| { | |
| "best_metric": 3.4337549209594727, | |
| "best_model_checkpoint": "output/yung-lean/checkpoint-144", | |
| "epoch": 3.0, | |
| "global_step": 144, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013355940688336427, | |
| "loss": 3.9118, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00012302403914397873, | |
| "loss": 3.761, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010671211798514472, | |
| "loss": 3.6532, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.635498649403293e-05, | |
| "loss": 3.4509, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.411334533481218e-05, | |
| "loss": 3.5511, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 3.6085, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.3368877084135277e-05, | |
| "loss": 3.2754, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.190657300387505e-06, | |
| "loss": 3.5324, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3181297643383925e-06, | |
| "loss": 3.2119, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.5056326389312744, | |
| "eval_runtime": 0.9143, | |
| "eval_samples_per_second": 76.563, | |
| "eval_steps_per_second": 9.844, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.868825097566078e-07, | |
| "loss": 3.5151, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.074529930857578e-06, | |
| "loss": 3.3697, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.009247481060283e-05, | |
| "loss": 3.4438, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.825899585097651e-05, | |
| "loss": 3.1986, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.964590321370446e-05, | |
| "loss": 3.0037, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.19831960903064e-05, | |
| "loss": 3.336, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00010290000000000001, | |
| "loss": 3.4818, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012017621079305782, | |
| "loss": 3.2708, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00013197813593027427, | |
| "loss": 3.0245, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0001370531221341682, | |
| "loss": 3.1731, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.4461593627929688, | |
| "eval_runtime": 0.9154, | |
| "eval_samples_per_second": 76.473, | |
| "eval_steps_per_second": 9.832, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.00013486251168343008, | |
| "loss": 3.1258, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0001256388154039546, | |
| "loss": 3.0698, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.00011036103402999826, | |
| "loss": 2.9638, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.065074731979686e-05, | |
| "loss": 2.9622, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.860000000000001e-05, | |
| "loss": 2.9506, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.6549252680203134e-05, | |
| "loss": 2.9087, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.683896597000177e-05, | |
| "loss": 2.9057, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.1561184596045404e-05, | |
| "loss": 2.9869, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 2.337488316569914e-06, | |
| "loss": 2.9926, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 3.4337549209594727, | |
| "eval_runtime": 0.9131, | |
| "eval_samples_per_second": 76.662, | |
| "eval_steps_per_second": 9.857, | |
| "step": 144 | |
| } | |
| ], | |
| "max_steps": 2880, | |
| "num_train_epochs": 60, | |
| "total_flos": 149328396288000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |