| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04552697473252902, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009105394946505805, | |
| "eval_loss": 6.645350456237793, | |
| "eval_runtime": 37.1629, | |
| "eval_samples_per_second": 12.459, | |
| "eval_steps_per_second": 6.243, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004552697473252903, | |
| "grad_norm": 18.139001846313477, | |
| "learning_rate": 5e-05, | |
| "loss": 6.5373, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009105394946505805, | |
| "grad_norm": 17.27703857421875, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4934, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009105394946505805, | |
| "eval_loss": 3.804079532623291, | |
| "eval_runtime": 37.3375, | |
| "eval_samples_per_second": 12.4, | |
| "eval_steps_per_second": 6.214, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013658092419758707, | |
| "grad_norm": 13.822649955749512, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.1006, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01821078989301161, | |
| "grad_norm": 10.816100120544434, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5895, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01821078989301161, | |
| "eval_loss": 2.150548219680786, | |
| "eval_runtime": 37.3883, | |
| "eval_samples_per_second": 12.384, | |
| "eval_steps_per_second": 6.205, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02276348736626451, | |
| "grad_norm": 8.916280746459961, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.2521, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027316184839517414, | |
| "grad_norm": 11.48447036743164, | |
| "learning_rate": 5e-05, | |
| "loss": 2.416, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027316184839517414, | |
| "eval_loss": 1.9078246355056763, | |
| "eval_runtime": 37.4007, | |
| "eval_samples_per_second": 12.379, | |
| "eval_steps_per_second": 6.203, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03186888231277032, | |
| "grad_norm": 8.533246040344238, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6025, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03642157978602322, | |
| "grad_norm": 8.27290153503418, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.9629, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03642157978602322, | |
| "eval_loss": 1.8377580642700195, | |
| "eval_runtime": 37.3981, | |
| "eval_samples_per_second": 12.38, | |
| "eval_steps_per_second": 6.204, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04097427725927612, | |
| "grad_norm": 10.21114444732666, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7723, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04552697473252902, | |
| "grad_norm": 8.158187866210938, | |
| "learning_rate": 0.0, | |
| "loss": 1.9387, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04552697473252902, | |
| "eval_loss": 1.8228884935379028, | |
| "eval_runtime": 37.2908, | |
| "eval_samples_per_second": 12.416, | |
| "eval_steps_per_second": 6.221, | |
| "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": 9555457081344000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |