| { | |
| "best_metric": 2.9845471382141113, | |
| "best_model_checkpoint": "output/cardi-b/checkpoint-114", | |
| "epoch": 2.0, | |
| "global_step": 114, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00013469952948681868, | |
| "loss": 3.9273, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001273804022850966, | |
| "loss": 3.6212, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00011577618287734484, | |
| "loss": 3.5805, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00010073281903200561, | |
| "loss": 3.7011, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.334697219847626e-05, | |
| "loss": 3.4198, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.488607087104036e-05, | |
| "loss": 3.712, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.6695915032671784e-05, | |
| "loss": 3.5622, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.0102567316140575e-05, | |
| "loss": 3.2665, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.6315683018244145e-05, | |
| "loss": 3.4291, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.340326210572357e-06, | |
| "loss": 3.3414, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.037005536513067e-07, | |
| "loss": 3.2621, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.3664300441741943, | |
| "eval_runtime": 1.5982, | |
| "eval_samples_per_second": 44.424, | |
| "eval_steps_per_second": 5.631, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.35614586573241e-07, | |
| "loss": 3.234, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.5610987761461805e-06, | |
| "loss": 3.3216, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.6868286569304916e-05, | |
| "loss": 3.2467, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.1079356352801514e-05, | |
| "loss": 3.3662, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 4.8121883965283725e-05, | |
| "loss": 3.3484, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 6.670977211354408e-05, | |
| "loss": 3.2623, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 8.54403044178588e-05, | |
| "loss": 3.0856, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00010290000000000001, | |
| "loss": 3.2992, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00011777128040335575, | |
| "loss": 3.1025, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00012893189933276512, | |
| "loss": 3.2896, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00013553963184824208, | |
| "loss": 3.228, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.9845471382141113, | |
| "eval_runtime": 3.4603, | |
| "eval_samples_per_second": 22.252, | |
| "eval_steps_per_second": 2.89, | |
| "step": 114 | |
| } | |
| ], | |
| "max_steps": 114, | |
| "num_train_epochs": 2, | |
| "total_flos": 117581414400000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |