| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0015492226775215535, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.098445355043107e-05, | |
| "eval_loss": 1.195532202720642, | |
| "eval_runtime": 1454.9398, | |
| "eval_samples_per_second": 9.341, | |
| "eval_steps_per_second": 4.67, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015492226775215535, | |
| "grad_norm": 0.22048205137252808, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2744, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003098445355043107, | |
| "grad_norm": 0.2948167622089386, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1851, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003098445355043107, | |
| "eval_loss": 1.146066427230835, | |
| "eval_runtime": 1458.2994, | |
| "eval_samples_per_second": 9.319, | |
| "eval_steps_per_second": 4.66, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004647668032564661, | |
| "grad_norm": 0.29153722524642944, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1034, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006196890710086214, | |
| "grad_norm": 0.31050845980644226, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0061, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006196890710086214, | |
| "eval_loss": 1.0127846002578735, | |
| "eval_runtime": 1456.8345, | |
| "eval_samples_per_second": 9.328, | |
| "eval_steps_per_second": 4.664, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007746113387607767, | |
| "grad_norm": 0.338260293006897, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0445, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0009295336065129322, | |
| "grad_norm": 0.33603912591934204, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9271, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009295336065129322, | |
| "eval_loss": 0.9617733359336853, | |
| "eval_runtime": 1465.4277, | |
| "eval_samples_per_second": 9.274, | |
| "eval_steps_per_second": 4.637, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0010844558742650874, | |
| "grad_norm": 0.29064711928367615, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9954, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0012393781420172428, | |
| "grad_norm": 0.26686355471611023, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8849, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0012393781420172428, | |
| "eval_loss": 0.9477787017822266, | |
| "eval_runtime": 1466.3979, | |
| "eval_samples_per_second": 9.268, | |
| "eval_steps_per_second": 4.634, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0013943004097693981, | |
| "grad_norm": 0.26942411065101624, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9229, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0015492226775215535, | |
| "grad_norm": 0.3074963688850403, | |
| "learning_rate": 0.0, | |
| "loss": 0.9729, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0015492226775215535, | |
| "eval_loss": 0.9452804327011108, | |
| "eval_runtime": 1463.3929, | |
| "eval_samples_per_second": 9.287, | |
| "eval_steps_per_second": 4.643, | |
| "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": 1.631344694132736e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |