| { | |
| "best_metric": 1.1562652587890625, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1658181818181819, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02327272727272727, | |
| "grad_norm": 1.7418212890625, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5999, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02327272727272727, | |
| "eval_loss": 1.7730071544647217, | |
| "eval_runtime": 5.7956, | |
| "eval_samples_per_second": 8.627, | |
| "eval_steps_per_second": 2.243, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04654545454545454, | |
| "grad_norm": 1.9036730527877808, | |
| "learning_rate": 0.0001, | |
| "loss": 1.773, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06981818181818182, | |
| "grad_norm": 1.3172043561935425, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.6503, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09309090909090909, | |
| "grad_norm": 0.7838025093078613, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.4638, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11636363636363636, | |
| "grad_norm": 0.8728094696998596, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.4451, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13963636363636364, | |
| "grad_norm": 0.6868547797203064, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3741, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16290909090909092, | |
| "grad_norm": 0.5994782447814941, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.3307, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18618181818181817, | |
| "grad_norm": 0.5220155119895935, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.3488, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20945454545454545, | |
| "grad_norm": 0.5508671998977661, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.3852, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23272727272727273, | |
| "grad_norm": 0.5149024724960327, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.4274, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 0.6122696995735168, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.3254, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2792727272727273, | |
| "grad_norm": 0.5678585767745972, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.3606, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.30254545454545456, | |
| "grad_norm": 0.39735573530197144, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.3344, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.32581818181818184, | |
| "grad_norm": 0.3837674856185913, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.2403, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3490909090909091, | |
| "grad_norm": 0.40712860226631165, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.2072, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.37236363636363634, | |
| "grad_norm": 0.3822881877422333, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.1608, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3956363636363636, | |
| "grad_norm": 0.42343980073928833, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.1956, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4189090909090909, | |
| "grad_norm": 0.3273860216140747, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.1946, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4421818181818182, | |
| "grad_norm": 0.3466838598251343, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.2408, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.46545454545454545, | |
| "grad_norm": 0.40050435066223145, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.3264, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48872727272727273, | |
| "grad_norm": 0.5331990718841553, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.411, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 0.5197176337242126, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.2133, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5352727272727272, | |
| "grad_norm": 0.4842509329319, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.2943, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5585454545454546, | |
| "grad_norm": 0.4113174080848694, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.2181, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 0.3551021218299866, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.1385, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "eval_loss": 1.203967571258545, | |
| "eval_runtime": 5.8142, | |
| "eval_samples_per_second": 8.6, | |
| "eval_steps_per_second": 2.236, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6050909090909091, | |
| "grad_norm": 0.35163772106170654, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.1142, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6283636363636363, | |
| "grad_norm": 0.3587358593940735, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.1149, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6516363636363637, | |
| "grad_norm": 0.377644419670105, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.1137, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6749090909090909, | |
| "grad_norm": 0.3828115165233612, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.1805, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6981818181818182, | |
| "grad_norm": 0.42565858364105225, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2981, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7214545454545455, | |
| "grad_norm": 0.4533040225505829, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.3059, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7447272727272727, | |
| "grad_norm": 0.37361446022987366, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.2207, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 0.3790070414543152, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.2411, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7912727272727272, | |
| "grad_norm": 0.3196423053741455, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.1851, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8145454545454546, | |
| "grad_norm": 0.3072417080402374, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.1154, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8378181818181818, | |
| "grad_norm": 0.26135000586509705, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.1771, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8610909090909091, | |
| "grad_norm": 0.26794689893722534, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.0627, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8843636363636364, | |
| "grad_norm": 0.26266616582870483, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.0719, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9076363636363637, | |
| "grad_norm": 0.275880366563797, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.1166, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9309090909090909, | |
| "grad_norm": 0.3153255879878998, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.2155, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9541818181818181, | |
| "grad_norm": 0.39986106753349304, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.3209, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9774545454545455, | |
| "grad_norm": 0.5153669118881226, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3614, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.002909090909091, | |
| "grad_norm": 0.2800445556640625, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.2959, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.026181818181818, | |
| "grad_norm": 0.31496769189834595, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.1274, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0494545454545454, | |
| "grad_norm": 0.27701205015182495, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.1971, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0727272727272728, | |
| "grad_norm": 0.24459481239318848, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.1391, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.096, | |
| "grad_norm": 0.2415713369846344, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.0888, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.1192727272727272, | |
| "grad_norm": 0.23551389575004578, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.0747, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1425454545454545, | |
| "grad_norm": 0.2616652846336365, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.0794, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1658181818181819, | |
| "grad_norm": 0.25251996517181396, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1063, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1658181818181819, | |
| "eval_loss": 1.1562652587890625, | |
| "eval_runtime": 5.9248, | |
| "eval_samples_per_second": 8.439, | |
| "eval_steps_per_second": 2.194, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 3.24961789018112e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |