| { | |
| "best_metric": 9.062572479248047, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.16420361247947454, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003284072249589491, | |
| "grad_norm": 5.0626983642578125, | |
| "learning_rate": 5e-05, | |
| "loss": 10.1534, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003284072249589491, | |
| "eval_loss": 10.289778709411621, | |
| "eval_runtime": 0.5713, | |
| "eval_samples_per_second": 87.527, | |
| "eval_steps_per_second": 22.757, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006568144499178982, | |
| "grad_norm": 4.237027645111084, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3178, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009852216748768473, | |
| "grad_norm": 3.833760976791382, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.4493, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013136288998357963, | |
| "grad_norm": 3.885283946990967, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.4143, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016420361247947456, | |
| "grad_norm": 3.647639751434326, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.2325, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.019704433497536946, | |
| "grad_norm": 3.458007574081421, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.2275, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022988505747126436, | |
| "grad_norm": 3.5521318912506104, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.089, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026272577996715927, | |
| "grad_norm": 3.2706851959228516, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 9.9827, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029556650246305417, | |
| "grad_norm": 3.162849187850952, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 9.6735, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03284072249589491, | |
| "grad_norm": 3.4256649017333984, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 9.6991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0361247947454844, | |
| "grad_norm": 3.1439263820648193, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 9.4494, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03940886699507389, | |
| "grad_norm": 3.6793322563171387, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 9.4807, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.042692939244663386, | |
| "grad_norm": 3.272399663925171, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 9.4473, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04597701149425287, | |
| "grad_norm": 3.0414819717407227, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 9.6337, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04926108374384237, | |
| "grad_norm": 2.6899259090423584, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 9.596, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.052545155993431854, | |
| "grad_norm": 2.572854518890381, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 9.5432, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05582922824302135, | |
| "grad_norm": 2.417119026184082, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 9.6109, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.059113300492610835, | |
| "grad_norm": 2.414215087890625, | |
| "learning_rate": 7.75e-05, | |
| "loss": 9.5861, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06239737274220033, | |
| "grad_norm": 2.457582950592041, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 9.5782, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06568144499178982, | |
| "grad_norm": 2.355839490890503, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 9.4318, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 2.5010826587677, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 9.409, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0722495894909688, | |
| "grad_norm": 2.6175942420959473, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 9.1827, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0755336617405583, | |
| "grad_norm": 3.066164016723633, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 9.1461, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07881773399014778, | |
| "grad_norm": 3.4586806297302246, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 9.2352, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08210180623973727, | |
| "grad_norm": 4.095075607299805, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 9.306, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08210180623973727, | |
| "eval_loss": 9.314793586730957, | |
| "eval_runtime": 0.5512, | |
| "eval_samples_per_second": 90.714, | |
| "eval_steps_per_second": 23.586, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08538587848932677, | |
| "grad_norm": 2.5130350589752197, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 9.1092, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08866995073891626, | |
| "grad_norm": 2.114590644836426, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 9.197, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09195402298850575, | |
| "grad_norm": 2.1008377075195312, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 9.2731, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 2.0370545387268066, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 9.4849, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09852216748768473, | |
| "grad_norm": 2.0477921962738037, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 9.3548, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10180623973727422, | |
| "grad_norm": 2.033531665802002, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 9.2227, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10509031198686371, | |
| "grad_norm": 2.0999460220336914, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 9.204, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10837438423645321, | |
| "grad_norm": 2.2290875911712646, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 9.1827, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1116584564860427, | |
| "grad_norm": 2.2694082260131836, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 9.1508, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11494252873563218, | |
| "grad_norm": 2.420377731323242, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 8.8894, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11822660098522167, | |
| "grad_norm": 2.9713902473449707, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 9.0052, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12151067323481117, | |
| "grad_norm": 3.350985050201416, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 8.9528, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12479474548440066, | |
| "grad_norm": 2.2344725131988525, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 8.8451, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12807881773399016, | |
| "grad_norm": 2.1066842079162598, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 9.112, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13136288998357964, | |
| "grad_norm": 1.8320448398590088, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 9.1202, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13464696223316913, | |
| "grad_norm": 1.908353567123413, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 9.2423, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 1.8999229669570923, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 9.167, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1412151067323481, | |
| "grad_norm": 1.8419102430343628, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 9.1372, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1444991789819376, | |
| "grad_norm": 1.9281691312789917, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 9.1061, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1477832512315271, | |
| "grad_norm": 1.9718252420425415, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 9.0683, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1510673234811166, | |
| "grad_norm": 2.044898509979248, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 8.9936, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15435139573070608, | |
| "grad_norm": 2.419887065887451, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 8.8617, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15763546798029557, | |
| "grad_norm": 2.657135009765625, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 8.9259, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16091954022988506, | |
| "grad_norm": 3.4543638229370117, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 9.0371, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16420361247947454, | |
| "grad_norm": 4.0607452392578125, | |
| "learning_rate": 1e-05, | |
| "loss": 8.7464, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16420361247947454, | |
| "eval_loss": 9.062572479248047, | |
| "eval_runtime": 0.5413, | |
| "eval_samples_per_second": 92.373, | |
| "eval_steps_per_second": 24.017, | |
| "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": 232013797785600.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |