| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9822294022617124, | |
| "eval_steps": 500, | |
| "global_step": 19, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1306, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 4.2147, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 3.8763, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.8022, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 2.038, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 2.2407, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.0329, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 2.0397, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 1.7539, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7279, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.9929, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 1.6477, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.7115, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 1.6787, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 1.6404, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.8626, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 1.8307, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 1.8578, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0, | |
| "loss": 1.7844, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "step": 19, | |
| "total_flos": 1010043695104.0, | |
| "train_loss": 2.2559843188837956, | |
| "train_runtime": 698.3551, | |
| "train_samples_per_second": 0.886, | |
| "train_steps_per_second": 0.027 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 19, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50000, | |
| "total_flos": 1010043695104.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |