| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 183, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0273224043715847, | |
| "grad_norm": 1.9637937392518852, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.0768, | |
| "num_tokens": 5232734.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0546448087431694, | |
| "grad_norm": 1.2562972922892146, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0277, | |
| "num_tokens": 10474742.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08196721311475409, | |
| "grad_norm": 0.6833142149279973, | |
| "learning_rate": 4.990731665851952e-05, | |
| "loss": 0.9226, | |
| "num_tokens": 15711541.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1092896174863388, | |
| "grad_norm": 0.5257977163642082, | |
| "learning_rate": 4.963003020757034e-05, | |
| "loss": 0.8754, | |
| "num_tokens": 20954421.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1366120218579235, | |
| "grad_norm": 0.4995258336987564, | |
| "learning_rate": 4.9170425076914354e-05, | |
| "loss": 0.8364, | |
| "num_tokens": 26183457.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16393442622950818, | |
| "grad_norm": 0.4384702185411981, | |
| "learning_rate": 4.8532287732264497e-05, | |
| "loss": 0.8251, | |
| "num_tokens": 31426089.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1912568306010929, | |
| "grad_norm": 0.46784765002825424, | |
| "learning_rate": 4.772087548041419e-05, | |
| "loss": 0.8213, | |
| "num_tokens": 36654552.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2185792349726776, | |
| "grad_norm": 0.480931544073295, | |
| "learning_rate": 4.6742873156814044e-05, | |
| "loss": 0.8078, | |
| "num_tokens": 41885527.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2459016393442623, | |
| "grad_norm": 0.4351542970626788, | |
| "learning_rate": 4.5606338052426475e-05, | |
| "loss": 0.7962, | |
| "num_tokens": 47120667.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.273224043715847, | |
| "grad_norm": 0.4359336265907784, | |
| "learning_rate": 4.432063353357899e-05, | |
| "loss": 0.7813, | |
| "num_tokens": 52353555.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3005464480874317, | |
| "grad_norm": 0.5238088158357288, | |
| "learning_rate": 4.289635190169054e-05, | |
| "loss": 0.7781, | |
| "num_tokens": 57596435.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.32786885245901637, | |
| "grad_norm": 0.4284871537213213, | |
| "learning_rate": 4.134522712839249e-05, | |
| "loss": 0.7797, | |
| "num_tokens": 62829836.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3551912568306011, | |
| "grad_norm": 0.46508893670733664, | |
| "learning_rate": 3.968003818497749e-05, | |
| "loss": 0.7784, | |
| "num_tokens": 68050846.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3825136612021858, | |
| "grad_norm": 0.5815913287659525, | |
| "learning_rate": 3.791450376259862e-05, | |
| "loss": 0.7756, | |
| "num_tokens": 73266605.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4098360655737705, | |
| "grad_norm": 0.45053521539007335, | |
| "learning_rate": 3.606316925056831e-05, | |
| "loss": 0.7686, | |
| "num_tokens": 78485239.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4371584699453552, | |
| "grad_norm": 0.3938839130452964, | |
| "learning_rate": 3.414128690388862e-05, | |
| "loss": 0.77, | |
| "num_tokens": 83716610.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4644808743169399, | |
| "grad_norm": 0.35181692505479023, | |
| "learning_rate": 3.2164690187254875e-05, | |
| "loss": 0.7689, | |
| "num_tokens": 88947050.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4918032786885246, | |
| "grad_norm": 0.3719054732206869, | |
| "learning_rate": 3.014966333075216e-05, | |
| "loss": 0.7606, | |
| "num_tokens": 94189930.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5191256830601093, | |
| "grad_norm": 0.5018011648361339, | |
| "learning_rate": 2.8112807171912342e-05, | |
| "loss": 0.7624, | |
| "num_tokens": 99429827.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.546448087431694, | |
| "grad_norm": 0.38465079866500806, | |
| "learning_rate": 2.607090238939466e-05, | |
| "loss": 0.7556, | |
| "num_tokens": 104663335.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5737704918032787, | |
| "grad_norm": 0.37532731568169625, | |
| "learning_rate": 2.404077125504165e-05, | |
| "loss": 0.7569, | |
| "num_tokens": 109906215.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6010928961748634, | |
| "grad_norm": 0.3762342252931946, | |
| "learning_rate": 2.2039139043268913e-05, | |
| "loss": 0.7512, | |
| "num_tokens": 115121622.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6284153005464481, | |
| "grad_norm": 0.35232043154343623, | |
| "learning_rate": 2.008249623956997e-05, | |
| "loss": 0.742, | |
| "num_tokens": 120364502.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 0.3769980927846154, | |
| "learning_rate": 1.81869626833342e-05, | |
| "loss": 0.751, | |
| "num_tokens": 125589822.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6830601092896175, | |
| "grad_norm": 0.30268379565372083, | |
| "learning_rate": 1.636815476423986e-05, | |
| "loss": 0.7545, | |
| "num_tokens": 130818677.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7103825136612022, | |
| "grad_norm": 0.31305983691887485, | |
| "learning_rate": 1.4641056766327183e-05, | |
| "loss": 0.7404, | |
| "num_tokens": 136051117.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7377049180327869, | |
| "grad_norm": 0.3433781391982165, | |
| "learning_rate": 1.3019897419686034e-05, | |
| "loss": 0.7375, | |
| "num_tokens": 141282965.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7650273224043715, | |
| "grad_norm": 0.3449350102574481, | |
| "learning_rate": 1.1518032676789216e-05, | |
| "loss": 0.7389, | |
| "num_tokens": 146500801.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7923497267759563, | |
| "grad_norm": 0.3142088879981572, | |
| "learning_rate": 1.0147835679221018e-05, | |
| "loss": 0.7368, | |
| "num_tokens": 151743681.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "grad_norm": 0.298418812628233, | |
| "learning_rate": 8.920594821312215e-06, | |
| "loss": 0.73, | |
| "num_tokens": 156986561.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8469945355191257, | |
| "grad_norm": 0.2733856337799136, | |
| "learning_rate": 7.846420750486131e-06, | |
| "loss": 0.7389, | |
| "num_tokens": 162218546.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.8743169398907104, | |
| "grad_norm": 0.2464558839127578, | |
| "learning_rate": 6.934163070495281e-06, | |
| "loss": 0.735, | |
| "num_tokens": 167459738.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9016393442622951, | |
| "grad_norm": 0.2692049560378807, | |
| "learning_rate": 6.191337433790586e-06, | |
| "loss": 0.7305, | |
| "num_tokens": 172686926.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9289617486338798, | |
| "grad_norm": 0.2506718947344618, | |
| "learning_rate": 5.624063623674014e-06, | |
| "loss": 0.7261, | |
| "num_tokens": 177915125.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9562841530054644, | |
| "grad_norm": 0.2476110056971902, | |
| "learning_rate": 5.237015136346088e-06, | |
| "loss": 0.7359, | |
| "num_tokens": 183153974.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.9836065573770492, | |
| "grad_norm": 0.2408809099794402, | |
| "learning_rate": 5.033380678217531e-06, | |
| "loss": 0.7412, | |
| "num_tokens": 188354277.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "num_tokens": 191500005.0, | |
| "step": 183, | |
| "total_flos": 166824045969408.0, | |
| "train_loss": 0.7854770610892707, | |
| "train_runtime": 4413.3549, | |
| "train_samples_per_second": 2.641, | |
| "train_steps_per_second": 0.041 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 183, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 166824045969408.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |