| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9748106591865358, | |
| "global_step": 2200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.765037593984963e-05, | |
| "loss": 12.2573, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 2.7165932655334473, | |
| "eval_runtime": 138.6905, | |
| "eval_samples_per_second": 13.483, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.295112781954887e-05, | |
| "loss": 2.6565, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 2.7028679847717285, | |
| "eval_runtime": 135.8765, | |
| "eval_samples_per_second": 13.762, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3.825187969924812e-05, | |
| "loss": 2.6054, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 2.677929162979126, | |
| "eval_runtime": 138.76, | |
| "eval_samples_per_second": 13.477, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.355263157894737e-05, | |
| "loss": 2.6296, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 2.667823553085327, | |
| "eval_runtime": 138.8745, | |
| "eval_samples_per_second": 13.465, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.8853383458646617e-05, | |
| "loss": 2.6148, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 2.6645262241363525, | |
| "eval_runtime": 138.612, | |
| "eval_samples_per_second": 13.491, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 2.4154135338345866e-05, | |
| "loss": 2.5843, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 2.6597423553466797, | |
| "eval_runtime": 138.5965, | |
| "eval_samples_per_second": 13.492, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.9454887218045115e-05, | |
| "loss": 2.5548, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 2.653554677963257, | |
| "eval_runtime": 138.5895, | |
| "eval_samples_per_second": 13.493, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.4755639097744361e-05, | |
| "loss": 2.5588, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 2.6523187160491943, | |
| "eval_runtime": 138.5665, | |
| "eval_samples_per_second": 13.495, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.005639097744361e-05, | |
| "loss": 2.5814, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 2.64888858795166, | |
| "eval_runtime": 138.6375, | |
| "eval_samples_per_second": 13.488, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 2.569, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 2.6475982666015625, | |
| "eval_runtime": 138.5945, | |
| "eval_samples_per_second": 13.493, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.578947368421053e-07, | |
| "loss": 2.5401, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 2.6439733505249023, | |
| "eval_runtime": 138.082, | |
| "eval_samples_per_second": 13.543, | |
| "step": 2200 | |
| } | |
| ], | |
| "max_steps": 2228, | |
| "num_train_epochs": 2, | |
| "total_flos": 2.691387690319872e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |