| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 940, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5369, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.7679553031921387, | |
| "eval_runtime": 21.844, | |
| "eval_samples_per_second": 9.156, | |
| "eval_steps_per_second": 1.144, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4721, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.7605249881744385, | |
| "eval_runtime": 20.3138, | |
| "eval_samples_per_second": 9.846, | |
| "eval_steps_per_second": 1.231, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4e-05, | |
| "loss": 3.4243, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.6854496002197266, | |
| "eval_runtime": 20.7618, | |
| "eval_samples_per_second": 9.633, | |
| "eval_steps_per_second": 1.204, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2e-05, | |
| "loss": 3.3027, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.6660890579223633, | |
| "eval_runtime": 20.6653, | |
| "eval_samples_per_second": 9.678, | |
| "eval_steps_per_second": 1.21, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 3.2875, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.6691887378692627, | |
| "eval_runtime": 20.1586, | |
| "eval_samples_per_second": 9.921, | |
| "eval_steps_per_second": 1.24, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4e-05, | |
| "loss": 3.2959, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.6477155685424805, | |
| "eval_runtime": 21.1835, | |
| "eval_samples_per_second": 9.441, | |
| "eval_steps_per_second": 1.18, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3e-05, | |
| "loss": 3.2286, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.6884500980377197, | |
| "eval_runtime": 20.3071, | |
| "eval_samples_per_second": 9.849, | |
| "eval_steps_per_second": 1.231, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2e-05, | |
| "loss": 3.1364, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.6582536697387695, | |
| "eval_runtime": 21.3174, | |
| "eval_samples_per_second": 9.382, | |
| "eval_steps_per_second": 1.173, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0872, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.666731595993042, | |
| "eval_runtime": 20.761, | |
| "eval_samples_per_second": 9.633, | |
| "eval_steps_per_second": 1.204, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 3.0935, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.616997718811035, | |
| "eval_runtime": 21.3962, | |
| "eval_samples_per_second": 9.347, | |
| "eval_steps_per_second": 1.168, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 940, | |
| "total_flos": 2.2901801877504e+17, | |
| "train_loss": 1.5841756617769283, | |
| "train_runtime": 646.9821, | |
| "train_samples_per_second": 11.592, | |
| "train_steps_per_second": 1.453 | |
| } | |
| ], | |
| "max_steps": 940, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.2901801877504e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |