| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 3495, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08583690987124463, | |
| "grad_norm": 0.13883593678474426, | |
| "learning_rate": 0.0001998960663781063, | |
| "loss": 0.829, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17167381974248927, | |
| "grad_norm": 0.13720104098320007, | |
| "learning_rate": 0.00019906589321760313, | |
| "loss": 0.648, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2575107296137339, | |
| "grad_norm": 0.1670483946800232, | |
| "learning_rate": 0.00019741244594178857, | |
| "loss": 0.587, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.34334763948497854, | |
| "grad_norm": 0.16993218660354614, | |
| "learning_rate": 0.00019494946530743566, | |
| "loss": 0.5547, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4291845493562232, | |
| "grad_norm": 0.16408105194568634, | |
| "learning_rate": 0.00019169741959214142, | |
| "loss": 0.5319, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5150214592274678, | |
| "grad_norm": 0.1872694492340088, | |
| "learning_rate": 0.0001876833344953899, | |
| "loss": 0.5147, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6008583690987125, | |
| "grad_norm": 0.18225158751010895, | |
| "learning_rate": 0.0001829405685450202, | |
| "loss": 0.5009, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6866952789699571, | |
| "grad_norm": 0.1850147843360901, | |
| "learning_rate": 0.00017750853587555535, | |
| "loss": 0.4866, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7725321888412017, | |
| "grad_norm": 0.20939144492149353, | |
| "learning_rate": 0.00017143237868220553, | |
| "loss": 0.4721, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8583690987124464, | |
| "grad_norm": 0.21306931972503662, | |
| "learning_rate": 0.00016476259207257407, | |
| "loss": 0.4626, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.944206008583691, | |
| "grad_norm": 0.13636501133441925, | |
| "learning_rate": 0.0001575546044336872, | |
| "loss": 0.4505, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.0300429184549356, | |
| "grad_norm": 0.21951957046985626, | |
| "learning_rate": 0.00014986831680165167, | |
| "loss": 0.4371, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.1158798283261802, | |
| "grad_norm": 0.183538556098938, | |
| "learning_rate": 0.00014176760506194906, | |
| "loss": 0.4241, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.201716738197425, | |
| "grad_norm": 0.27745020389556885, | |
| "learning_rate": 0.00013331978911726523, | |
| "loss": 0.4247, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.2875536480686696, | |
| "grad_norm": 0.16314753890037537, | |
| "learning_rate": 0.00012459507343426653, | |
| "loss": 0.4142, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.3733905579399142, | |
| "grad_norm": 0.13504645228385925, | |
| "learning_rate": 0.00011566596361858548, | |
| "loss": 0.3982, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.4592274678111588, | |
| "grad_norm": 0.21324139833450317, | |
| "learning_rate": 0.0001066066638664925, | |
| "loss": 0.4026, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.5450643776824036, | |
| "grad_norm": 0.3690386116504669, | |
| "learning_rate": 9.749246030065306e-05, | |
| "loss": 0.3991, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.6309012875536482, | |
| "grad_norm": 0.32246139645576477, | |
| "learning_rate": 8.839909531467737e-05, | |
| "loss": 0.3949, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.7167381974248928, | |
| "grad_norm": 0.14840121567249298, | |
| "learning_rate": 7.940213812589018e-05, | |
| "loss": 0.3874, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.8025751072961373, | |
| "grad_norm": 0.16993016004562378, | |
| "learning_rate": 7.057635676725945e-05, | |
| "loss": 0.3886, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.888412017167382, | |
| "grad_norm": 0.21142154932022095, | |
| "learning_rate": 6.199509673746246e-05, | |
| "loss": 0.3868, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.9742489270386265, | |
| "grad_norm": 0.17925000190734863, | |
| "learning_rate": 5.372967147273683e-05, | |
| "loss": 0.381, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.060085836909871, | |
| "grad_norm": 0.20707811415195465, | |
| "learning_rate": 4.584876970591957e-05, | |
| "loss": 0.3713, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.1459227467811157, | |
| "grad_norm": 0.22432269155979156, | |
| "learning_rate": 3.841788463774003e-05, | |
| "loss": 0.366, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.2317596566523603, | |
| "grad_norm": 0.26082319021224976, | |
| "learning_rate": 3.149876966416321e-05, | |
| "loss": 0.3681, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.317596566523605, | |
| "grad_norm": 0.16953982412815094, | |
| "learning_rate": 2.514892518288988e-05, | |
| "loss": 0.3684, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.40343347639485, | |
| "grad_norm": 0.24221323430538177, | |
| "learning_rate": 1.9421120743841902e-05, | |
| "loss": 0.3694, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.4892703862660945, | |
| "grad_norm": 0.14716067910194397, | |
| "learning_rate": 1.436295651473667e-05, | |
| "loss": 0.37, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.575107296137339, | |
| "grad_norm": 0.2028035819530487, | |
| "learning_rate": 1.0016467706135135e-05, | |
| "loss": 0.367, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.6609442060085837, | |
| "grad_norm": 0.1700461506843567, | |
| "learning_rate": 6.417775243336544e-06, | |
| "loss": 0.3622, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.7467811158798283, | |
| "grad_norm": 0.16668541729450226, | |
| "learning_rate": 3.5967855881650302e-06, | |
| "loss": 0.3659, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.832618025751073, | |
| "grad_norm": 0.16603396832942963, | |
| "learning_rate": 1.576942205240317e-06, | |
| "loss": 0.3623, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.9184549356223175, | |
| "grad_norm": 0.15877024829387665, | |
| "learning_rate": 3.750307381389484e-07, | |
| "loss": 0.3682, | |
| "step": 3400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3495, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2889443120552346e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |