| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9905660377358491, | |
| "eval_steps": 10, | |
| "global_step": 42, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9930094929529506e-05, | |
| "loss": 1.2348, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.827184371610511e-05, | |
| "loss": 1.2258, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.332629679574566e-05, | |
| "loss": 1.2298, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.1997809410095215, | |
| "eval_runtime": 24.4233, | |
| "eval_samples_per_second": 5.282, | |
| "eval_steps_per_second": 1.761, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.5847093477938956e-05, | |
| "loss": 1.2091, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.686825233966061e-05, | |
| "loss": 1.1885, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.1652644872665405, | |
| "eval_runtime": 24.4242, | |
| "eval_samples_per_second": 5.282, | |
| "eval_steps_per_second": 1.761, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.7631120639727393e-05, | |
| "loss": 1.1647, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.412754953531663e-06, | |
| "loss": 1.1674, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.1437482833862305, | |
| "eval_runtime": 24.4259, | |
| "eval_samples_per_second": 5.281, | |
| "eval_steps_per_second": 1.76, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 1.151, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.7922934437178695e-07, | |
| "loss": 1.1425, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.1380583047866821, | |
| "eval_runtime": 24.4167, | |
| "eval_samples_per_second": 5.283, | |
| "eval_steps_per_second": 1.761, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "step": 42, | |
| "total_flos": 6.447644673468006e+16, | |
| "train_loss": 1.1835048993428547, | |
| "train_runtime": 3217.2275, | |
| "train_samples_per_second": 1.58, | |
| "train_steps_per_second": 0.013 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 42, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "total_flos": 6.447644673468006e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |