| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5235602094240838, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02617801047120419, |
| "grad_norm": 1.4316072463989258, |
| "learning_rate": 6.363636363636363e-06, |
| "loss": 1.0183, |
| "mean_token_accuracy": 0.8535788297653198, |
| "num_tokens": 367251.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.05235602094240838, |
| "grad_norm": 0.3439352810382843, |
| "learning_rate": 1.4318181818181818e-05, |
| "loss": 0.3552, |
| "mean_token_accuracy": 0.9084522366523743, |
| "num_tokens": 736944.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07853403141361257, |
| "grad_norm": 0.4000185430049896, |
| "learning_rate": 2.227272727272727e-05, |
| "loss": 0.3266, |
| "mean_token_accuracy": 0.9090922474861145, |
| "num_tokens": 1103710.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.10471204188481675, |
| "grad_norm": 0.4231952726840973, |
| "learning_rate": 3.0227272727272725e-05, |
| "loss": 0.3551, |
| "mean_token_accuracy": 0.9081164598464966, |
| "num_tokens": 1471709.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13089005235602094, |
| "grad_norm": 0.31727662682533264, |
| "learning_rate": 3.499979493322583e-05, |
| "loss": 0.3665, |
| "mean_token_accuracy": 0.9083151340484619, |
| "num_tokens": 1841439.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.15706806282722513, |
| "grad_norm": 0.28530699014663696, |
| "learning_rate": 3.499748800560744e-05, |
| "loss": 0.3446, |
| "mean_token_accuracy": 0.9064475655555725, |
| "num_tokens": 2207080.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.18324607329842932, |
| "grad_norm": 0.3164561986923218, |
| "learning_rate": 3.499261826894553e-05, |
| "loss": 0.3102, |
| "mean_token_accuracy": 0.9147708892822266, |
| "num_tokens": 2577288.0, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.2094240837696335, |
| "grad_norm": 0.48501917719841003, |
| "learning_rate": 3.498518667429489e-05, |
| "loss": 0.3125, |
| "mean_token_accuracy": 0.9136863827705384, |
| "num_tokens": 2943463.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2356020942408377, |
| "grad_norm": 0.39581820368766785, |
| "learning_rate": 3.497519467303868e-05, |
| "loss": 0.3328, |
| "mean_token_accuracy": 0.9117220759391784, |
| "num_tokens": 3319962.0, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.2617801047120419, |
| "grad_norm": 0.34402891993522644, |
| "learning_rate": 3.4962644216604936e-05, |
| "loss": 0.3148, |
| "mean_token_accuracy": 0.912682318687439, |
| "num_tokens": 3690158.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2879581151832461, |
| "grad_norm": 0.29138538241386414, |
| "learning_rate": 3.49475377560855e-05, |
| "loss": 0.3115, |
| "mean_token_accuracy": 0.9203069567680359, |
| "num_tokens": 4062060.0, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.31413612565445026, |
| "grad_norm": 0.2792457640171051, |
| "learning_rate": 3.492987824175731e-05, |
| "loss": 0.3015, |
| "mean_token_accuracy": 0.9141550898551941, |
| "num_tokens": 4436254.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.3403141361256545, |
| "grad_norm": 0.30358779430389404, |
| "learning_rate": 3.4909669122506196e-05, |
| "loss": 0.2302, |
| "mean_token_accuracy": 0.9322636842727661, |
| "num_tokens": 4811698.0, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.36649214659685864, |
| "grad_norm": 0.2963319718837738, |
| "learning_rate": 3.4886914345153334e-05, |
| "loss": 0.2878, |
| "mean_token_accuracy": 0.9199236869812012, |
| "num_tokens": 5182959.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.39267015706806285, |
| "grad_norm": 0.3031884431838989, |
| "learning_rate": 3.486161835368445e-05, |
| "loss": 0.2966, |
| "mean_token_accuracy": 0.9157989859580994, |
| "num_tokens": 5555766.0, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.418848167539267, |
| "grad_norm": 0.2854786217212677, |
| "learning_rate": 3.4833786088381864e-05, |
| "loss": 0.3078, |
| "mean_token_accuracy": 0.9176850080490112, |
| "num_tokens": 5923597.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.44502617801047123, |
| "grad_norm": 0.26075834035873413, |
| "learning_rate": 3.480342298485971e-05, |
| "loss": 0.2726, |
| "mean_token_accuracy": 0.9211544632911682, |
| "num_tokens": 6292042.0, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.4712041884816754, |
| "grad_norm": 0.24862438440322876, |
| "learning_rate": 3.477053497300234e-05, |
| "loss": 0.3242, |
| "mean_token_accuracy": 0.9118959903717041, |
| "num_tokens": 6667493.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4973821989528796, |
| "grad_norm": 0.22300361096858978, |
| "learning_rate": 3.473512847580624e-05, |
| "loss": 0.2891, |
| "mean_token_accuracy": 0.9222010493278503, |
| "num_tokens": 7030101.0, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.5235602094240838, |
| "grad_norm": 0.3619837760925293, |
| "learning_rate": 3.4697210408125585e-05, |
| "loss": 0.3445, |
| "mean_token_accuracy": 0.909607207775116, |
| "num_tokens": 7401039.0, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1146, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.2115031692804096e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
