| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5263157894736842, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010526315789473684, | |
| "eval_loss": 5.782024383544922, | |
| "eval_runtime": 1.2678, | |
| "eval_samples_per_second": 31.552, | |
| "eval_steps_per_second": 15.776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 22.532424926757812, | |
| "learning_rate": 5e-05, | |
| "loss": 5.6649, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 6.581038475036621, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9436, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "eval_loss": 4.780341148376465, | |
| "eval_runtime": 1.3178, | |
| "eval_samples_per_second": 30.354, | |
| "eval_steps_per_second": 15.177, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 7.639489650726318, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.4268, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 4.636980056762695, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2459, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "eval_loss": 3.265232801437378, | |
| "eval_runtime": 1.3174, | |
| "eval_samples_per_second": 30.362, | |
| "eval_steps_per_second": 15.181, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 9.490302085876465, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.0356, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 5.229157447814941, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7367, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "eval_loss": 2.613542079925537, | |
| "eval_runtime": 1.3555, | |
| "eval_samples_per_second": 29.51, | |
| "eval_steps_per_second": 14.755, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 8.166553497314453, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.3516, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 4.274360179901123, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3017, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "eval_loss": 2.4747276306152344, | |
| "eval_runtime": 1.3146, | |
| "eval_samples_per_second": 30.428, | |
| "eval_steps_per_second": 15.214, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 4.358697414398193, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.3813, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 4.9004974365234375, | |
| "learning_rate": 0.0, | |
| "loss": 2.4422, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "eval_loss": 2.4381790161132812, | |
| "eval_runtime": 1.3079, | |
| "eval_samples_per_second": 30.582, | |
| "eval_steps_per_second": 15.291, | |
| "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": 1278959891251200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |