| { | |
| "best_metric": 1.8023031949996948, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.7760532150776052, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03547671840354767, | |
| "grad_norm": 12.724061012268066, | |
| "learning_rate": 5e-05, | |
| "loss": 4.6763, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03547671840354767, | |
| "eval_loss": 5.99407958984375, | |
| "eval_runtime": 0.8254, | |
| "eval_samples_per_second": 60.573, | |
| "eval_steps_per_second": 15.749, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07095343680709534, | |
| "grad_norm": 14.900910377502441, | |
| "learning_rate": 0.0001, | |
| "loss": 5.43, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10643015521064302, | |
| "grad_norm": 12.636441230773926, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.617, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1419068736141907, | |
| "grad_norm": 7.304109573364258, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.1331, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17738359201773837, | |
| "grad_norm": 9.609624862670898, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.7081, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21286031042128603, | |
| "grad_norm": 7.860935688018799, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.7118, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24833702882483372, | |
| "grad_norm": 4.936010360717773, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.396, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2838137472283814, | |
| "grad_norm": 10.622501373291016, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.3273, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.31929046563192903, | |
| "grad_norm": 10.488219261169434, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.3307, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.35476718403547675, | |
| "grad_norm": 3.8527562618255615, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.0453, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 6.716139793395996, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.1969, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.42572062084257206, | |
| "grad_norm": 6.578034400939941, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.8983, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4611973392461197, | |
| "grad_norm": 3.6023688316345215, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.8527, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.49667405764966743, | |
| "grad_norm": 2.803765296936035, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.9696, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.532150776053215, | |
| "grad_norm": 2.6298434734344482, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.8644, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5676274944567627, | |
| "grad_norm": 2.5654900074005127, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.9544, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6031042128603105, | |
| "grad_norm": 2.001566171646118, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.8754, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6385809312638581, | |
| "grad_norm": 2.398838520050049, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.9237, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6740576496674058, | |
| "grad_norm": 2.143735885620117, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.7714, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7095343680709535, | |
| "grad_norm": 1.954122543334961, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.7033, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7450110864745011, | |
| "grad_norm": 2.0909314155578613, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.7329, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 1.8812015056610107, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.713, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8159645232815964, | |
| "grad_norm": 1.8215457201004028, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.8447, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8514412416851441, | |
| "grad_norm": 2.0654754638671875, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.8287, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8869179600886918, | |
| "grad_norm": 2.009129047393799, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.7592, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8869179600886918, | |
| "eval_loss": 1.844842553138733, | |
| "eval_runtime": 0.8732, | |
| "eval_samples_per_second": 57.26, | |
| "eval_steps_per_second": 14.888, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9223946784922394, | |
| "grad_norm": 2.189703941345215, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.6794, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9578713968957872, | |
| "grad_norm": 2.097830295562744, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.7231, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9933481152993349, | |
| "grad_norm": 2.1691596508026123, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.7862, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0310421286031042, | |
| "grad_norm": 5.34002685546875, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.0291, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0665188470066518, | |
| "grad_norm": 1.8050270080566406, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.6163, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1019955654101996, | |
| "grad_norm": 1.752409815788269, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.5963, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1374722838137472, | |
| "grad_norm": 1.962044358253479, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.3796, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1729490022172948, | |
| "grad_norm": 2.2525737285614014, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.5301, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2084257206208426, | |
| "grad_norm": 1.9950754642486572, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.5008, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2439024390243902, | |
| "grad_norm": 2.0618607997894287, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.4928, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2793791574279378, | |
| "grad_norm": 2.0370469093322754, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.4469, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3148558758314857, | |
| "grad_norm": 2.0353357791900635, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.4729, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3503325942350333, | |
| "grad_norm": 2.2255871295928955, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.5445, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3858093126385809, | |
| "grad_norm": 2.0936543941497803, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.5054, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4212860310421287, | |
| "grad_norm": 2.298006534576416, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.4022, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4567627494456763, | |
| "grad_norm": 2.1407575607299805, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.426, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.492239467849224, | |
| "grad_norm": 2.340196132659912, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.504, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5277161862527717, | |
| "grad_norm": 2.015380620956421, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.3684, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5631929046563193, | |
| "grad_norm": 2.134154796600342, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.5322, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.598669623059867, | |
| "grad_norm": 2.0442440509796143, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.525, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6341463414634148, | |
| "grad_norm": 1.9398062229156494, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.3588, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6696230598669624, | |
| "grad_norm": 2.1052966117858887, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.3799, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.70509977827051, | |
| "grad_norm": 2.180793523788452, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.3701, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7405764966740578, | |
| "grad_norm": 2.127793312072754, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.4814, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7760532150776052, | |
| "grad_norm": 2.040327548980713, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3444, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7760532150776052, | |
| "eval_loss": 1.8023031949996948, | |
| "eval_runtime": 0.8606, | |
| "eval_samples_per_second": 58.101, | |
| "eval_steps_per_second": 15.106, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.589463780163584e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |