| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 550, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.1882656350741457, | |
| "eval_loss": 5.243511199951172, | |
| "eval_runtime": 4.8686, | |
| "eval_samples_per_second": 48.268, | |
| "eval_steps_per_second": 6.162, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.2259354006780225, | |
| "eval_loss": 4.6670308113098145, | |
| "eval_runtime": 4.8738, | |
| "eval_samples_per_second": 48.217, | |
| "eval_steps_per_second": 6.155, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_accuracy": 0.24813543811484787, | |
| "eval_loss": 4.436723709106445, | |
| "eval_runtime": 4.8864, | |
| "eval_samples_per_second": 48.093, | |
| "eval_steps_per_second": 6.14, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_accuracy": 0.25969925750296374, | |
| "eval_loss": 4.3258056640625, | |
| "eval_runtime": 4.8712, | |
| "eval_samples_per_second": 48.243, | |
| "eval_steps_per_second": 6.159, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.772727272727273e-05, | |
| "loss": 6.175, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_accuracy": 0.26481562363511574, | |
| "eval_loss": 4.270518779754639, | |
| "eval_runtime": 4.8757, | |
| "eval_samples_per_second": 48.198, | |
| "eval_steps_per_second": 6.153, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_accuracy": 0.26965745304798155, | |
| "eval_loss": 4.2317938804626465, | |
| "eval_runtime": 4.8861, | |
| "eval_samples_per_second": 48.096, | |
| "eval_steps_per_second": 6.14, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_accuracy": 0.2718995029221522, | |
| "eval_loss": 4.208972454071045, | |
| "eval_runtime": 4.8935, | |
| "eval_samples_per_second": 48.023, | |
| "eval_steps_per_second": 6.131, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_accuracy": 0.27399596514215596, | |
| "eval_loss": 4.191540718078613, | |
| "eval_runtime": 4.8923, | |
| "eval_samples_per_second": 48.035, | |
| "eval_steps_per_second": 6.132, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_accuracy": 0.2745658368170379, | |
| "eval_loss": 4.18229866027832, | |
| "eval_runtime": 4.8912, | |
| "eval_samples_per_second": 48.045, | |
| "eval_steps_per_second": 6.133, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 5e-06, | |
| "loss": 3.9191, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "eval_accuracy": 0.2756639836941827, | |
| "eval_loss": 4.17605447769165, | |
| "eval_runtime": 4.8985, | |
| "eval_samples_per_second": 47.974, | |
| "eval_steps_per_second": 6.124, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.27604251159501675, | |
| "eval_loss": 4.173768997192383, | |
| "eval_runtime": 4.8913, | |
| "eval_samples_per_second": 48.044, | |
| "eval_steps_per_second": 6.133, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 550, | |
| "total_flos": 4585675161600000.0, | |
| "train_loss": 4.937346829501065, | |
| "train_runtime": 481.6631, | |
| "train_samples_per_second": 18.218, | |
| "train_steps_per_second": 1.142 | |
| } | |
| ], | |
| "max_steps": 550, | |
| "num_train_epochs": 5, | |
| "total_flos": 4585675161600000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |