| { | |
| "best_metric": 0.1445566862821579, | |
| "best_model_checkpoint": "finetuned-fake-food/checkpoint-200", | |
| "epoch": 20.0, | |
| "eval_steps": 100, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.19071011245250702, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.328, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.38541921973228455, | |
| "eval_runtime": 0.6081, | |
| "eval_samples_per_second": 34.535, | |
| "eval_steps_per_second": 4.934, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 4.4858717918396, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.1729, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "eval_accuracy": 0.9523809523809523, | |
| "eval_loss": 0.1445566862821579, | |
| "eval_runtime": 0.6148, | |
| "eval_samples_per_second": 34.158, | |
| "eval_steps_per_second": 4.88, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.0665096864104271, | |
| "learning_rate": 0.0, | |
| "loss": 0.0508, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9523809523809523, | |
| "eval_loss": 0.2076147198677063, | |
| "eval_runtime": 0.6275, | |
| "eval_samples_per_second": 33.468, | |
| "eval_steps_per_second": 4.781, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 300, | |
| "total_flos": 1.8288109549043712e+17, | |
| "train_loss": 0.18390971183776855, | |
| "train_runtime": 151.0028, | |
| "train_samples_per_second": 15.629, | |
| "train_steps_per_second": 1.987 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 300, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8288109549043712e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |