| { | |
| "best_metric": 7.95767068862915, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4625614339404452, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009251228678808905, | |
| "grad_norm": 4.89844274520874, | |
| "learning_rate": 5e-05, | |
| "loss": 9.8817, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009251228678808905, | |
| "eval_loss": 9.016510963439941, | |
| "eval_runtime": 0.7476, | |
| "eval_samples_per_second": 66.879, | |
| "eval_steps_per_second": 17.389, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01850245735761781, | |
| "grad_norm": 3.1463985443115234, | |
| "learning_rate": 0.0001, | |
| "loss": 9.2431, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.027753686036426712, | |
| "grad_norm": 2.822237014770508, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 9.0718, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03700491471523562, | |
| "grad_norm": 2.731067180633545, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 8.8489, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04625614339404452, | |
| "grad_norm": 2.654003143310547, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 8.8476, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.055507372072853424, | |
| "grad_norm": 2.670952558517456, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 8.6677, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06475860075166233, | |
| "grad_norm": 2.6398637294769287, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 8.6832, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07400982943047124, | |
| "grad_norm": 2.579364538192749, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 8.5877, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08326105810928014, | |
| "grad_norm": 2.7029902935028076, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 8.5979, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09251228678808904, | |
| "grad_norm": 2.9253904819488525, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 8.5614, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10176351546689795, | |
| "grad_norm": 3.1259610652923584, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 8.7359, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11101474414570685, | |
| "grad_norm": 4.356231689453125, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 8.9214, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12026597282451576, | |
| "grad_norm": 5.031243801116943, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 9.2625, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12951720150332466, | |
| "grad_norm": 2.5803394317626953, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 8.6955, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13876843018213356, | |
| "grad_norm": 1.9104470014572144, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 8.4649, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14801965886094248, | |
| "grad_norm": 1.7666088342666626, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 8.4588, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15727088753975138, | |
| "grad_norm": 1.6460059881210327, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 8.3894, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16652211621856028, | |
| "grad_norm": 1.698133945465088, | |
| "learning_rate": 7.75e-05, | |
| "loss": 8.3618, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17577334489736918, | |
| "grad_norm": 1.5541409254074097, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 8.2921, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18502457357617808, | |
| "grad_norm": 1.6291533708572388, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 8.1995, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.194275802254987, | |
| "grad_norm": 1.7791177034378052, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 8.1354, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2035270309337959, | |
| "grad_norm": 1.7086344957351685, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 8.1375, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2127782596126048, | |
| "grad_norm": 1.8993000984191895, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 8.141, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2220294882914137, | |
| "grad_norm": 2.3244051933288574, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 8.312, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2312807169702226, | |
| "grad_norm": 4.274384021759033, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 8.7624, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2312807169702226, | |
| "eval_loss": 8.139893531799316, | |
| "eval_runtime": 0.7595, | |
| "eval_samples_per_second": 65.836, | |
| "eval_steps_per_second": 17.117, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24053194564903152, | |
| "grad_norm": 4.174472332000732, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 8.7814, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24978317432784042, | |
| "grad_norm": 1.737717628479004, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 8.2499, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2590344030066493, | |
| "grad_norm": 1.5726858377456665, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 8.1994, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2682856316854582, | |
| "grad_norm": 1.4943739175796509, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 8.143, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2775368603642671, | |
| "grad_norm": 1.4114775657653809, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 8.1014, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.286788089043076, | |
| "grad_norm": 1.3771249055862427, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 8.0529, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.29603931772188496, | |
| "grad_norm": 1.3822271823883057, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 7.9885, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.30529054640069386, | |
| "grad_norm": 1.4392659664154053, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 7.9505, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.31454177507950276, | |
| "grad_norm": 1.3860464096069336, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 8.0864, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.32379300375831166, | |
| "grad_norm": 1.371462345123291, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 8.0629, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.33304423243712056, | |
| "grad_norm": 1.6449263095855713, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 8.1709, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.34229546111592946, | |
| "grad_norm": 2.209439277648926, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 8.3228, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.35154668979473835, | |
| "grad_norm": 5.064708232879639, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 8.7106, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.36079791847354725, | |
| "grad_norm": 2.071536064147949, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 8.3119, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.37004914715235615, | |
| "grad_norm": 1.3740651607513428, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 8.0236, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3793003758311651, | |
| "grad_norm": 1.3041908740997314, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 8.1272, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.388551604509974, | |
| "grad_norm": 1.2141309976577759, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 7.9449, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3978028331887829, | |
| "grad_norm": 1.2382042407989502, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 8.078, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4070540618675918, | |
| "grad_norm": 1.2371668815612793, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 8.003, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4163052905464007, | |
| "grad_norm": 1.2782078981399536, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 8.1092, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4255565192252096, | |
| "grad_norm": 1.2752069234848022, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 7.9829, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4348077479040185, | |
| "grad_norm": 1.3277031183242798, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 8.0168, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4440589765828274, | |
| "grad_norm": 1.4168155193328857, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 8.0042, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4533102052616363, | |
| "grad_norm": 1.7632670402526855, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 8.095, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4625614339404452, | |
| "grad_norm": 3.518686532974243, | |
| "learning_rate": 1e-05, | |
| "loss": 8.2842, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4625614339404452, | |
| "eval_loss": 7.95767068862915, | |
| "eval_runtime": 0.7539, | |
| "eval_samples_per_second": 66.322, | |
| "eval_steps_per_second": 17.244, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 232340067975168.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |