| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10922992900054615, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002184598580010923, | |
| "eval_loss": 7.941990852355957, | |
| "eval_runtime": 14.6223, | |
| "eval_samples_per_second": 13.199, | |
| "eval_steps_per_second": 6.634, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010922992900054615, | |
| "grad_norm": 25.455711364746094, | |
| "learning_rate": 5e-05, | |
| "loss": 7.9324, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02184598580010923, | |
| "grad_norm": 22.484371185302734, | |
| "learning_rate": 0.0001, | |
| "loss": 5.7697, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02184598580010923, | |
| "eval_loss": 3.301812171936035, | |
| "eval_runtime": 14.8432, | |
| "eval_samples_per_second": 13.003, | |
| "eval_steps_per_second": 6.535, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03276897870016385, | |
| "grad_norm": 17.777523040771484, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1332, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04369197160021846, | |
| "grad_norm": 9.074566841125488, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9946, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04369197160021846, | |
| "eval_loss": 0.9706413149833679, | |
| "eval_runtime": 14.9005, | |
| "eval_samples_per_second": 12.953, | |
| "eval_steps_per_second": 6.51, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054614964500273075, | |
| "grad_norm": 16.745901107788086, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.95, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0655379574003277, | |
| "grad_norm": 9.343716621398926, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8587, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0655379574003277, | |
| "eval_loss": 0.9797313213348389, | |
| "eval_runtime": 14.9045, | |
| "eval_samples_per_second": 12.949, | |
| "eval_steps_per_second": 6.508, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0764609503003823, | |
| "grad_norm": 5.940131664276123, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8317, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08738394320043692, | |
| "grad_norm": 14.620291709899902, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9143, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08738394320043692, | |
| "eval_loss": 0.8667392134666443, | |
| "eval_runtime": 15.046, | |
| "eval_samples_per_second": 12.827, | |
| "eval_steps_per_second": 6.447, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09830693610049153, | |
| "grad_norm": 21.33104133605957, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8446, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10922992900054615, | |
| "grad_norm": 14.127695083618164, | |
| "learning_rate": 0.0, | |
| "loss": 0.8292, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10922992900054615, | |
| "eval_loss": 0.8796916604042053, | |
| "eval_runtime": 14.9708, | |
| "eval_samples_per_second": 12.892, | |
| "eval_steps_per_second": 6.479, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 9603234366750720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |