Invalid JSON:Unexpected token 'N', ..."_metric": NaN,
"be"... is not valid JSON
| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.6257332811888933, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012514665623777864, | |
| "grad_norm": 3.0296430587768555, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7718, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012514665623777864, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4927, | |
| "eval_samples_per_second": 33.497, | |
| "eval_steps_per_second": 8.709, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025029331247555728, | |
| "grad_norm": 2.6776905059814453, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3173, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03754399687133359, | |
| "grad_norm": 2.049504041671753, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.5068, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.050058662495111456, | |
| "grad_norm": 1.9125001430511475, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.0839, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06257332811888933, | |
| "grad_norm": 2.1216201782226562, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.1768, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07508799374266718, | |
| "grad_norm": 2.6879284381866455, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.1485, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08760265936644505, | |
| "grad_norm": 2.6845970153808594, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.2773, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10011732499022291, | |
| "grad_norm": 5.18543004989624, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.5148, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11263199061400078, | |
| "grad_norm": 3.3763484954833984, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.0925, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12514665623777865, | |
| "grad_norm": 2.664220094680786, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.9021, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13766132186155652, | |
| "grad_norm": 4.278801441192627, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.3248, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15017598748533437, | |
| "grad_norm": 2.7003016471862793, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.1808, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16269065310911224, | |
| "grad_norm": 1.9050196409225464, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.3947, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1752053187328901, | |
| "grad_norm": 2.221489906311035, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.4116, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.18771998435666798, | |
| "grad_norm": 2.0264992713928223, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.9157, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20023464998044582, | |
| "grad_norm": 1.619139552116394, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.52, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2127493156042237, | |
| "grad_norm": 1.420589804649353, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.5398, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.22526398122800156, | |
| "grad_norm": 1.607064127922058, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.4449, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23777864685177943, | |
| "grad_norm": 1.704248070716858, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.673, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2502933124755573, | |
| "grad_norm": 1.6400680541992188, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.6934, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26280797809933515, | |
| "grad_norm": 2.4245526790618896, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.2303, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.27532264372311305, | |
| "grad_norm": 2.0330018997192383, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.4898, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2878373093468909, | |
| "grad_norm": 2.172152280807495, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.4093, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.30035197497066873, | |
| "grad_norm": 2.44553804397583, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.4047, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.31286664059444663, | |
| "grad_norm": 3.5043981075286865, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.9017, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31286664059444663, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5407, | |
| "eval_samples_per_second": 32.454, | |
| "eval_steps_per_second": 8.438, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3253813062182245, | |
| "grad_norm": 1.8852589130401611, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.9857, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3378959718420024, | |
| "grad_norm": 1.9653517007827759, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.352, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3504106374657802, | |
| "grad_norm": 1.741631031036377, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.5297, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.36292530308955806, | |
| "grad_norm": 1.4939073324203491, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.1796, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.37543996871333596, | |
| "grad_norm": 1.9613261222839355, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2641, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3879546343371138, | |
| "grad_norm": 2.448169231414795, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.088, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.40046929996089164, | |
| "grad_norm": 1.9696348905563354, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.2429, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.41298396558466954, | |
| "grad_norm": 1.830755591392517, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.3355, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4254986312084474, | |
| "grad_norm": 1.900875210762024, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.2828, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4380132968322253, | |
| "grad_norm": 2.263303518295288, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.1999, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.45052796245600313, | |
| "grad_norm": 2.3293285369873047, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.0375, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.46304262807978097, | |
| "grad_norm": 2.2211854457855225, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.2903, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.47555729370355887, | |
| "grad_norm": 1.6142629384994507, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.9743, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4880719593273367, | |
| "grad_norm": 1.505129098892212, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.8478, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5005866249511146, | |
| "grad_norm": 1.8305461406707764, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.5612, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5131012905748924, | |
| "grad_norm": 1.6045444011688232, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.1132, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5256159561986703, | |
| "grad_norm": 1.7376651763916016, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.1452, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5381306218224482, | |
| "grad_norm": 1.6962471008300781, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.0739, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5506452874462261, | |
| "grad_norm": 1.7979378700256348, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.1389, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5631599530700039, | |
| "grad_norm": 1.698608160018921, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.1921, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5756746186937818, | |
| "grad_norm": 1.2694196701049805, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.6618, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5881892843175597, | |
| "grad_norm": 1.769540786743164, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.9457, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6007039499413375, | |
| "grad_norm": 2.079148292541504, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.996, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6132186155651154, | |
| "grad_norm": 1.7896637916564941, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.9705, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6257332811888933, | |
| "grad_norm": 2.5797500610351562, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6221, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6257332811888933, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5472, | |
| "eval_samples_per_second": 32.316, | |
| "eval_steps_per_second": 8.402, | |
| "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": 1 | |
| } | |
| }, | |
| "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": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |