| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 17, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.2623544037342072, |
| "epoch": 0.06153846153846154, |
| "grad_norm": 0.19557932019233704, |
| "learning_rate": 0.0, |
| "loss": 1.363303303718567, |
| "mean_token_accuracy": 0.6967771947383881, |
| "num_tokens": 8983.0, |
| "step": 1 |
| }, |
| { |
| "entropy": 1.2696461975574493, |
| "epoch": 0.12307692307692308, |
| "grad_norm": 0.2623090445995331, |
| "learning_rate": 0.0001, |
| "loss": 1.3970271348953247, |
| "mean_token_accuracy": 0.7032225728034973, |
| "num_tokens": 15469.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 1.351563960313797, |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.2595767080783844, |
| "learning_rate": 0.0002, |
| "loss": 1.438194990158081, |
| "mean_token_accuracy": 0.6762479990720749, |
| "num_tokens": 23136.0, |
| "step": 3 |
| }, |
| { |
| "entropy": 1.156097874045372, |
| "epoch": 0.24615384615384617, |
| "grad_norm": 0.9452286958694458, |
| "learning_rate": 0.00019979453927503364, |
| "loss": 1.191060185432434, |
| "mean_token_accuracy": 0.7312490344047546, |
| "num_tokens": 31431.0, |
| "step": 4 |
| }, |
| { |
| "entropy": 1.2470719814300537, |
| "epoch": 0.3076923076923077, |
| "grad_norm": 0.29575249552726746, |
| "learning_rate": 0.0001991790013823246, |
| "loss": 1.2078289985656738, |
| "mean_token_accuracy": 0.7162232249975204, |
| "num_tokens": 39311.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 1.3020514845848083, |
| "epoch": 0.36923076923076925, |
| "grad_norm": 0.12131688743829727, |
| "learning_rate": 0.00019815591569910654, |
| "loss": 1.236517310142517, |
| "mean_token_accuracy": 0.7079942375421524, |
| "num_tokens": 46157.0, |
| "step": 6 |
| }, |
| { |
| "entropy": 1.1494204998016357, |
| "epoch": 0.4307692307692308, |
| "grad_norm": 0.07860170304775238, |
| "learning_rate": 0.00019672948630390294, |
| "loss": 1.0905468463897705, |
| "mean_token_accuracy": 0.74454265832901, |
| "num_tokens": 55535.0, |
| "step": 7 |
| }, |
| { |
| "entropy": 1.0420133769512177, |
| "epoch": 0.49230769230769234, |
| "grad_norm": 0.09150254726409912, |
| "learning_rate": 0.00019490557470106686, |
| "loss": 1.0026195049285889, |
| "mean_token_accuracy": 0.7577853351831436, |
| "num_tokens": 63422.0, |
| "step": 8 |
| }, |
| { |
| "entropy": 1.0447807163000107, |
| "epoch": 0.5538461538461539, |
| "grad_norm": 0.10369911789894104, |
| "learning_rate": 0.0001926916757346022, |
| "loss": 1.0252422094345093, |
| "mean_token_accuracy": 0.7560650110244751, |
| "num_tokens": 70555.0, |
| "step": 9 |
| }, |
| { |
| "entropy": 1.0285034626722336, |
| "epoch": 0.6153846153846154, |
| "grad_norm": 0.11572559177875519, |
| "learning_rate": 0.0001900968867902419, |
| "loss": 1.052419900894165, |
| "mean_token_accuracy": 0.7432190179824829, |
| "num_tokens": 78003.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.0061500668525696, |
| "epoch": 0.676923076923077, |
| "grad_norm": 0.10965128242969513, |
| "learning_rate": 0.00018713187041233896, |
| "loss": 0.9987847805023193, |
| "mean_token_accuracy": 0.7628708183765411, |
| "num_tokens": 86065.0, |
| "step": 11 |
| }, |
| { |
| "entropy": 1.0449193269014359, |
| "epoch": 0.7384615384615385, |
| "grad_norm": 0.10073477029800415, |
| "learning_rate": 0.00018380881048918405, |
| "loss": 1.0622799396514893, |
| "mean_token_accuracy": 0.746578574180603, |
| "num_tokens": 93482.0, |
| "step": 12 |
| }, |
| { |
| "entropy": 0.8957007825374603, |
| "epoch": 0.8, |
| "grad_norm": 0.10005328059196472, |
| "learning_rate": 0.00018014136218679567, |
| "loss": 0.8889887928962708, |
| "mean_token_accuracy": 0.77289679646492, |
| "num_tokens": 100654.0, |
| "step": 13 |
| }, |
| { |
| "entropy": 0.9818997383117676, |
| "epoch": 0.8615384615384616, |
| "grad_norm": 0.12628009915351868, |
| "learning_rate": 0.00017614459583691346, |
| "loss": 0.976428210735321, |
| "mean_token_accuracy": 0.7596915662288666, |
| "num_tokens": 108091.0, |
| "step": 14 |
| }, |
| { |
| "entropy": 0.9654281437397003, |
| "epoch": 0.9230769230769231, |
| "grad_norm": 0.11806830018758774, |
| "learning_rate": 0.00017183493500977278, |
| "loss": 0.9671178460121155, |
| "mean_token_accuracy": 0.7701253145933151, |
| "num_tokens": 114707.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 0.9159971326589584, |
| "epoch": 0.9846153846153847, |
| "grad_norm": 0.09751465171575546, |
| "learning_rate": 0.0001672300890261317, |
| "loss": 0.902397632598877, |
| "mean_token_accuracy": 0.7794631719589233, |
| "num_tokens": 121769.0, |
| "step": 16 |
| }, |
| { |
| "entropy": 1.1713899374008179, |
| "epoch": 1.0, |
| "grad_norm": 0.5108214020729065, |
| "learning_rate": 0.00016234898018587337, |
| "loss": 1.1008179187774658, |
| "mean_token_accuracy": 0.7128027677536011, |
| "num_tokens": 122059.0, |
| "step": 17 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 51, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 1465581970962432.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
