| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.88, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 10.590332717346035, | |
| "learning_rate": 5e-07, | |
| "loss": 1.7036, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 7.214343866416259, | |
| "learning_rate": 9.157348061512726e-07, | |
| "loss": 1.7014, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.9007039070129395, | |
| "eval_runtime": 5.4927, | |
| "eval_samples_per_second": 10.924, | |
| "eval_steps_per_second": 0.728, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 5.81180350509424, | |
| "learning_rate": 5e-07, | |
| "loss": 1.6286, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 1.8676100969314575, | |
| "eval_runtime": 5.3411, | |
| "eval_samples_per_second": 11.234, | |
| "eval_steps_per_second": 0.749, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 4.832124501533971, | |
| "learning_rate": 8.426519384872732e-08, | |
| "loss": 1.5573, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 1.859337568283081, | |
| "eval_runtime": 5.2859, | |
| "eval_samples_per_second": 11.351, | |
| "eval_steps_per_second": 0.757, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "step": 18, | |
| "total_flos": 3716488888320.0, | |
| "train_loss": 1.6118529703882005, | |
| "train_runtime": 323.9524, | |
| "train_samples_per_second": 3.612, | |
| "train_steps_per_second": 0.056 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 18, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3716488888320.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |