| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 351, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 1.4181480407714844, | |
| "learning_rate": 9.992791852820709e-06, | |
| "loss": 0.665, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 1.27070951461792, | |
| "learning_rate": 9.971188194237141e-06, | |
| "loss": 0.473, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 1.1482155323028564, | |
| "learning_rate": 9.935251313189564e-06, | |
| "loss": 0.449, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 1.2000395059585571, | |
| "learning_rate": 9.885084825009085e-06, | |
| "loss": 0.4306, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.42735042735042733, | |
| "grad_norm": 1.1685457229614258, | |
| "learning_rate": 9.820833372667813e-06, | |
| "loss": 0.4141, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 1.1243082284927368, | |
| "learning_rate": 9.742682209735727e-06, | |
| "loss": 0.4107, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5982905982905983, | |
| "grad_norm": 1.0574721097946167, | |
| "learning_rate": 9.650856666246693e-06, | |
| "loss": 0.4056, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 1.2004579305648804, | |
| "learning_rate": 9.54562149901362e-06, | |
| "loss": 0.4012, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.9274908304214478, | |
| "learning_rate": 9.427280128266049e-06, | |
| "loss": 0.3855, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 1.248368263244629, | |
| "learning_rate": 9.296173762811084e-06, | |
| "loss": 0.3987, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9401709401709402, | |
| "grad_norm": 1.0070111751556396, | |
| "learning_rate": 9.152680416240059e-06, | |
| "loss": 0.3871, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 0.8592380881309509, | |
| "learning_rate": 8.997213817017508e-06, | |
| "loss": 0.3453, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 1.1061818599700928, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 0.26, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.1965811965811965, | |
| "grad_norm": 1.1157325506210327, | |
| "learning_rate": 8.652187091988516e-06, | |
| "loss": 0.2432, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.282051282051282, | |
| "grad_norm": 1.1478718519210815, | |
| "learning_rate": 8.463621767547998e-06, | |
| "loss": 0.2481, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.3675213675213675, | |
| "grad_norm": 1.0965734720230103, | |
| "learning_rate": 8.265069924917925e-06, | |
| "loss": 0.2392, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.452991452991453, | |
| "grad_norm": 1.0359482765197754, | |
| "learning_rate": 8.057104040460062e-06, | |
| "loss": 0.2345, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 1.0444822311401367, | |
| "learning_rate": 7.84032373365578e-06, | |
| "loss": 0.2372, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.623931623931624, | |
| "grad_norm": 1.166808009147644, | |
| "learning_rate": 7.615354038247889e-06, | |
| "loss": 0.2373, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7094017094017095, | |
| "grad_norm": 1.1571974754333496, | |
| "learning_rate": 7.382843600106539e-06, | |
| "loss": 0.2404, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.7948717948717947, | |
| "grad_norm": 1.1317440271377563, | |
| "learning_rate": 7.143462807015271e-06, | |
| "loss": 0.2394, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.8803418803418803, | |
| "grad_norm": 1.1420925855636597, | |
| "learning_rate": 6.897901855769483e-06, | |
| "loss": 0.2341, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.965811965811966, | |
| "grad_norm": 1.0969715118408203, | |
| "learning_rate": 6.646868762160399e-06, | |
| "loss": 0.2363, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 1.1839579343795776, | |
| "learning_rate": 6.391087319582264e-06, | |
| "loss": 0.1572, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.1367521367521367, | |
| "grad_norm": 1.3952598571777344, | |
| "learning_rate": 6.131295012148613e-06, | |
| "loss": 0.0963, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 1.2655587196350098, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 0.0934, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 1.3720885515213013, | |
| "learning_rate": 5.6026834012766155e-06, | |
| "loss": 0.0897, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.393162393162393, | |
| "grad_norm": 1.4065742492675781, | |
| "learning_rate": 5.335388221955012e-06, | |
| "loss": 0.0919, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.4786324786324787, | |
| "grad_norm": 1.3926897048950195, | |
| "learning_rate": 5.067126031566988e-06, | |
| "loss": 0.0892, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 1.1955878734588623, | |
| "learning_rate": 4.798670299452926e-06, | |
| "loss": 0.0877, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.6495726495726495, | |
| "grad_norm": 1.3691728115081787, | |
| "learning_rate": 4.530795052984104e-06, | |
| "loss": 0.0901, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.735042735042735, | |
| "grad_norm": 1.1833082437515259, | |
| "learning_rate": 4.264272645841419e-06, | |
| "loss": 0.0891, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.8205128205128203, | |
| "grad_norm": 1.3318713903427124, | |
| "learning_rate": 3.999871531119779e-06, | |
| "loss": 0.0846, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.905982905982906, | |
| "grad_norm": 1.2540022134780884, | |
| "learning_rate": 3.7383540456788915e-06, | |
| "loss": 0.0856, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.9914529914529915, | |
| "grad_norm": 1.1811027526855469, | |
| "learning_rate": 3.480474212128766e-06, | |
| "loss": 0.081, | |
| "step": 350 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 585, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 50.0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.398524460433408e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |