| { | |
| "best_metric": 0.983562707901001, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04609888210210902, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009219776420421805, | |
| "grad_norm": 0.3132103383541107, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8784, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009219776420421805, | |
| "eval_loss": 1.2618366479873657, | |
| "eval_runtime": 4.7601, | |
| "eval_samples_per_second": 10.504, | |
| "eval_steps_per_second": 2.731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001843955284084361, | |
| "grad_norm": 0.38565558195114136, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0075, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0027659329261265414, | |
| "grad_norm": 0.3640933334827423, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.0473, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003687910568168722, | |
| "grad_norm": 0.2646391987800598, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.0058, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004609888210210902, | |
| "grad_norm": 0.2934136986732483, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.0938, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005531865852253083, | |
| "grad_norm": 0.29494020342826843, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.0948, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0064538434942952635, | |
| "grad_norm": 0.24726805090904236, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.1273, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007375821136337444, | |
| "grad_norm": 0.2277357578277588, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.13, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008297798778379625, | |
| "grad_norm": 0.23507241904735565, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.2183, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009219776420421804, | |
| "grad_norm": 0.24017858505249023, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.2373, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010141754062463985, | |
| "grad_norm": 0.2978171110153198, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.3909, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011063731704506165, | |
| "grad_norm": 0.3846418559551239, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.6288, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011985709346548346, | |
| "grad_norm": 0.20880825817584991, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.8443, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012907686988590527, | |
| "grad_norm": 0.19771325588226318, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.8533, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013829664630632708, | |
| "grad_norm": 0.1600092202425003, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.8067, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014751642272674888, | |
| "grad_norm": 0.1727035790681839, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.8908, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01567361991471707, | |
| "grad_norm": 0.16494901478290558, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.9216, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01659559755675925, | |
| "grad_norm": 0.14137199521064758, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.9524, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01751757519880143, | |
| "grad_norm": 0.1514618694782257, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.025, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.018439552840843608, | |
| "grad_norm": 0.15840674936771393, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.0296, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01936153048288579, | |
| "grad_norm": 0.1647600531578064, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.0706, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02028350812492797, | |
| "grad_norm": 0.1615896075963974, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.178, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02120548576697015, | |
| "grad_norm": 0.20074398815631866, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.2397, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02212746340901233, | |
| "grad_norm": 0.25603824853897095, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.3702, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02304944105105451, | |
| "grad_norm": 0.3893183171749115, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.6295, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02304944105105451, | |
| "eval_loss": 1.0104379653930664, | |
| "eval_runtime": 3.0597, | |
| "eval_samples_per_second": 16.342, | |
| "eval_steps_per_second": 4.249, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023971418693096692, | |
| "grad_norm": 0.1446598619222641, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7335, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.024893396335138873, | |
| "grad_norm": 0.16403502225875854, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.7692, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.025815373977181054, | |
| "grad_norm": 0.18820112943649292, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.8644, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.026737351619223235, | |
| "grad_norm": 0.19414544105529785, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.8491, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.027659329261265415, | |
| "grad_norm": 0.16365379095077515, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.9683, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.028581306903307596, | |
| "grad_norm": 0.16391751170158386, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.0038, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.029503284545349777, | |
| "grad_norm": 0.15574006736278534, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.9643, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.030425262187391954, | |
| "grad_norm": 0.1687910556793213, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.0626, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03134723982943414, | |
| "grad_norm": 0.18482720851898193, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.1207, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03226921747147632, | |
| "grad_norm": 0.22824575006961823, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.1453, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0331911951135185, | |
| "grad_norm": 0.23433442413806915, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.2672, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03411317275556068, | |
| "grad_norm": 0.34760910272598267, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.4551, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03503515039760286, | |
| "grad_norm": 0.09731561690568924, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.7236, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.035957128039645035, | |
| "grad_norm": 0.09190354496240616, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.7556, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.036879105681687216, | |
| "grad_norm": 0.11261679977178574, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.8309, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0378010833237294, | |
| "grad_norm": 0.13187381625175476, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.7903, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03872306096577158, | |
| "grad_norm": 0.13414575159549713, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.9099, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03964503860781376, | |
| "grad_norm": 0.1466209590435028, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.8833, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04056701624985594, | |
| "grad_norm": 0.1413664072751999, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.9864, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04148899389189812, | |
| "grad_norm": 0.13641425967216492, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.069, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0424109715339403, | |
| "grad_norm": 0.14130431413650513, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.0774, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04333294917598248, | |
| "grad_norm": 0.1519637107849121, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.1186, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04425492681802466, | |
| "grad_norm": 0.18100306391716003, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.2517, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04517690446006684, | |
| "grad_norm": 0.21845021843910217, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.4335, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04609888210210902, | |
| "grad_norm": 0.4103708267211914, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6454, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04609888210210902, | |
| "eval_loss": 0.983562707901001, | |
| "eval_runtime": 3.0034, | |
| "eval_samples_per_second": 16.648, | |
| "eval_steps_per_second": 4.328, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |