| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.016544513012259485, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "eval_accuracy": 0.3502469255350053, | |
| "eval_loss": 3.632826328277588, | |
| "eval_runtime": 398.6921, | |
| "eval_samples_per_second": 1.279, | |
| "eval_steps_per_second": 0.321, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_accuracy": 0.3616211331782439, | |
| "eval_loss": 3.540499210357666, | |
| "eval_runtime": 408.0902, | |
| "eval_samples_per_second": 1.25, | |
| "eval_steps_per_second": 0.314, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_accuracy": 0.3631109076341994, | |
| "eval_loss": 3.538304090499878, | |
| "eval_runtime": 413.5149, | |
| "eval_samples_per_second": 1.233, | |
| "eval_steps_per_second": 0.31, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.3691925896000462, | |
| "eval_loss": 3.498488187789917, | |
| "eval_runtime": 416.6621, | |
| "eval_samples_per_second": 1.224, | |
| "eval_steps_per_second": 0.307, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.8307032585144043, | |
| "learning_rate": 4.958638717469351e-05, | |
| "loss": 3.5814, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.3655637771728712, | |
| "eval_loss": 3.510744333267212, | |
| "eval_runtime": 417.8436, | |
| "eval_samples_per_second": 1.221, | |
| "eval_steps_per_second": 0.306, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.37279766365016237, | |
| "eval_loss": 3.448606014251709, | |
| "eval_runtime": 418.2361, | |
| "eval_samples_per_second": 1.219, | |
| "eval_steps_per_second": 0.306, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.37432385775117966, | |
| "eval_loss": 3.437483072280884, | |
| "eval_runtime": 424.8484, | |
| "eval_samples_per_second": 1.2, | |
| "eval_steps_per_second": 0.301, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.37553490882454993, | |
| "eval_loss": 3.4409470558166504, | |
| "eval_runtime": 426.0459, | |
| "eval_samples_per_second": 1.197, | |
| "eval_steps_per_second": 0.3, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.37346273380746275, | |
| "eval_loss": 3.4459047317504883, | |
| "eval_runtime": 426.9882, | |
| "eval_samples_per_second": 1.194, | |
| "eval_steps_per_second": 0.3, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.9651877880096436, | |
| "learning_rate": 4.917277434938703e-05, | |
| "loss": 3.462, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.37652163895395724, | |
| "eval_loss": 3.4321560859680176, | |
| "eval_runtime": 427.9304, | |
| "eval_samples_per_second": 1.192, | |
| "eval_steps_per_second": 0.299, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "step": 1000, | |
| "total_flos": 4505964380160000.0, | |
| "train_loss": 3.5216834716796876, | |
| "train_runtime": 13589.9527, | |
| "train_samples_per_second": 17.79, | |
| "train_steps_per_second": 4.448 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 60443, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "total_flos": 4505964380160000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |