| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 290, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.724137931034483e-06, | |
| "loss": 13.7082, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 3.448275862068966e-06, | |
| "loss": 13.6049, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.999083215558211e-06, | |
| "loss": 13.2358, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.88988035667903e-06, | |
| "loss": 12.582, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.606455184041623e-06, | |
| "loss": 11.3961, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.169469396971739e-06, | |
| "loss": 10.3617, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 3.6107792658847597e-06, | |
| "loss": 9.6083, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.971113309695796e-06, | |
| "loss": 9.3376, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.2971031861814225e-06, | |
| "loss": 8.9473, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.6378842434300746e-06, | |
| "loss": 8.776, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.041513552231265e-06, | |
| "loss": 8.6731, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.51466544896021e-07, | |
| "loss": 8.6288, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.0346765559094566e-07, | |
| "loss": 8.7519, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.2886008552983064e-08, | |
| "loss": 8.7899, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 290, | |
| "total_flos": 8592765192732672.0, | |
| "train_loss": 10.40311779153758, | |
| "train_runtime": 167.4524, | |
| "train_samples_per_second": 3.458, | |
| "train_steps_per_second": 1.732 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 290, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 8592765192732672.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |