| { | |
| "best_metric": 0.6058931946754456, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.21299254526091588, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004259850905218318, | |
| "grad_norm": 0.9056071639060974, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7514, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004259850905218318, | |
| "eval_loss": 1.5612910985946655, | |
| "eval_runtime": 5.8239, | |
| "eval_samples_per_second": 67.824, | |
| "eval_steps_per_second": 8.585, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008519701810436636, | |
| "grad_norm": 1.0584379434585571, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7262, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012779552715654952, | |
| "grad_norm": 1.4639778137207031, | |
| "learning_rate": 6e-05, | |
| "loss": 0.8158, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01703940362087327, | |
| "grad_norm": 1.1897181272506714, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9592, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021299254526091587, | |
| "grad_norm": 1.4072225093841553, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9839, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.025559105431309903, | |
| "grad_norm": 1.473567008972168, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.9557, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.029818956336528223, | |
| "grad_norm": 1.6296859979629517, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.6532, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03407880724174654, | |
| "grad_norm": 1.2023602724075317, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.8162, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.038338658146964855, | |
| "grad_norm": 1.2582991123199463, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.7173, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.042598509052183174, | |
| "grad_norm": 0.9673406481742859, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.6549, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.046858359957401494, | |
| "grad_norm": 0.8178759813308716, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.647, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.051118210862619806, | |
| "grad_norm": 1.2818442583084106, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.6202, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.055378061767838126, | |
| "grad_norm": 1.052995204925537, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.6351, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.059637912673056445, | |
| "grad_norm": 0.7368398904800415, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.5988, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06389776357827476, | |
| "grad_norm": 1.1218278408050537, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.7072, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06815761448349308, | |
| "grad_norm": 1.0739364624023438, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.7453, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0724174653887114, | |
| "grad_norm": 0.820106565952301, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.5605, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07667731629392971, | |
| "grad_norm": 0.9270951747894287, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.648, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08093716719914804, | |
| "grad_norm": 0.9930429458618164, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.7394, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08519701810436635, | |
| "grad_norm": 1.0608173608779907, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8507, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08945686900958466, | |
| "grad_norm": 0.9992531538009644, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.6659, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09371671991480299, | |
| "grad_norm": 0.9413906335830688, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.6771, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0979765708200213, | |
| "grad_norm": 0.9012166261672974, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.6352, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10223642172523961, | |
| "grad_norm": 0.9687148332595825, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.636, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10649627263045794, | |
| "grad_norm": 1.190940022468567, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.883, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10649627263045794, | |
| "eval_loss": 0.6344612240791321, | |
| "eval_runtime": 5.8456, | |
| "eval_samples_per_second": 67.572, | |
| "eval_steps_per_second": 8.553, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11075612353567625, | |
| "grad_norm": 1.2329808473587036, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.8209, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11501597444089456, | |
| "grad_norm": 0.911182165145874, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.6311, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11927582534611289, | |
| "grad_norm": 1.124248743057251, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.622, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1235356762513312, | |
| "grad_norm": 0.9084705710411072, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.5056, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12779552715654952, | |
| "grad_norm": 0.9366480708122253, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.634, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13205537806176784, | |
| "grad_norm": 1.0503653287887573, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.694, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13631522896698617, | |
| "grad_norm": 0.9009410738945007, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.4827, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14057507987220447, | |
| "grad_norm": 1.1687300205230713, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.7158, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1448349307774228, | |
| "grad_norm": 0.9068652987480164, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.5126, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14909478168264112, | |
| "grad_norm": 1.5940452814102173, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8104, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15335463258785942, | |
| "grad_norm": 1.2183023691177368, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.6102, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15761448349307774, | |
| "grad_norm": 1.6368961334228516, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.8406, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16187433439829607, | |
| "grad_norm": 1.4957292079925537, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.8413, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.16613418530351437, | |
| "grad_norm": 1.0769766569137573, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.4668, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1703940362087327, | |
| "grad_norm": 1.3235946893692017, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.7607, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17465388711395102, | |
| "grad_norm": 1.5516222715377808, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.8801, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.17891373801916932, | |
| "grad_norm": 1.559802532196045, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.6937, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18317358892438765, | |
| "grad_norm": 1.502659559249878, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.8395, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.18743343982960597, | |
| "grad_norm": 1.6062182188034058, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.7279, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.19169329073482427, | |
| "grad_norm": 2.240816354751587, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.9803, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1959531416400426, | |
| "grad_norm": 5.78132438659668, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.9435, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.20021299254526093, | |
| "grad_norm": 3.2474586963653564, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.787, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.20447284345047922, | |
| "grad_norm": 4.021317958831787, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.8541, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.20873269435569755, | |
| "grad_norm": 2.8254783153533936, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.7608, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.21299254526091588, | |
| "grad_norm": 5.236809730529785, | |
| "learning_rate": 0.0, | |
| "loss": 0.7803, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21299254526091588, | |
| "eval_loss": 0.6058931946754456, | |
| "eval_runtime": 5.8556, | |
| "eval_samples_per_second": 67.456, | |
| "eval_steps_per_second": 8.539, | |
| "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": 5, | |
| "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": 6803618267136000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |