| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006216160774782279, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2432321549564558e-05, | |
| "eval_loss": 0.8783668875694275, | |
| "eval_runtime": 986.9906, | |
| "eval_samples_per_second": 34.314, | |
| "eval_steps_per_second": 17.157, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.216160774782279e-05, | |
| "grad_norm": 3.6310617923736572, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8162, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00012432321549564557, | |
| "grad_norm": 3.315478801727295, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5446, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00012432321549564557, | |
| "eval_loss": 0.19229428470134735, | |
| "eval_runtime": 985.0624, | |
| "eval_samples_per_second": 34.382, | |
| "eval_steps_per_second": 17.191, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00018648482324346838, | |
| "grad_norm": 0.5569245219230652, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0472, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00024864643099129115, | |
| "grad_norm": 0.08528528362512589, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1099, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00024864643099129115, | |
| "eval_loss": 0.04116155579686165, | |
| "eval_runtime": 980.8914, | |
| "eval_samples_per_second": 34.528, | |
| "eval_steps_per_second": 17.264, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00031080803873911395, | |
| "grad_norm": 0.5110355019569397, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.013, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00037296964648693675, | |
| "grad_norm": 0.6540066599845886, | |
| "learning_rate": 5e-05, | |
| "loss": 0.042, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00037296964648693675, | |
| "eval_loss": 0.03175438195466995, | |
| "eval_runtime": 978.2167, | |
| "eval_samples_per_second": 34.622, | |
| "eval_steps_per_second": 17.311, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00043513125423475955, | |
| "grad_norm": 0.07520467787981033, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.004, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0004972928619825823, | |
| "grad_norm": 3.0061545372009277, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.054, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0004972928619825823, | |
| "eval_loss": 0.03129574656486511, | |
| "eval_runtime": 986.8939, | |
| "eval_samples_per_second": 34.318, | |
| "eval_steps_per_second": 17.159, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0005594544697304051, | |
| "grad_norm": 0.04781950265169144, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0012, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0006216160774782279, | |
| "grad_norm": 0.04722150042653084, | |
| "learning_rate": 0.0, | |
| "loss": 0.0658, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0006216160774782279, | |
| "eval_loss": 0.02980978600680828, | |
| "eval_runtime": 987.4836, | |
| "eval_samples_per_second": 34.297, | |
| "eval_steps_per_second": 17.149, | |
| "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": 1268877593935872.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |