| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.125, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 2.1368, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.6266, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 3e-06, | |
| "loss": 1.1649, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.9517, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8344, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 6e-06, | |
| "loss": 0.7346, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7e-06, | |
| "loss": 0.633, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.5706, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9e-06, | |
| "loss": 0.5311, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5041, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 9e-06, | |
| "loss": 0.4821, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.4497, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 7e-06, | |
| "loss": 0.4379, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 6e-06, | |
| "loss": 0.3421, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3355, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.3401, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3e-06, | |
| "loss": 0.3302, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.3229, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.3128, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0, | |
| "loss": 0.2841, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "step": 500, | |
| "total_flos": 1.845734503366656e+19, | |
| "train_loss": 0.6662537975311279, | |
| "train_runtime": 10584.1971, | |
| "train_samples_per_second": 6.047, | |
| "train_steps_per_second": 0.047 | |
| } | |
| ], | |
| "max_steps": 500, | |
| "num_train_epochs": 4, | |
| "total_flos": 1.845734503366656e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |