| { | |
| "best_metric": 1.1387065649032593, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.012809120093506576, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025618240187013155, | |
| "grad_norm": 1.0117958784103394, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8953, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00025618240187013155, | |
| "eval_loss": 3.3035411834716797, | |
| "eval_runtime": 1.3216, | |
| "eval_samples_per_second": 37.834, | |
| "eval_steps_per_second": 9.837, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005123648037402631, | |
| "grad_norm": 3.5799102783203125, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9788, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007685472056103946, | |
| "grad_norm": 2.472435474395752, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.9668, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010247296074805262, | |
| "grad_norm": 2.5880753993988037, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.7071, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012809120093506578, | |
| "grad_norm": 3.2060391902923584, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.4239, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001537094411220789, | |
| "grad_norm": 2.78033447265625, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2182, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017932768130909207, | |
| "grad_norm": 3.5117530822753906, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.9991, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0020494592149610524, | |
| "grad_norm": 49.99619674682617, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.158, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002305641616831184, | |
| "grad_norm": 14.32833194732666, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.781, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025618240187013155, | |
| "grad_norm": 5.2996296882629395, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.5104, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028180064205714467, | |
| "grad_norm": 4.237436771392822, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.3103, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003074188822441578, | |
| "grad_norm": 3.8762218952178955, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.1729, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0033303712243117098, | |
| "grad_norm": 1.1300048828125, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.6434, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0035865536261818413, | |
| "grad_norm": 2.842411994934082, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.3702, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003842736028051973, | |
| "grad_norm": 1.7373723983764648, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.0943, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004098918429922105, | |
| "grad_norm": 1.6425620317459106, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.6383, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004355100831792236, | |
| "grad_norm": 1.6332066059112549, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.3914, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004611283233662368, | |
| "grad_norm": 1.2231783866882324, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.3286, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0048674656355324995, | |
| "grad_norm": 1.177355170249939, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.1223, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005123648037402631, | |
| "grad_norm": 1.1488226652145386, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.0321, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005379830439272763, | |
| "grad_norm": 0.7047779560089111, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.9133, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005636012841142893, | |
| "grad_norm": 0.6960715055465698, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.8929, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005892195243013025, | |
| "grad_norm": 0.8420125246047974, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.818, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006148377644883156, | |
| "grad_norm": 1.9466040134429932, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.9685, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006404560046753288, | |
| "grad_norm": 1.9700946807861328, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.0097, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006404560046753288, | |
| "eval_loss": 1.1993739604949951, | |
| "eval_runtime": 1.3174, | |
| "eval_samples_per_second": 37.954, | |
| "eval_steps_per_second": 9.868, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0066607424486234195, | |
| "grad_norm": 0.6878185272216797, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.7723, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006916924850493551, | |
| "grad_norm": 1.156850814819336, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.0832, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007173107252363683, | |
| "grad_norm": 1.2199252843856812, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.6599, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007429289654233814, | |
| "grad_norm": 1.1851943731307983, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.2332, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007685472056103946, | |
| "grad_norm": 1.0575395822525024, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.1859, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007941654457974078, | |
| "grad_norm": 0.8781502842903137, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.1534, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00819783685984421, | |
| "grad_norm": 0.7835288643836975, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.0699, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008454019261714341, | |
| "grad_norm": 0.7258645296096802, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.006, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008710201663584473, | |
| "grad_norm": 0.5958614945411682, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.9268, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008966384065454604, | |
| "grad_norm": 0.6093451380729675, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.8199, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009222566467324736, | |
| "grad_norm": 0.5917091369628906, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.7703, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009478748869194868, | |
| "grad_norm": 1.675472617149353, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.0259, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009734931271064999, | |
| "grad_norm": 0.5305991768836975, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.6949, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00999111367293513, | |
| "grad_norm": 0.7452951669692993, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.2857, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010247296074805262, | |
| "grad_norm": 0.8421163558959961, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.8188, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010503478476675394, | |
| "grad_norm": 0.8257361650466919, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.3073, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010759660878545525, | |
| "grad_norm": 0.7207552790641785, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.138, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011015843280415655, | |
| "grad_norm": 0.6140944957733154, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.1504, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011272025682285787, | |
| "grad_norm": 0.5321956276893616, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.0165, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011528208084155918, | |
| "grad_norm": 0.41653451323509216, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.9307, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01178439048602605, | |
| "grad_norm": 0.396756112575531, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.9256, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012040572887896181, | |
| "grad_norm": 0.4138922691345215, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.8874, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012296755289766313, | |
| "grad_norm": 0.45892012119293213, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.8118, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012552937691636444, | |
| "grad_norm": 0.7600415945053101, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.9194, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.012809120093506576, | |
| "grad_norm": 1.6304396390914917, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9984, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012809120093506576, | |
| "eval_loss": 1.1387065649032593, | |
| "eval_runtime": 1.3363, | |
| "eval_samples_per_second": 37.416, | |
| "eval_steps_per_second": 9.728, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |