| { | |
| "best_metric": 2.524803876876831, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.9975062344139651, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0199501246882793, | |
| "grad_norm": 45.49735641479492, | |
| "learning_rate": 5e-05, | |
| "loss": 53.0963, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0199501246882793, | |
| "eval_loss": 6.295931816101074, | |
| "eval_runtime": 4.7388, | |
| "eval_samples_per_second": 10.551, | |
| "eval_steps_per_second": 2.743, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0399002493765586, | |
| "grad_norm": 69.68228912353516, | |
| "learning_rate": 0.0001, | |
| "loss": 80.9094, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.059850374064837904, | |
| "grad_norm": 82.03534698486328, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 90.1925, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0798004987531172, | |
| "grad_norm": 67.20115661621094, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 79.4407, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09975062344139651, | |
| "grad_norm": 56.21864700317383, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 77.7849, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11970074812967581, | |
| "grad_norm": 51.309059143066406, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 69.1449, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1396508728179551, | |
| "grad_norm": 54.87021255493164, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 65.2283, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1596009975062344, | |
| "grad_norm": 52.90449142456055, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 60.9675, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.17955112219451372, | |
| "grad_norm": 47.95082092285156, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 53.2583, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.19950124688279303, | |
| "grad_norm": 50.49687576293945, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 52.856, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2194513715710723, | |
| "grad_norm": 66.57158660888672, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 46.9209, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.23940149625935161, | |
| "grad_norm": 88.94745635986328, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 51.286, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2593516209476309, | |
| "grad_norm": 141.8347930908203, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 56.7859, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2793017456359102, | |
| "grad_norm": 143.94796752929688, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 58.1637, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.29925187032418954, | |
| "grad_norm": 75.26687622070312, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 53.1067, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3192019950124688, | |
| "grad_norm": 46.707462310791016, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 50.0477, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.33915211970074816, | |
| "grad_norm": 36.482765197753906, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 51.0176, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.35910224438902744, | |
| "grad_norm": 36.98707962036133, | |
| "learning_rate": 7.75e-05, | |
| "loss": 45.1953, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3790523690773067, | |
| "grad_norm": 41.583335876464844, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 46.8739, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.39900249376558605, | |
| "grad_norm": 42.5671272277832, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 46.5591, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.41895261845386533, | |
| "grad_norm": 41.880489349365234, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 41.2506, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4389027431421446, | |
| "grad_norm": 37.36667251586914, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 42.2529, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.45885286783042395, | |
| "grad_norm": 47.602298736572266, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 43.1833, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.47880299251870323, | |
| "grad_norm": 48.13751220703125, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 42.4669, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.49875311720698257, | |
| "grad_norm": 34.0434684753418, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 41.8652, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.49875311720698257, | |
| "eval_loss": 2.8791680335998535, | |
| "eval_runtime": 5.0723, | |
| "eval_samples_per_second": 9.857, | |
| "eval_steps_per_second": 2.563, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5187032418952618, | |
| "grad_norm": 97.8256607055664, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 45.9514, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5386533665835411, | |
| "grad_norm": 77.4750747680664, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 49.0584, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5586034912718204, | |
| "grad_norm": 82.93704223632812, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 52.5617, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5785536159600998, | |
| "grad_norm": 80.46338653564453, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 50.8175, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5985037406483791, | |
| "grad_norm": 71.76152038574219, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 50.5376, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6184538653366584, | |
| "grad_norm": 59.59098815917969, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 43.2234, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6384039900249376, | |
| "grad_norm": 50.75923538208008, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 47.6493, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6583541147132169, | |
| "grad_norm": 35.34622573852539, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 42.2573, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6783042394014963, | |
| "grad_norm": 31.810007095336914, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 37.8188, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6982543640897756, | |
| "grad_norm": 36.85839080810547, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 41.3035, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7182044887780549, | |
| "grad_norm": 74.53050994873047, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 39.4763, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7381546134663342, | |
| "grad_norm": 22.744556427001953, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 39.0481, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7581047381546134, | |
| "grad_norm": 54.96494674682617, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 37.8641, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7780548628428927, | |
| "grad_norm": 26.874835968017578, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 40.2222, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7980049875311721, | |
| "grad_norm": 24.924524307250977, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 40.2855, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8179551122194514, | |
| "grad_norm": 23.27718162536621, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 43.3991, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8379052369077307, | |
| "grad_norm": 22.71009635925293, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 44.0086, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.85785536159601, | |
| "grad_norm": 22.148950576782227, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 43.2824, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8778054862842892, | |
| "grad_norm": 20.373430252075195, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 42.4885, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8977556109725686, | |
| "grad_norm": 32.94357681274414, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 42.1664, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9177057356608479, | |
| "grad_norm": 30.303119659423828, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 38.0548, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9376558603491272, | |
| "grad_norm": 38.92861557006836, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 40.9199, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9576059850374065, | |
| "grad_norm": 53.80879211425781, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 44.9965, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9775561097256857, | |
| "grad_norm": 68.30091094970703, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 40.5606, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9975062344139651, | |
| "grad_norm": 24.644094467163086, | |
| "learning_rate": 1e-05, | |
| "loss": 37.6299, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9975062344139651, | |
| "eval_loss": 2.524803876876831, | |
| "eval_runtime": 5.0778, | |
| "eval_samples_per_second": 9.847, | |
| "eval_steps_per_second": 2.56, | |
| "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": 1.8310908287647744e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |