| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.977464023893565, | |
| "global_step": 3600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.325278305729025e-05, | |
| "loss": 0.5728, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.762572169303894, | |
| "eval_runtime": 157.3465, | |
| "eval_samples_per_second": 5.199, | |
| "eval_steps_per_second": 5.199, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.6464838446918274e-05, | |
| "loss": 1.1434, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.572243571281433, | |
| "eval_runtime": 167.1313, | |
| "eval_samples_per_second": 4.894, | |
| "eval_steps_per_second": 4.894, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.969046972576704e-05, | |
| "loss": 1.1231, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.5563775300979614, | |
| "eval_runtime": 168.524, | |
| "eval_samples_per_second": 4.854, | |
| "eval_steps_per_second": 4.854, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.290252511539506e-05, | |
| "loss": 1.0814, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.530091643333435, | |
| "eval_runtime": 160.6191, | |
| "eval_samples_per_second": 5.093, | |
| "eval_steps_per_second": 5.093, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.611458050502308e-05, | |
| "loss": 1.0611, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.4997280836105347, | |
| "eval_runtime": 164.048, | |
| "eval_samples_per_second": 4.986, | |
| "eval_steps_per_second": 4.986, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.3266358946511e-06, | |
| "loss": 1.0328, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.4869426488876343, | |
| "eval_runtime": 169.4258, | |
| "eval_samples_per_second": 4.828, | |
| "eval_steps_per_second": 4.828, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.5386912842791203e-06, | |
| "loss": 1.0173, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.4691505432128906, | |
| "eval_runtime": 155.7447, | |
| "eval_samples_per_second": 5.252, | |
| "eval_steps_per_second": 5.252, | |
| "step": 3500 | |
| } | |
| ], | |
| "max_steps": 3683, | |
| "num_train_epochs": 1, | |
| "total_flos": 7.77658992427008e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |