| { | |
| "best_metric": 3.0511791706085205, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0071301247771836, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028520499108734403, | |
| "grad_norm": 0.9442576766014099, | |
| "learning_rate": 2e-05, | |
| "loss": 3.3049, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028520499108734403, | |
| "eval_loss": 3.7652459144592285, | |
| "eval_runtime": 857.4027, | |
| "eval_samples_per_second": 6.888, | |
| "eval_steps_per_second": 1.723, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005704099821746881, | |
| "grad_norm": 0.9913172721862793, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7418, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000855614973262032, | |
| "grad_norm": 0.9472721815109253, | |
| "learning_rate": 6e-05, | |
| "loss": 3.7158, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011408199643493761, | |
| "grad_norm": 1.1189954280853271, | |
| "learning_rate": 8e-05, | |
| "loss": 3.9813, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00142602495543672, | |
| "grad_norm": 1.040862798690796, | |
| "learning_rate": 0.0001, | |
| "loss": 3.569, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00142602495543672, | |
| "eval_loss": 3.6927330493927, | |
| "eval_runtime": 862.1425, | |
| "eval_samples_per_second": 6.85, | |
| "eval_steps_per_second": 1.713, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001711229946524064, | |
| "grad_norm": 1.2287300825119019, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 3.6772, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019964349376114083, | |
| "grad_norm": 1.2859654426574707, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.6225, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022816399286987523, | |
| "grad_norm": 1.526451587677002, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 3.5456, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025668449197860962, | |
| "grad_norm": 1.2330029010772705, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.9909, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00285204991087344, | |
| "grad_norm": 1.516096591949463, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.4418, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00285204991087344, | |
| "eval_loss": 3.3367996215820312, | |
| "eval_runtime": 862.3847, | |
| "eval_samples_per_second": 6.848, | |
| "eval_steps_per_second": 1.713, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003137254901960784, | |
| "grad_norm": 1.3773342370986938, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 3.1527, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003422459893048128, | |
| "grad_norm": 1.2679097652435303, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 3.2337, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0037076648841354726, | |
| "grad_norm": 1.1964778900146484, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.9654, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0039928698752228165, | |
| "grad_norm": 0.9561767578125, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 2.7436, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0042780748663101605, | |
| "grad_norm": 1.2431445121765137, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2928, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0042780748663101605, | |
| "eval_loss": 3.126676559448242, | |
| "eval_runtime": 859.4772, | |
| "eval_samples_per_second": 6.872, | |
| "eval_steps_per_second": 1.718, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0045632798573975045, | |
| "grad_norm": 1.0335696935653687, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 2.878, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0048484848484848485, | |
| "grad_norm": 0.8544740080833435, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.7072, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0051336898395721925, | |
| "grad_norm": 0.9683927297592163, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 3.0918, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0054188948306595364, | |
| "grad_norm": 1.025421380996704, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 3.0183, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00570409982174688, | |
| "grad_norm": 0.8975963592529297, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.9735, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00570409982174688, | |
| "eval_loss": 3.0618274211883545, | |
| "eval_runtime": 867.1811, | |
| "eval_samples_per_second": 6.811, | |
| "eval_steps_per_second": 1.703, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005989304812834224, | |
| "grad_norm": 0.8859240412712097, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 3.0036, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006274509803921568, | |
| "grad_norm": 0.8403681516647339, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 2.8981, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006559714795008912, | |
| "grad_norm": 0.9174202680587769, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 3.0085, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006844919786096256, | |
| "grad_norm": 1.1602686643600464, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 3.0675, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0071301247771836, | |
| "grad_norm": 0.8188506960868835, | |
| "learning_rate": 0.0, | |
| "loss": 2.8007, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0071301247771836, | |
| "eval_loss": 3.0511791706085205, | |
| "eval_runtime": 857.788, | |
| "eval_samples_per_second": 6.885, | |
| "eval_steps_per_second": 1.722, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.26729100951552e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |