| { | |
| "best_metric": 0.9530366063117981, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.010930753675465924, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021861507350931847, | |
| "grad_norm": 16.371868133544922, | |
| "learning_rate": 2e-05, | |
| "loss": 7.5287, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021861507350931847, | |
| "eval_loss": 2.686614751815796, | |
| "eval_runtime": 563.5532, | |
| "eval_samples_per_second": 13.67, | |
| "eval_steps_per_second": 1.709, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00043723014701863694, | |
| "grad_norm": 17.845510482788086, | |
| "learning_rate": 4e-05, | |
| "loss": 7.593, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006558452205279554, | |
| "grad_norm": 12.47093677520752, | |
| "learning_rate": 6e-05, | |
| "loss": 7.3002, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008744602940372739, | |
| "grad_norm": 13.079608917236328, | |
| "learning_rate": 8e-05, | |
| "loss": 6.6762, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010930753675465923, | |
| "grad_norm": 11.010284423828125, | |
| "learning_rate": 0.0001, | |
| "loss": 6.5342, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013116904410559109, | |
| "grad_norm": 9.200610160827637, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 5.993, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015303055145652292, | |
| "grad_norm": 8.311590194702148, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 5.8221, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0017489205880745478, | |
| "grad_norm": 7.400461196899414, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 5.6104, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001967535661583866, | |
| "grad_norm": 8.270915985107422, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 5.6882, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0021861507350931847, | |
| "grad_norm": 6.692793369293213, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 5.659, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002404765808602503, | |
| "grad_norm": 5.965865135192871, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 5.3667, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0026233808821118218, | |
| "grad_norm": 6.994250297546387, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 5.6383, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00284199595562114, | |
| "grad_norm": 6.316064834594727, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 5.3244, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0030606110291304584, | |
| "grad_norm": 6.096770286560059, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 5.3306, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003279226102639777, | |
| "grad_norm": 7.069843769073486, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 5.2282, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0034978411761490955, | |
| "grad_norm": 6.554002285003662, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 4.9578, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003716456249658414, | |
| "grad_norm": 6.956838130950928, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 4.8354, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003935071323167732, | |
| "grad_norm": 6.20825719833374, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 4.946, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004153686396677051, | |
| "grad_norm": 6.226200580596924, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 4.833, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004372301470186369, | |
| "grad_norm": 6.16742467880249, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.9317, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004590916543695688, | |
| "grad_norm": 6.157779216766357, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 4.8334, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004809531617205006, | |
| "grad_norm": 6.149705410003662, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 4.8967, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005028146690714325, | |
| "grad_norm": 6.403168201446533, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 4.769, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0052467617642236435, | |
| "grad_norm": 5.821649551391602, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 4.8568, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005465376837732962, | |
| "grad_norm": 5.976842403411865, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 4.6424, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005465376837732962, | |
| "eval_loss": 0.9530366063117981, | |
| "eval_runtime": 568.623, | |
| "eval_samples_per_second": 13.549, | |
| "eval_steps_per_second": 1.694, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00568399191124228, | |
| "grad_norm": 6.021666049957275, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 4.9027, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005902606984751598, | |
| "grad_norm": 5.490301132202148, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 4.7596, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006121222058260917, | |
| "grad_norm": 5.370169162750244, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 4.3889, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006339837131770235, | |
| "grad_norm": 5.458473205566406, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 4.9394, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006558452205279554, | |
| "grad_norm": 5.836726665496826, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 4.5724, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0067770672787888725, | |
| "grad_norm": 5.416110038757324, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 4.0619, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006995682352298191, | |
| "grad_norm": 6.177218914031982, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 4.3057, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00721429742580751, | |
| "grad_norm": 6.053664207458496, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 4.3497, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.007432912499316828, | |
| "grad_norm": 6.283422470092773, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 4.1713, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007651527572826147, | |
| "grad_norm": 8.608915328979492, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.447, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007870142646335464, | |
| "grad_norm": 12.189590454101562, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.1306, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.008088757719844783, | |
| "grad_norm": 9.416007995605469, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.034, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.008307372793354102, | |
| "grad_norm": 9.622803688049316, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.9917, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00852598786686342, | |
| "grad_norm": 8.2776517868042, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.0554, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.008744602940372739, | |
| "grad_norm": 9.129863739013672, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.9946, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008963218013882057, | |
| "grad_norm": 8.29858684539795, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.0052, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.009181833087391376, | |
| "grad_norm": 6.464522838592529, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.955, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.009400448160900694, | |
| "grad_norm": 9.313206672668457, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.069, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009619063234410013, | |
| "grad_norm": 11.673344612121582, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.1005, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009837678307919331, | |
| "grad_norm": 12.842467308044434, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.0141, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01005629338142865, | |
| "grad_norm": 8.365056037902832, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.0543, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.010274908454937969, | |
| "grad_norm": 7.161728382110596, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.8468, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.010493523528447287, | |
| "grad_norm": 7.479653358459473, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.8851, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.010712138601956606, | |
| "grad_norm": 11.35835075378418, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.8487, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.010930753675465924, | |
| "grad_norm": 8.02046012878418, | |
| "learning_rate": 0.0, | |
| "loss": 0.8637, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010930753675465924, | |
| "eval_loss": 0.9873353838920593, | |
| "eval_runtime": 568.6292, | |
| "eval_samples_per_second": 13.548, | |
| "eval_steps_per_second": 1.694, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.11922310751191e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |