.0279, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0019907826762091516, | |
| "grad_norm": 1.311830997467041, | |
| "learning_rate": 0.0, | |
| "loss": 4.0459, | |
| "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": 1.5831020863488e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |