| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "global_step": 640, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.49765625e-05, | |
| "loss": 3.2919, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.2656250000000001e-05, | |
| "loss": 3.4091, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.34718954248366013, | |
| "eval_loss": 3.7237555980682373, | |
| "eval_runtime": 0.6878, | |
| "eval_samples_per_second": 87.234, | |
| "eval_steps_per_second": 7.27, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.03125e-05, | |
| "loss": 3.3483, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 7.96875e-06, | |
| "loss": 3.2338, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.344640522875817, | |
| "eval_loss": 3.739302396774292, | |
| "eval_runtime": 0.6495, | |
| "eval_samples_per_second": 92.384, | |
| "eval_steps_per_second": 7.699, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.625e-06, | |
| "loss": 3.1684, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3443790849673203, | |
| "eval_loss": 3.7517521381378174, | |
| "eval_runtime": 0.6571, | |
| "eval_samples_per_second": 91.306, | |
| "eval_steps_per_second": 7.609, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.28125e-06, | |
| "loss": 3.1497, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 9.375e-07, | |
| "loss": 3.0989, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3435947712418301, | |
| "eval_loss": 3.7601635456085205, | |
| "eval_runtime": 0.6542, | |
| "eval_samples_per_second": 91.721, | |
| "eval_steps_per_second": 7.643, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 640, | |
| "total_flos": 1783105333493760.0, | |
| "train_loss": 3.228607414290309, | |
| "train_runtime": 136.9037, | |
| "train_samples_per_second": 28.049, | |
| "train_steps_per_second": 4.675 | |
| } | |
| ], | |
| "max_steps": 640, | |
| "num_train_epochs": 4, | |
| "total_flos": 1783105333493760.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |