| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.03788865471595349, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007577730943190698, | |
| "grad_norm": 2.9950623512268066, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1967, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007577730943190698, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4801, | |
| "eval_samples_per_second": 33.781, | |
| "eval_steps_per_second": 8.783, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015155461886381396, | |
| "grad_norm": 4.4123992919921875, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3201, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022733192829572095, | |
| "grad_norm": 5.187244415283203, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.8391, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003031092377276279, | |
| "grad_norm": 3.759066104888916, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.5287, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0037888654715953493, | |
| "grad_norm": 7.097353458404541, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.2846, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004546638565914419, | |
| "grad_norm": 7.373788356781006, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.1297, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005304411660233489, | |
| "grad_norm": 9.771177291870117, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.187, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006062184754552558, | |
| "grad_norm": 7.501010894775391, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.2104, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006819957848871628, | |
| "grad_norm": 12.057483673095703, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.4529, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007577730943190699, | |
| "grad_norm": 20.803834915161133, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.8192, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008335504037509768, | |
| "grad_norm": 11.555624008178711, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.0855, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009093277131828838, | |
| "grad_norm": 18.56887435913086, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.4639, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009851050226147908, | |
| "grad_norm": 4.186460018157959, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.5997, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010608823320466977, | |
| "grad_norm": 3.294348955154419, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.4819, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011366596414786047, | |
| "grad_norm": 2.7303218841552734, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.5151, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012124369509105117, | |
| "grad_norm": 3.9799444675445557, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.2868, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012882142603424187, | |
| "grad_norm": 4.029333591461182, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.5565, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013639915697743256, | |
| "grad_norm": 3.069025754928589, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.6689, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014397688792062328, | |
| "grad_norm": 7.187241554260254, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.4651, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015155461886381397, | |
| "grad_norm": 4.753688812255859, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.4793, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015913234980700467, | |
| "grad_norm": 6.129785060882568, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.1736, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016671008075019537, | |
| "grad_norm": 6.636349201202393, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.388, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.017428781169338606, | |
| "grad_norm": 9.702000617980957, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.5525, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018186554263657676, | |
| "grad_norm": 3.2611210346221924, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.2517, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.018944327357976746, | |
| "grad_norm": 8.047220230102539, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.6687, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018944327357976746, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4856, | |
| "eval_samples_per_second": 33.656, | |
| "eval_steps_per_second": 8.75, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.019702100452295816, | |
| "grad_norm": 1.749448537826538, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.2472, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.020459873546614885, | |
| "grad_norm": 2.111176013946533, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.1888, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.021217646640933955, | |
| "grad_norm": 2.5237910747528076, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.5017, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.021975419735253025, | |
| "grad_norm": 2.5511085987091064, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.3932, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.022733192829572094, | |
| "grad_norm": 3.7789735794067383, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.2392, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023490965923891164, | |
| "grad_norm": 2.9801998138427734, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.3539, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.024248739018210234, | |
| "grad_norm": 3.6138417720794678, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.4737, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.025006512112529303, | |
| "grad_norm": 5.1532440185546875, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.966, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.025764285206848373, | |
| "grad_norm": 7.934006690979004, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.3545, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.026522058301167443, | |
| "grad_norm": 6.219781875610352, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.1804, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.027279831395486513, | |
| "grad_norm": 7.571138381958008, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.1309, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.028037604489805582, | |
| "grad_norm": 6.972225666046143, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.5274, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.028795377584124655, | |
| "grad_norm": 1.4634031057357788, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.2254, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.029553150678443725, | |
| "grad_norm": 1.465823769569397, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.1561, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.030310923772762795, | |
| "grad_norm": 1.9862278699874878, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.2085, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.031068696867081864, | |
| "grad_norm": 3.049453020095825, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.9606, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.031826469961400934, | |
| "grad_norm": 2.612853527069092, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.5356, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.032584243055720004, | |
| "grad_norm": 4.496172904968262, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.1076, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.033342016150039074, | |
| "grad_norm": 6.122722148895264, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.7963, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03409978924435814, | |
| "grad_norm": 4.462775230407715, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.1375, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03485756233867721, | |
| "grad_norm": 5.868408203125, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.4557, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03561533543299628, | |
| "grad_norm": 8.171089172363281, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.0499, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03637310852731535, | |
| "grad_norm": 6.449460029602051, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.7635, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03713088162163442, | |
| "grad_norm": 8.228046417236328, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.2257, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03788865471595349, | |
| "grad_norm": 10.642376899719238, | |
| "learning_rate": 1e-05, | |
| "loss": 2.1021, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03788865471595349, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5062, | |
| "eval_samples_per_second": 33.195, | |
| "eval_steps_per_second": 8.631, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.95300912644096e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |