| { | |
| "best_metric": 0.46706730127334595, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.9850746268656714, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 3.5658681392669678, | |
| "learning_rate": 5e-05, | |
| "loss": 4.02, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "eval_loss": 4.0691962242126465, | |
| "eval_runtime": 1.0155, | |
| "eval_samples_per_second": 49.236, | |
| "eval_steps_per_second": 12.801, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 3.6752662658691406, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0386, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 3.4304988384246826, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.934, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 3.4331161975860596, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.4025, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 2.86146879196167, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.933, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 3.29848575592041, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.5313, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 3.4076099395751953, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.1612, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 3.4900922775268555, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.7945, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 3.1352570056915283, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.592, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 2.8966023921966553, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.3648, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6567164179104478, | |
| "grad_norm": 2.6492793560028076, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.1024, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 2.408184766769409, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.0192, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7761194029850746, | |
| "grad_norm": 2.837423086166382, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.0637, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.835820895522388, | |
| "grad_norm": 2.4028074741363525, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.9924, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 2.0693113803863525, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.8807, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 2.3545737266540527, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.8494, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0149253731343284, | |
| "grad_norm": 2.4344043731689453, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.0704, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0746268656716418, | |
| "grad_norm": 1.97946035861969, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.8242, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1343283582089552, | |
| "grad_norm": 1.3914319276809692, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.7583, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "grad_norm": 1.658143401145935, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7018, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2537313432835822, | |
| "grad_norm": 1.53111732006073, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.7096, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.3134328358208955, | |
| "grad_norm": 1.038472056388855, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6786, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.373134328358209, | |
| "grad_norm": 0.9662055373191833, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.6339, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "grad_norm": 1.0910096168518066, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.6243, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4925373134328357, | |
| "grad_norm": 1.071887493133545, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.6414, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4925373134328357, | |
| "eval_loss": 0.6234197616577148, | |
| "eval_runtime": 0.5477, | |
| "eval_samples_per_second": 91.288, | |
| "eval_steps_per_second": 23.735, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5522388059701493, | |
| "grad_norm": 1.2679883241653442, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6249, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6119402985074627, | |
| "grad_norm": 1.1665154695510864, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6001, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.671641791044776, | |
| "grad_norm": 1.2832471132278442, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.5607, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7313432835820897, | |
| "grad_norm": 1.2532341480255127, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.605, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7910447761194028, | |
| "grad_norm": 0.9181452989578247, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.5312, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8507462686567164, | |
| "grad_norm": 1.0095727443695068, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.5491, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.9104477611940298, | |
| "grad_norm": 1.0146640539169312, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.4843, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.9701492537313432, | |
| "grad_norm": 1.0201386213302612, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.5598, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.029850746268657, | |
| "grad_norm": 1.2566463947296143, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.5806, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.08955223880597, | |
| "grad_norm": 1.1451953649520874, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.5185, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.1492537313432836, | |
| "grad_norm": 1.1555943489074707, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.4616, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.208955223880597, | |
| "grad_norm": 1.0790717601776123, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.4342, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.2686567164179103, | |
| "grad_norm": 0.8986020088195801, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.4887, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.328358208955224, | |
| "grad_norm": 0.936444878578186, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4496, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.388059701492537, | |
| "grad_norm": 0.9543986916542053, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4424, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4477611940298507, | |
| "grad_norm": 1.245566725730896, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.4677, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.5074626865671643, | |
| "grad_norm": 0.9546048641204834, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4777, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.5671641791044775, | |
| "grad_norm": 0.859067440032959, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.4685, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.626865671641791, | |
| "grad_norm": 0.9560415148735046, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.4458, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.6865671641791042, | |
| "grad_norm": 1.2271660566329956, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4315, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.746268656716418, | |
| "grad_norm": 1.0750199556350708, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.4651, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8059701492537314, | |
| "grad_norm": 1.072292685508728, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.4574, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.8656716417910446, | |
| "grad_norm": 0.9041290283203125, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.4365, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.925373134328358, | |
| "grad_norm": 0.9276415109634399, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.4438, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.9850746268656714, | |
| "grad_norm": 0.9930983781814575, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5146, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.9850746268656714, | |
| "eval_loss": 0.46706730127334595, | |
| "eval_runtime": 0.5399, | |
| "eval_samples_per_second": 92.605, | |
| "eval_steps_per_second": 24.077, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 7.83042868150272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |