| { | |
| "best_metric": 0.7682966589927673, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.14958863126402394, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0029917726252804786, | |
| "grad_norm": 0.8472118973731995, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8116, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029917726252804786, | |
| "eval_loss": 3.5583090782165527, | |
| "eval_runtime": 2.2545, | |
| "eval_samples_per_second": 22.178, | |
| "eval_steps_per_second": 5.766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005983545250560957, | |
| "grad_norm": 1.8868770599365234, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2636, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008975317875841436, | |
| "grad_norm": 2.297649621963501, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.2068, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011967090501121914, | |
| "grad_norm": 2.6677541732788086, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.3948, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014958863126402393, | |
| "grad_norm": 4.302576065063477, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.2177, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01795063575168287, | |
| "grad_norm": 4.331410884857178, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.2722, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020942408376963352, | |
| "grad_norm": 2.7970023155212402, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.1305, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02393418100224383, | |
| "grad_norm": 3.471433639526367, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.1443, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02692595362752431, | |
| "grad_norm": 3.222832441329956, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.0968, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.029917726252804786, | |
| "grad_norm": 2.3945374488830566, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.0505, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.032909498878085267, | |
| "grad_norm": 2.1883208751678467, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.985, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03590127150336574, | |
| "grad_norm": 2.0559756755828857, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.9535, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03889304412864622, | |
| "grad_norm": 3.229199171066284, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.9607, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.041884816753926704, | |
| "grad_norm": 1.7521278858184814, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5513, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04487658937920718, | |
| "grad_norm": 1.384356141090393, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.7672, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04786836200448766, | |
| "grad_norm": 1.4511749744415283, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.7264, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.050860134629768135, | |
| "grad_norm": 1.3389586210250854, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.6552, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05385190725504862, | |
| "grad_norm": 1.361345648765564, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.7642, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.056843679880329095, | |
| "grad_norm": 1.4190034866333008, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.8965, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05983545250560957, | |
| "grad_norm": 1.4803298711776733, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.9159, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06282722513089005, | |
| "grad_norm": 1.1865524053573608, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.7867, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06581899775617053, | |
| "grad_norm": 1.478258728981018, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.9134, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.068810770381451, | |
| "grad_norm": 1.3490551710128784, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.9508, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07180254300673149, | |
| "grad_norm": 1.3381999731063843, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.9404, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07479431563201197, | |
| "grad_norm": 1.4291648864746094, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.99, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07479431563201197, | |
| "eval_loss": 0.8095762729644775, | |
| "eval_runtime": 2.3243, | |
| "eval_samples_per_second": 21.511, | |
| "eval_steps_per_second": 5.593, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07778608825729244, | |
| "grad_norm": 1.5679738521575928, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6606, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08077786088257292, | |
| "grad_norm": 2.017695426940918, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6623, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08376963350785341, | |
| "grad_norm": 1.8687834739685059, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.6911, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08676140613313388, | |
| "grad_norm": 1.2854175567626953, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.716, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08975317875841436, | |
| "grad_norm": 1.0887775421142578, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.7153, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09274495138369485, | |
| "grad_norm": 1.1645829677581787, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.7103, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09573672400897532, | |
| "grad_norm": 1.5978320837020874, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.793, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0987284966342558, | |
| "grad_norm": 1.9266237020492554, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.8441, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10172026925953627, | |
| "grad_norm": 1.7711067199707031, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.9265, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10471204188481675, | |
| "grad_norm": 1.509682297706604, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.8721, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10770381451009724, | |
| "grad_norm": 1.9011367559432983, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.7926, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11069558713537771, | |
| "grad_norm": 1.442139983177185, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.8771, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11368735976065819, | |
| "grad_norm": 0.765552282333374, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.7513, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11667913238593867, | |
| "grad_norm": 0.9881536960601807, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4893, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11967090501121914, | |
| "grad_norm": 1.0248054265975952, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.5891, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12266267763649963, | |
| "grad_norm": 1.327256441116333, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.5846, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1256544502617801, | |
| "grad_norm": 1.2667062282562256, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.5805, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1286462228870606, | |
| "grad_norm": 1.031787395477295, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.7589, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13163799551234107, | |
| "grad_norm": 1.0182056427001953, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.669, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13462976813762154, | |
| "grad_norm": 1.0797855854034424, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.7008, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.137621540762902, | |
| "grad_norm": 1.1892286539077759, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.8283, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1406133133881825, | |
| "grad_norm": 1.1198517084121704, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.7594, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14360508601346297, | |
| "grad_norm": 1.2403697967529297, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.8554, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14659685863874344, | |
| "grad_norm": 1.477218508720398, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.8582, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.14958863126402394, | |
| "grad_norm": 1.4384434223175049, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9193, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14958863126402394, | |
| "eval_loss": 0.7682966589927673, | |
| "eval_runtime": 2.3312, | |
| "eval_samples_per_second": 21.448, | |
| "eval_steps_per_second": 5.577, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |