| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 1484, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.95e-05, | |
| "loss": 6.3737, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 5.842774868011475, | |
| "eval_runtime": 3.9529, | |
| "eval_samples_per_second": 171.015, | |
| "eval_steps_per_second": 21.503, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.900000000000001e-05, | |
| "loss": 5.5296, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 4.859792232513428, | |
| "eval_runtime": 4.2848, | |
| "eval_samples_per_second": 157.766, | |
| "eval_steps_per_second": 19.837, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.850000000000001e-05, | |
| "loss": 4.6838, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 4.013933181762695, | |
| "eval_runtime": 4.1662, | |
| "eval_samples_per_second": 162.258, | |
| "eval_steps_per_second": 20.402, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.8e-05, | |
| "loss": 3.9438, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 3.277362585067749, | |
| "eval_runtime": 4.2258, | |
| "eval_samples_per_second": 159.97, | |
| "eval_steps_per_second": 20.115, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.75e-05, | |
| "loss": 3.2751, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.62673282623291, | |
| "eval_runtime": 4.5502, | |
| "eval_samples_per_second": 148.565, | |
| "eval_steps_per_second": 18.68, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9.7e-05, | |
| "loss": 2.6863, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.0860772132873535, | |
| "eval_runtime": 4.2538, | |
| "eval_samples_per_second": 158.917, | |
| "eval_steps_per_second": 19.982, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.65e-05, | |
| "loss": 2.193, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.6755822896957397, | |
| "eval_runtime": 4.2558, | |
| "eval_samples_per_second": 158.842, | |
| "eval_steps_per_second": 19.973, | |
| "step": 1484 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 42400, | |
| "num_train_epochs": 200, | |
| "save_steps": 500, | |
| "total_flos": 2164845934111632.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |